Skip to content

Update instances list for grouped convolution forward #3288

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wj-laskowski merged 1 commit into from
Dec 16, 2025
Merged

Update instances list for grouped convolution forward #3288

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
159 changes: 0 additions & 159 deletions ...n_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_comp_instance.hpp
View file
Open in desktop

This file was deleted.

433 changes: 60 additions & 373 deletions ...ration_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp
View file
Open in desktop

Large diffs are not rendered by default.

131 changes: 0 additions & 131 deletions ...on_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_mem_instance.hpp
View file
Open in desktop

This file was deleted.

125 changes: 0 additions & 125 deletions ...e/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_merged_groups_instance.hpp
View file
Open in desktop

This file was deleted.

108 changes: 70 additions & 38 deletions ...nce/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp
View file
Open in desktop

Large diffs are not rendered by default.

332 changes: 0 additions & 332 deletions library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp
View file
Open in desktop

Large diffs are not rendered by default.

40 changes: 0 additions & 40 deletions ...clude/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_bias_clamp.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand All @@ -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
}
Expand All @@ -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
Expand All @@ -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
}
Expand Down
Loading