diff --git a/experimental/builder/test/test_ck_factory_grouped_convolution_forward_clamp.cpp b/experimental/builder/test/test_ck_factory_grouped_convolution_forward_clamp.cpp index e3182cc53d..3c6cd72eec 100644 --- a/experimental/builder/test/test_ck_factory_grouped_convolution_forward_clamp.cpp +++ b/experimental/builder/test/test_ck_factory_grouped_convolution_forward_clamp.cpp @@ -10,17 +10,27 @@ using ck_tile::test::InstancesMatch; namespace { + using InLayout = ck::tensor_layout::convolution::NDHWGC; using WeiLayout = ck::tensor_layout::convolution::GKZYXC; using OutLayout = ck::tensor_layout::convolution::NDHWGK; using DsLayout = ck::Tuple<>; +using ck::tensor_layout::convolution::NHWGC; +using ck::tensor_layout::convolution::GKYXC; +using ck::tensor_layout::convolution::NHWGK; +using ck::tensor_layout::convolution::NDHWGC; +using ck::tensor_layout::convolution::GKZYXC; +using ck::tensor_layout::convolution::NDHWGK; + +using DsLayout = ck::Tuple<>; + using ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD; using ck::tensor_operation::element_wise::Clamp; using ck::tensor_operation::element_wise::PassThrough; -template +template using DeviceOp = DeviceGroupedConvFwdMultipleABD; + using DeviceOp = ::DeviceOp<2, float, NHWGC, GKYXC, NHWGK>; constexpr static auto expected = { // clang-format off - "" + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>" + // clang-format on + }; +}; + +struct F32_3D +{ + using DeviceOp = ::DeviceOp<3, float, NDHWGC, GKZYXC, NDHWGK>; + + constexpr static auto expected = { + // clang-format off + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp32,fp32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp32,fp32>" + // clang-format on + }; +}; + +struct F32_TF32_2D +{ + using DeviceOp = ::DeviceOp<2, float, NHWGC, GKYXC, NHWGK, ck::tf32_t>; + + constexpr static auto expected = { + // clang-format off + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>" // clang-format on }; }; @@ -63,54 +418,831 @@ struct F32_3D struct F32_TF32_3D { - using DeviceOp = ::DeviceOp<3, float, ck::tf32_t>; + using DeviceOp = ::DeviceOp<3, float, NDHWGC, GKZYXC, NDHWGK, ck::tf32_t>; constexpr static auto expected = { // clang-format off - "" + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Interwave,v2,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,tf32,tf32>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp32,fp32,fp32,fp32,EmptyTuple,fp32,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,4,4,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,tf32,tf32>" + // clang-format on + }; +}; + +struct F16_2D +{ + using DeviceOp = ::DeviceOp<2, ck::half_t, NHWGC, GKYXC, NHWGK>; + + constexpr static auto expected = { + // clang-format off + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>" // clang-format on }; }; struct F16_3D { - using DeviceOp = ::DeviceOp<3, ck::half_t>; + using DeviceOp = ::DeviceOp<3, ck::half_t, NDHWGC, GKZYXC, NDHWGK>; constexpr static auto expected = { // clang-format off - "" + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,fp16,fp16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,fp16,fp16,fp32,fp16,EmptyTuple,fp16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,fp16,fp16>" + // clang-format on + }; +}; + +struct BF16_2D +{ + using DeviceOp = ::DeviceOp<2, ck::bhalf_t, NHWGC, GKYXC, NHWGK>; + + constexpr static auto expected = { + // clang-format off + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<2,NHWGC,GKYXC,EmptyTuple,NHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>" // clang-format on }; }; struct BF16_3D { - using DeviceOp = ::DeviceOp<3, ck::bhalf_t>; + using DeviceOp = ::DeviceOp<3, ck::bhalf_t, NDHWGC, GKZYXC, NDHWGK>; constexpr static auto expected = { // clang-format off - "" - // clang-format on - }; -}; - -struct INT8_3D -{ - using DeviceOp = ::DeviceOp<3, int8_t>; - - constexpr static auto expected = { - // clang-format off - "" + "", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Default,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,16,64,8,8,16,16,4,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,128,32,64,8,8,32,32,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,128,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,32,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,16,64,64,8,8,16,16,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,128,64,8,8,32,32,1,2,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,16,64,8,8,16,16,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,32,64,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,16,64,8,8,16,16,2,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,128,64,32,64,8,8,32,32,1,1,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,32,8,8,32,32,2,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,128,64,8,8,32,32,2,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,256,32,8,8,32,32,2,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,128,64,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,16,256,64,8,8,16,16,1,4,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,224,256,64,8,8,16,16,7,8,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,128,32,8,8,32,32,4,2,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,16,64,8,8,16,16,4,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,16,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),2,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,224,64,8,8,16,16,8,7,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,2,1,Seq(1,64,1,4),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,16,16,8,8,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,2,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v4,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,256,32,8,8,32,32,4,4,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(4,64,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v5,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,256,32,64,8,8,32,32,2,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,32,256,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,16),8,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,64,128,64,8,8,32,32,1,2,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,256,64,64,64,8,8,32,32,1,1,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,32,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,32,1,8),8,Intrawave,v3,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,128,8,8,16,16,1,1,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(16,4,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Interwave,v2,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v1,bf16,bf16>", + "DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<3,NDHWGC,GKZYXC,EmptyTuple,NDHWGK,bf16,bf16,fp32,bf16,EmptyTuple,bf16,PassThrough,PassThrough,Clamp,Filter1x1Stride1Pad0,MNKPadding,64,16,16,64,8,8,16,16,1,1,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,Seq(8,8,1),Seq(1,0,2),Seq(1,0,2),2,8,8,0,1,1,Seq(1,16,1,4),4,Intrawave,v2,bf16,bf16>" // clang-format on }; }; -using TestTypes = ::testing::Types; + BF16_3D>; TYPED_TEST_SUITE(CkFactoryTestBilinearFwd, TestTypes);