Adding tuned instace list for groupoed conv fwd

Following flavors are updated with tuned instance list:
  - grouped_conv2d_fwd
  - grouped_conv2d_fwd_bias_clamp
  - grouped_conv2d_fwd_clamp
  - grouped_conv3d_fwd
  - grouped_conv3d_fwd_bias_clamp
  - grouped_conv3d_fwd_clamp
  - grouped_conv3d_fwd_scaleadd_ab

Re-factored instance selection:
  - removed all the unnecessary instance tuples (comp/mem/16x16/generic)
  - removed all unnecessary layouts and data types

Author: wj-laskowski

library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp

@@ -287,18 +287,8 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
             {
                 add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_bf16_instances(
                     op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_bf16_16x16_instances(
-                    op_ptrs);
                 // add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_large_tensor_nhwgc_gkyxc_nhwgk_bf16_instances(
                 //     op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_merged_groups_nhwgc_gkyxc_nhwgk_bf16_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_bf16_comp_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_bf16_mem_intra_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_bf16_mem_inter_instances(
-                    op_ptrs);
             }
 #endif
 #ifdef CK_ENABLE_FP16
@@ -308,18 +298,8 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
             {
                 add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_f16_instances(
                     op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_f16_16x16_instances(
-                    op_ptrs);
                 // add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_large_tensor_nhwgc_gkyxc_nhwgk_f16_instances(
                 //     op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_merged_groups_nhwgc_gkyxc_nhwgk_f16_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_f16_comp_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_f16_mem_intra_instances(
-                    op_ptrs);
-                add_device_grouped_conv2d_fwd_bias_clamp_wmma_cshufflev3_nhwgc_gkyxc_nhwgk_f16_mem_inter_instances(
-                    op_ptrs);
             }
 #endif
         }
@@ -336,18 +316,8 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
             {
                 add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
                     op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_bf16_16x16_instances(
-                    op_ptrs);
                 // add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_large_tensor_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
                 //     op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_merged_groups_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_bf16_comp_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_bf16_mem_intra_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_bf16_mem_inter_instances(
-                    op_ptrs);
             }
 #endif
 #ifdef CK_ENABLE_FP16
@@ -357,18 +327,8 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
             {
                 add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_instances(
                     op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_16x16_instances(
-                    op_ptrs);
                 // add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_large_tensor_ndhwgc_gkzyxc_ndhwgk_f16_instances(
                 //     op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_merged_groups_ndhwgc_gkzyxc_ndhwgk_f16_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_comp_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_mem_intra_instances(
-                    op_ptrs);
-                add_device_grouped_conv3d_fwd_bias_clamp_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_mem_inter_instances(
-                    op_ptrs);
             }
 #endif
         }