ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_BUILDER]ckb add remining fwd conv device ops (#3155)

Browse Source 
* Add device operation to conv signature. Use unions to hold conv layouts and device operations.

* Add predicates for all device op instances.

* Use the device op signature for validation.

* Fix ckb CMakeLists.txt file for tests.

* Fix building CK Builder instance traits after the introduction of direct load template parameter in CK.

* Fix clang-formatting.

* add device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk

* Add full DL configurability with Option A implementation

- Added 5 DL descriptor structs (39 configurable parameters)
- Added 10 C++20 concepts for type-safe validation
- Updated factory to read all parameters from descriptors
- Updated test helper to populate all descriptors
- All tests passing (13/13 including 3 new DL tests)

* Add factory and test support for DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor

- Add factory specialization for Large_Tensor device operation (conv_factory.hpp lines 1145-1265)
- Add macro collision workaround using pragma push/pop (conv_factory.hpp lines 43-51)
- Add test helper function run_test_DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor
- Add builder test file test_ckb_conv_fwd_2d_large_tensor_fp16.cpp with 2 test cases
- Update CMakeLists.txt to include new test file
- Reuse existing ConvAlgorithm_DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle descriptor
- Map all 42 template parameters identical to regular XDL CShuffle
- All 15 builder tests passing including 2 new Large_Tensor tests

Completes Task 350: All 4 forward convolution device operations now supported in CK Builder.

* Update copyright headers to new format

- Change copyright format to: Copyright (C) Advanced Micro Devices, Inc., or its affiliates.
- Reorder headers: Copyright first, then SPDX-License-Identifier
- Updated files:
  * experimental/builder/test/conv/test_ckb_conv_fwd_2d_dl_fp16.cpp
  * experimental/builder/test/conv/test_ckb_conv_fwd_2d_large_tensor_fp16.cpp
  * experimental/builder/include/ck_tile/builder/device_op_types.hpp

* fix c++ 18 format

* Fix clang-format-18 error in device_op_types.hpp

---------

Co-authored-by: Ville Pietilä <ville.pietila@amd.com>
Co-authored-by: Ville Pietilä <188998872+vpietila-amd@users.noreply.github.com>
This commit is contained in:
JH-Leon-KIM-AMD
2025-11-07 02:29:48 +02:00
committed by GitHub
parent 76c4c12f59
commit 5f3cae3e28
8 changed files with 725 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
experimental/builder/test/conv/test_ckb_conv_fwd_2d_dl_fp16.cpp Normal file
View File

@@ -0,0 +1,69 @@
// Copyright (C) Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#include "utils/ckb_conv_test_common.hpp"
using namespace ck_tile::builder::test_utils;
namespace ck_tile::builder::testing {
TEST(FwdConvInstances, Create_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK_Instance_2D_FP16_GNHWC)
{
constexpr ConvSignature FwdConvSignature{
.spatial_dim = 2,
.direction = ConvDirection::FORWARD,
.layout = GroupConvLayout2D::GNHWC_GKYXC_GNHWK,
.data_type = DataType::FP16,
.elementwise_operation = ElementwiseOperation::PASS_THROUGH,
.device_operation =
FwdGroupConvDeviceOperation::DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK};
constexpr ThreadBlock FwdThreadBlock{.block_size = 256,
.tile_size = {.m = 128, .n = 128, .k = 16}};
run_test_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK<FwdConvSignature,
FwdThreadBlock,
ConvFwdSpecialization::DEFAULT>();
}
TEST(FwdConvInstances, Create_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK_Instance_2D_FP16_NHWGC)
{
constexpr ConvSignature FwdConvSignature{
.spatial_dim = 2,
.direction = ConvDirection::FORWARD,
.layout = GroupConvLayout2D::NHWGC_GKYXC_NHWGK,
.data_type = DataType::FP16,
.elementwise_operation = ElementwiseOperation::PASS_THROUGH,
.device_operation =
FwdGroupConvDeviceOperation::DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK};
constexpr ThreadBlock FwdThreadBlock{.block_size = 256,
.tile_size = {.m = 128, .n = 128, .k = 16}};
run_test_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK<FwdConvSignature,
FwdThreadBlock,
ConvFwdSpecialization::DEFAULT>();
}
TEST(FwdConvInstances,
Create_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK_Instance_2D_FP16_FILTER_1X1_PAD0)
{
constexpr ConvSignature FwdConvSignature{
.spatial_dim = 2,
.direction = ConvDirection::FORWARD,
.layout = GroupConvLayout2D::GNHWC_GKYXC_GNHWK,
.data_type = DataType::FP16,
.elementwise_operation = ElementwiseOperation::PASS_THROUGH,
.device_operation =
FwdGroupConvDeviceOperation::DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK};
constexpr ThreadBlock FwdThreadBlock{.block_size = 256,
.tile_size = {.m = 128, .n = 128, .k = 16}};
run_test_DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK<
FwdConvSignature,
FwdThreadBlock,
ConvFwdSpecialization::FILTER_1X1_PAD0>();
}
} // namespace ck_tile::builder::testing

53
experimental/builder/test/conv/test_ckb_conv_fwd_2d_large_tensor_fp16.cpp Normal file
View File

@@ -0,0 +1,53 @@
// Copyright (C) Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#include "utils/ckb_conv_test_common.hpp"
using namespace ck_tile::builder::test_utils;
namespace ck_tile::builder::testing {
TEST(FwdConvInstances,
Create_DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor_Instance_2D_FP16_GNHWC)
{
constexpr ConvSignature FwdConvSignature{
.spatial_dim = 2,
.direction = ConvDirection::FORWARD,
.layout = GroupConvLayout2D::GNHWC_GKYXC_GNHWK,
.data_type = DataType::FP16,
.elementwise_operation = ElementwiseOperation::PASS_THROUGH,
.device_operation =
FwdGroupConvDeviceOperation::DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor};
constexpr ThreadBlock FwdThreadBlock{.block_size = 256,
.tile_size = {.m = 256, .n = 128, .k = 32}};
run_test_DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<
FwdConvSignature,
FwdThreadBlock,
ConvFwdSpecialization::DEFAULT>();
}
TEST(
FwdConvInstances,
Create_DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor_Instance_2D_FP16_GNHWC_Filter1x1Pad0)
{
constexpr ConvSignature FwdConvSignature{
.spatial_dim = 2,
.direction = ConvDirection::FORWARD,
.layout = GroupConvLayout2D::GNHWC_GKYXC_GNHWK,
.data_type = DataType::FP16,
.elementwise_operation = ElementwiseOperation::PASS_THROUGH,
.device_operation =
FwdGroupConvDeviceOperation::DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor};
constexpr ThreadBlock FwdThreadBlock{.block_size = 128,
.tile_size = {.m = 128, .n = 128, .k = 32}};
run_test_DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<
FwdConvSignature,
FwdThreadBlock,
ConvFwdSpecialization::FILTER_1X1_PAD0>();
}
} // namespace ck_tile::builder::testing