Merge branch 'lib_gemm_softmax_gemm_type' of...

Merge branch 'lib_gemm_softmax_gemm_type' of https://github.com/ROCmSoftwarePlatform/composable_kernel into lib_gemm_softmax_gemm_type

Merge branch 'lib_gemm_softmax_gemm_type' of...
Merge branch 'lib_gemm_softmax_gemm_type' of https://github.com/ROCmSoftwarePlatform/composable_kernel into lib_gemm_softmax_gemm_type
a483948c · ltqin · 54e599ca · e288457d · a483948c · a483948c
Commit a483948c authored Mar 31, 2023 by ltqin
14 changed files
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_f64_mnnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt
 add_instance_library(device_contraction_scale_instance
+    #float
    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp
    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp
    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp
    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp
+    #double
+    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
+    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
+    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
+    device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
 )

--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
--- a/script/cmake-ck-dev.sh
+++ b/script/cmake-ck-dev.sh
@@ -8,8 +8,8 @@ MY_PROJECT_SOURCE=$1
 cmake                                                                                             \
 -D CMAKE_PREFIX_PATH=/opt/rocm                                                                    \
 -D CMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc                                                         \
-D CMAKE_CXX_FLAGS="-std=c++17 -O3 -ftemplate-backtrace-limit=0 -fPIE -mcumode                    \
-mno-wavefrontsize64 -Wno-gnu-line-marker -save-temps=$PWD"                                       \
+-D CMAKE_CXX_FLAGS="-std=c++17 -O3 -ftemplate-backtrace-limit=0  -fPIE  -Wno-gnu-line-marker      \
+-save-temps=$PWD"                                                                                 \
 -D CMAKE_BUILD_TYPE=Release                                                                       \
 -D BUILD_DEV=ON                                                                                   \
 -D GPU_TARGETS="gfx908;gfx90a"                                                                    \

--- a/test/grouped_convnd_bwd_weight/grouped_convnd_bwd_weight.cpp
+++ b/test/grouped_convnd_bwd_weight/grouped_convnd_bwd_weight.cpp