diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp
index 059f961ece..044866dac2 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp
@@ -24,6 +24,7 @@ using BF8 = ck::bf8_t;
 using BF16 = ck::bhalf_t;
 using F16  = ck::half_t;
 using F32  = float;
+using I8   = int8_t;
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;
@@ -61,22 +62,30 @@ template <index_t NDimSpatial,
           typename OutElementOp = PassThrough>
 using device_grouped_conv_fwd_wmma_cshufflev3_bf16_comp_instances = std::tuple<
     // clang-format off
-          //########################################|     NumDim|       A|       B|          Ds|       E| AData| BData| AccData| CShuffle|             Ds| EData|           A|           B|          CDE|    ConvForward|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
-          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|  Type|  Type|    Type| DataType|       DataType|  Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization| Prefetch|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines
-          //########################################|           |        |        |            |        |      |      |        |         |               |      |   Operation|   Operation|    Operation|               |               |    Stage|      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|
-          //########################################|           |        |        |            |        |      |      |        |         |               |      |            |            |             |               |               | TODO: ??|      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |
+          //########################################|     NumDim|       A|       B|          Ds|       E| AData| BData| AccData| CShuffle|             Ds| EData|           A|           B|          CDE|    ConvForward|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|                   Pipeline scheduler |            Pipeline version |
+          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|  Type|  Type|    Type| DataType|       DataType|  Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
     // Compute friendly
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,             256,   256,   256,    32,   8,   8,   16,   16,     8,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,  32,   32,    2,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v4>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,  32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v4>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,  32,   32,    4,    4,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,  32,   32,    4,    4,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v5>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,  32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,  32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,  32,   32,    2,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,    64,    64,   8,   8,  32,   32,    2,    1,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   128,    64,   8,   8,  32,   32,    1,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
-    // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,  32,   32,    1,    1,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,    S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,              8,              8,          0,          1,           1,                   S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     8,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
+    ,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     8,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,    64,    64,   8,   8,   16,   16,     4,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   128,    64,   8,   8,   16,   16,     2,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    // "2x" instances
+    // DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,  16,  16,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1> // Assert broken
+    // "part 2" instances
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     4,     8,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            2,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    // AGPR Spill when use permuted lds layout. so, use padding for these two.
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   224,   256,    64,   8,   8,   16,   16,     7,     4,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            2,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   224,    64,   8,   8,   16,   16,     4,     7,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            2,            1,               S<1, 64, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>
+#endif
     // clang-format on
     >;
 
@@ -90,11 +99,26 @@ template <index_t NDimSpatial,
           typename OutElementOp = PassThrough>
 using device_grouped_conv_fwd_wmma_cshufflev3_f16_comp_instances = std::tuple<
     // clang-format off
-          //########################################|     NumDim|       A|       B|          Ds|       E| AData| BData| AccData| CShuffle|             Ds| EData|           A|           B|          CDE|    ConvForward|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
-          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|  Type|  Type|    Type| DataType|       DataType|  Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization| Prefetch|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines
-          //########################################|           |        |        |            |        |      |      |        |         |               |      |   Operation|   Operation|    Operation|               |               |    Stage|      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|
-          //########################################|           |        |        |            |        |      |      |        |         |               |      |            |            |             |               |               | TODO: ??|      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,             256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+          //########################################|     NumDim|       A|       B|          Ds|       E| AData| BData| AccData| CShuffle|             Ds| EData|           A|           B|          CDE|    ConvForward|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|                   Pipeline scheduler |            Pipeline version |
+          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|  Type|  Type|    Type| DataType|       DataType|  Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
+    ,
+    // "2x" instances
+    // DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,  16,  16,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          1,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>, // Assert broken
+    // "part 2" instances
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     8,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     4,     8,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            2,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    // AGPR Spill when use permuted lds layout. so, use padding for these two.
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   224,   256,    64,   8,   8,   16,   16,     7,     4,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            2,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   224,    64,   8,   8,   16,   16,     4,     7,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           2,            1,               S<1, 64, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,          0,           1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>
+#endif
     // clang-format on
     >;
 
@@ -108,11 +132,24 @@ template <index_t NDimSpatial,
           typename OutElementOp = PassThrough>
 using device_grouped_conv_fwd_wmma_cshufflev3_int8_comp_instances = std::tuple<
     // clang-format off
-          //########################################|     NumDim|       A|       B|          Ds|       E|  AData|  BData| AccData| CShuffle|             Ds|  EData|           A|           B|          CDE|    ConvForward|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
-          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|   Type|   Type|    Type| DataType|       DataType|   Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization| Prefetch|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines
-          //########################################|           |        |        |            |        |       |       |        |         |               |       |   Operation|   Operation|    Operation|               |               |    Stage|      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|
-          //########################################|           |        |        |            |        |       |       |        |         |               |       |            |            |             |               |               | TODO: ??|      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout, int8_t, int8_t, int32_t,   int8_t,    DsDataTypes, int8_t, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,             256,   128,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8,  BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+          //########################################|     NumDim|       A|       B|          Ds|       E| AData| BData| AccData| CShuffle|             Ds| EData|           A|           B|          CDE|    ConvForward|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MWmma| NWmma|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|     CShuffle|     CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|                   Pipeline scheduler |            Pipeline version |
+          //########################################|    Spatial|  Layout|  Layout|      Layout|  Layout|  Type|  Type|    Type| DataType|       DataType|  Type| Elementwise| Elementwise|  Elementwise| Specialization| Specialization|  Size| Block| Block| Block|    |    | WMMA| WMMA|   Per|   Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
+          //########################################|           |        |        |            |        |      |      |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
+    ,
+    // "2x" instances
+    // DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,   128,  32,  32,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,            1,            1,               S<1, 64, 1, 4>,              16, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>, // Assert broken
+    // "part 2" instances
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     8,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   256,    32,   8,   8,   16,   16,     4,     8,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            2,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    // AGPR Spill when use permuted lds layout. so, use padding for these two.
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>
+#endif
     // clang-format on
     >;