diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_v3_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_v3_instance.hpp
index 35178310db..4458cb51bd 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_v3_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_v3_instance.hpp
@@ -65,8 +65,11 @@ using device_grouped_conv_bwd_data_xdl_v3_f16_instances = std::tuple<
         // ##############################################|           |        |        |            |        |      |      |        |         |            |      |             |             |               |                    |      |      |           |      |      |      |    |    |     |     |        |        | Lengths_AK0_M_AK1|   ArrangeOrder|               |               |      PerVector|  PerVector_AK1|          | Lengths_BK0_N_BK1|   ArrangeOrder|               |               |      PerVector|  PerVector_BK1|          |   PerShuffle|   PerShuffle|  _NBlock_NPerBlock|                 |
         // ##############################################|           |        |        |            |        |      |      |        |         |            |      |             |             |               |                    |      |      |           |      |      |      |    |    |     |     |        |        |                  |               |               |               |               |               |          |                  |               |               |               |               |               |          |             |             |                   |                 |                 
         // generic instance
-        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial,  ALayout, BLayout,   DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,         64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              2,              8,         1,        S<4, 2, 8>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,            1,            1,     S<1, 16, 1, 4>,         S<2,2,2>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, true>
-        
+        //DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial,  ALayout, BLayout,   DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,         64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              2,              8,         1,        S<4, 2, 8>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,            1,            1,     S<1, 16, 1, 4>,         S<2,2,2>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, true>
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,        64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,        S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 16, 1, 4>,             S<1,1,1>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, false>,
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,       128,    16,    32,    64,   8,   8,   16,   16,       1,       1,       S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,        S<4, 4, 8>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              8,              8,         1,            1,            1,     S<1, 16, 1, 8>,             S<2,2,2>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, true>
+        //DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,       128,    16,    32,    64,   8,   8,   16,   16,       1,       1,       S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,        S<8, 2, 8>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              8,              8,         1,            1,            1,     S<1, 16, 1, 8>,             S<1,1,1>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, true>,
+       //DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,       128,    16,    32,    64,   8,   8,   16,   16,       1,       1,       S<8, 2, 8>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,        S<4, 4, 8>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              8,              8,         1,            1,            1,     S<1, 16, 1, 8>,             S<1,1,1>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F16, F16, 1, 1, true>
         // DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial,  ALayout, BLayout,   DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,         64,    64,    32,    64,   8,   8,   16,   16,       4,       1,        S<8, 8, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,        S<8, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              8,         1,            1,            1,     S<1, 16, 1, 4>,         S<8,8,8>>,
         // DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial,  ALayout, BLayout,   DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,         64,    64,    64,    32,   8,   8,   16,   16,       4,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              8,         1,       S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              8,         1,            1,            1,     S<1, 16, 1, 4>,         S<8,8,8>>,
         // DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3<NDimSpatial,  ALayout, BLayout,   DsLayout, ELayout,   F16,   F16,     F32,      F16, Empty_Tuple,   F16,  PassThrough,  PassThrough,    PassThrough,            ConvSpec,  true,  true,        128,   128,    64,    32,   8,   8,   16,   16,       8,       1,       S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              8,         1,       S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 16, 1, 8>,         S<8,8,8>>,