diff --git a/library/include/ck_tile/library/tensor_operation_instance/gpu/tile_grouped_conv_bwd_weight_bf16_instances.hpp b/library/include/ck_tile/library/tensor_operation_instance/gpu/tile_grouped_conv_bwd_weight_bf16_instances.hpp
index 2bb3cd9cca..93fa3a1708 100644
--- a/library/include/ck_tile/library/tensor_operation_instance/gpu/tile_grouped_conv_bwd_weight_bf16_instances.hpp
+++ b/library/include/ck_tile/library/tensor_operation_instance/gpu/tile_grouped_conv_bwd_weight_bf16_instances.hpp
@@ -22,14 +22,143 @@ using tile_grouped_conv_bwd_weight_bf16_instances = std::tuple<
         //#####################################|       Dim|          |          |          |   Type|    Type|    Type|  Elementwise| Elementwise| Elementwise|      per|        |        |        |       |       |       |   tile|   tile|   tile|   size|   size|   size|
         //#####################################|   Spatial|          |          |          |       |        |        |    Operation|   Operation|   Operation|       CU|        |        |        |       |       |       |   size|   size|   size|      A|      B|      C|
         //#####################################|          |          |          |          |       |        |        |             |            |            |                    
-        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       1>,
         GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       2>,
         GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       4>,
         GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       8>,
-        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        1,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       1>,
         GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       2>,
         GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       4>,
-        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       8>
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      1,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      4,     8,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     1,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     2,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       4>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     4,       8>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       1>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      8,     8,       4>,
+
+        //#####################################|       Num|  InLayout| WeiLayout| OutLayout| InData| WeiData| OutData|           In|         Wei|         Out|  K-block|  M-tile| N-tile | K-tile | M-warp| N-warp| K-warp| M-warp| N-warp| K-warp| Vector| Vector| Vector|
+        //#####################################|       Dim|          |          |          |   Type|    Type|    Type|  Elementwise| Elementwise| Elementwise|      per|        |        |        |       |       |       |   tile|   tile|   tile|   size|   size|   size|
+        //#####################################|   Spatial|          |          |          |       |        |        |    Operation|   Operation|   Operation|       CU|        |        |        |       |       |       |   size|   size|   size|      A|      B|      C|
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,     16,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     32,     32,      8,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,      64,      64,      64,      2,      2,      1,     16,     16,     32,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,       8,     128,      64,      2,      2,      1,      4,     64,     16,      2,     4,       2>,
+        GroupedConvolutionBackwardWeightInvoker<NDimSpatial,   ALayout,   BLayout,   ELayout,   BF16,    BF16,    BF16,  PassThrough, PassThrough, PassThrough,        2,     128,       8,      64,      2,      2,      1,     64,      4,     16,      2,     4,       2>
+    // // clang-format on
     // clang-format on
     >;
 
diff --git a/profiler/ck_tile/src/tile_profile_grouped_conv_bwd_weight.cpp b/profiler/ck_tile/src/tile_profile_grouped_conv_bwd_weight.cpp
index faccc8fcce..d29df87ea6 100644
--- a/profiler/ck_tile/src/tile_profile_grouped_conv_bwd_weight.cpp
+++ b/profiler/ck_tile/src/tile_profile_grouped_conv_bwd_weight.cpp
@@ -119,16 +119,12 @@ int tile_profile_grouped_conv_bwd_weight(int argc, char* argv[])
     using TF32 = ck::tf32_t;
 #endif
 
-    //using namespace ck::tensor_layout::convolution;
-    //using NWGC   = ck_tile::tensor_layout::convolution::NWGC;
     using NHWGC  = ck_tile::tensor_layout::convolution::NHWGC;
     using NDHWGC = ck_tile::tensor_layout::convolution::NDHWGC;
 
-    //using GKXC   = ck_tile::tensor_layout::convolution::GKXC;
     using GKYXC  = ck_tile::tensor_layout::convolution::GKYXC;
     using GKZYXC = ck_tile::tensor_layout::convolution::GKZYXC;
 
-    //using NWGK   = ck_tile::tensor_layout::convolution::NWGK;
     using NHWGK  = ck_tile::tensor_layout::convolution::NHWGK;
     using NDHWGK = ck_tile::tensor_layout::convolution::NDHWGK;