[CK_BUILDER] Add grouped conv fwd ck tile profiler (#3518)

* [BULDER] Add grouped conv fwd ck tile profiler

* [CK TILE] Fix grouped conv kernels splitk and double lds

* Updates

* Fixes

* Move to ckProfiler

* Fixes

* fix

* fix

* Change instances to empty list by default

* fix

* fix

* Update grouped_convolution_signatures.hpp

* Update grouped_convolution_forward_tile_algs.hpp

* [CK TILE] Add grouped convolution forward tests (#3556)

* [CK TILE] Add grouped convolution forward tests

* fix jenkins

* fixes

* comments fixes

* unit test

* unit test fix

* Move instances outside builder

* fix includes

* clang format fix

* readme fix

* fix includes

* fixes
This commit is contained in:
Bartłomiej Kocot
2026-01-20 06:29:01 +01:00
committed by GitHub
parent 0517d43d31
commit 0727e85e52
44 changed files with 3083 additions and 65 deletions

View File

@@ -0,0 +1,19 @@
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
# SPDX-License-Identifier: MIT
if(GPU_TARGETS MATCHES "gfx9")
# Generate instances using python script (empty to just generate empty instance list)
if(NOT EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/grouped_convolution_forward_tile_ndhwgc_fp32.inc)
find_package(Python3 COMPONENTS Interpreter Development)
execute_process(
COMMAND ${Python3_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/generate_instances.py --mode=tests
RESULT_VARIABLE ret
)
endif()
# Find cpp files and create lib for instances
file(GLOB_RECURSE GROUPED_CONV_FWD_TILE "instances/*.cpp")
add_instance_library(device_grouped_conv_fwd_tile_instances ${GROUPED_CONV_FWD_TILE})
target_include_directories(device_grouped_conv_fwd_tile_instances PRIVATE
"${PROJECT_SOURCE_DIR}/experimental/builder/test/utils")
endif()