Split the instances by architecture. (#1223)

* parse examples inside the add_example_executable function

* fix the example 64 cmake file

* add xdl flag to the gemm_bias_softmax_gemm_permute example

* add filtering of tests based on architecture type

* enable test_grouped_gemm for gfx9 only

* enable test_transpose only for gfx9

* only linnk test_transpose if it gets built

* split the gemm instances by architectures

* split gemm_bilinear,grouped_conv_bwd_weight instances by targets

* split instances by architecture

* split grouped_conv instances by architecture

* fix clang format

* fix the if-else logic in group_conv headers

* small fix for grouped convolution instances

* fix the grouped conv bwd weight dl instances

* fix client examples

* only enable client examples 3 and 4 on gfx9

* set the gfx9 macro

* make sure the architecture macros are set by cmake

* use separate set of xdl/wmma flags for host code

* sinmplify the main cmake file

* add conv_fwd_bf8 instance declaration
This commit is contained in:
Illia Silin
2024-04-02 09:42:17 -07:00
committed by GitHub
parent 303d4594f4
commit ae57e5938e
160 changed files with 3770 additions and 3392 deletions

View File

@@ -4,49 +4,49 @@ add_custom_target(example_contraction_bilinear)
# FP32
add_example_executable(example_contraction_bilinear_xdl_fp32 contraction_bilinear_xdl_fp32.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32)
add_example_executable(example_contraction_scale_xdl_fp32 contraction_scale_xdl_fp32.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32)
add_example_executable(example_contraction_bilinear_xdl_fp32_compute_bf16 contraction_bilinear_xdl_fp32_compute_bf16.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32_compute_bf16)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32_compute_bf16)
add_example_executable(example_contraction_scale_xdl_fp32_compute_bf16 contraction_scale_xdl_fp32_compute_bf16.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32_compute_bf16)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32_compute_bf16)
add_example_executable(example_contraction_bilinear_xdl_fp32_compute_fp16 contraction_bilinear_xdl_fp32_compute_fp16.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32_compute_fp16)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp32_compute_fp16)
add_example_executable(example_contraction_scale_xdl_fp32_compute_fp16 contraction_scale_xdl_fp32_compute_fp16.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32_compute_fp16)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp32_compute_fp16)
# FP64
add_example_executable(example_contraction_bilinear_xdl_fp64 contraction_bilinear_xdl_fp64.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp64)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp64)
add_example_executable(example_contraction_scale_xdl_fp64 contraction_scale_xdl_fp64.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp64)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp64)
add_example_executable(example_contraction_bilinear_xdl_fp64_compute_fp32 contraction_bilinear_xdl_fp64_compute_fp32.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp64_compute_fp32)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp64_compute_fp32)
add_example_executable(example_contraction_scale_xdl_fp64_compute_fp32 contraction_scale_xdl_fp64_compute_fp32.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp64_compute_fp32)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp64_compute_fp32)
# FP16
add_example_executable(example_contraction_bilinear_xdl_fp16_compute_fp32 contraction_bilinear_xdl_fp16_compute_fp32.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp16_compute_fp32)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_fp16_compute_fp32)
add_example_executable(example_contraction_scale_xdl_fp16_compute_fp32 contraction_scale_xdl_fp16_compute_fp32.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_fp16_compute_fp32)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_fp16_compute_fp32)
# BF16
add_example_executable(example_contraction_bilinear_xdl_bf16_compute_fp32 contraction_bilinear_xdl_bf16_compute_fp32.cpp)
add_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_bf16_compute_fp32)
add_example_dependencies(example_contraction_bilinear example_contraction_bilinear_xdl_bf16_compute_fp32)
add_example_executable(example_contraction_scale_xdl_bf16_compute_fp32 contraction_scale_xdl_bf16_compute_fp32.cpp)
add_dependencies(example_contraction_scale example_contraction_scale_xdl_bf16_compute_fp32)
add_example_dependencies(example_contraction_scale example_contraction_scale_xdl_bf16_compute_fp32)
add_dependencies(example_contraction example_contraction_scale)
add_dependencies(example_contraction example_contraction_bilinear)
add_example_dependencies(example_contraction example_contraction_scale)
add_example_dependencies(example_contraction example_contraction_bilinear)