mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-21 21:39:15 +00:00
d34916a7ff
* Adding remaining flavors for grouped conv fwd
As titled. Following variants are added:
- grouped_conv2d_fwd_dynamic_op
- grouped_conv3d_fwd_dynamic_op
- grouped_conv3d_fwd_bilinear
- grouped_conv3d_fwd_convscale
- grouped_conv3d_fwd_convinvscale
- grouped_conv3d_fwd_convscale_add
- grouped_conv3d_fwd_convscale_relu
- grouped_conv3d_fwd_scale
- grouped_conv3d_fwd_combconvscale
- grouped_conv3d_fwd_scaleadd_scaleadd_relu
* Fix incomplete parsing of types from source names in add_instance_library() cmakelists function so we don't build f8 on RDNA3.
* Do not build f8 / bf8 only flavor tests on RDNA3
* Make sure we have proper generic instances for all instance lists related to the post-ces extra flavors, with scalarPerVector = 1. Then disable all but one generic instance per instance list to reduce compile time.
* Post rebase fix: Template parameters for Grouped Conv Fwd Device Impl got tweaked upstream.
* adding int8 and fp16 overloads to the elementwise operations
* fixed copilot nits
* Addressing review comments:
- removed unnecessary examples for dynamic op
- removed unnecessary conv specalizations for all the flavors
- removed spurious bilinear and scale source files
* clang-format
* reduced no of tests
---------
Co-authored-by: Wojciech Laskowski <wojciech.laskowski@streamhpc.com>
[ROCm/composable_kernel commit: 2377a62837]
34 lines
1.9 KiB
CMake
34 lines
1.9 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
if (NOT GPU_TARGETS MATCHES "gfx11")
|
|
add_custom_target(example_convnd_activ_xdl_convscale)
|
|
add_example_executable(example_convnd_fwd_xdl_convscale_fp8 convnd_fwd_xdl_convscale_fp8.cpp)
|
|
add_example_dependencies(example_convnd_activ_xdl_convscale example_convnd_fwd_xdl_convscale_fp8 )
|
|
|
|
add_example_executable(example_convnd_fwd_xdl_convscale_bf8 convnd_fwd_xdl_convscale_bf8.cpp)
|
|
add_example_dependencies(example_convnd_activ_xdl_convscale example_convnd_fwd_xdl_convscale_bf8)
|
|
|
|
add_example_executable(example_convnd_fwd_xdl_convscale_fp8_bf8 convnd_fwd_xdl_convscale_fp8_bf8.cpp)
|
|
add_example_dependencies(example_convnd_activ_xdl_convscale example_convnd_fwd_xdl_convscale_fp8_bf8)
|
|
|
|
add_example_executable(example_convnd_fwd_xdl_convscale_bf8_fp8 convnd_fwd_xdl_convscale_bf8_fp8.cpp)
|
|
add_example_dependencies(example_convnd_activ_xdl_convscale example_convnd_fwd_xdl_convscale_bf8_fp8)
|
|
endif()
|
|
|
|
# WMMA
|
|
if (GPU_TARGETS MATCHES "gfx12")
|
|
add_custom_target(example_convnd_activ_wmma_convscale)
|
|
add_example_executable(example_convnd_fwd_wmma_convscale_fp8 convnd_fwd_wmma_convscale_fp8.cpp)
|
|
add_example_dependencies(example_convnd_activ_wmma_convscale example_convnd_fwd_wmma_convscale_fp8)
|
|
|
|
add_example_executable(example_convnd_fwd_wmma_convscale_bf8 convnd_fwd_wmma_convscale_bf8.cpp)
|
|
add_example_dependencies(example_convnd_activ_wmma_convscale example_convnd_fwd_wmma_convscale_bf8)
|
|
|
|
add_example_executable(example_convnd_fwd_wmma_convscale_fp8_bf8 convnd_fwd_wmma_convscale_fp8_bf8.cpp)
|
|
add_example_dependencies(example_convnd_activ_wmma_convscale example_convnd_fwd_wmma_convscale_fp8_bf8)
|
|
|
|
add_example_executable(example_convnd_fwd_wmma_convscale_bf8_fp8 convnd_fwd_wmma_convscale_bf8_fp8.cpp)
|
|
add_example_dependencies(example_convnd_activ_wmma_convscale example_convnd_fwd_wmma_convscale_bf8_fp8)
|
|
endif()
|