Merge branch 'develop' of...

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

Merge branch 'develop' of...
Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into lds_bypass_spilling
a3b86965 · aska-0096 · bdd0f64e · fe96e8fb · a3b86965 · a3b86965
Commit a3b86965 authored Mar 23, 2023 by aska-0096
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
--- 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_dl_int8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_int8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/device_conv2d_xdl_int8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/gemm/device_gemm_quantization_dl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp