Merge branch 'develop' into normalization/splitK

0d6da13c · rocking · GitHub · 27f8c64b · b076a02a · 0d6da13c
Unverified Commit 0d6da13c authored May 05, 2023 by rocking Committed by GitHub May 05, 2023
18 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_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_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/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/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/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
--- a/profiler/include/profiler/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_splitk_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_impl.hpp
--- a/profiler/src/profile_grouped_gemm.cpp
+++ b/profiler/src/profile_grouped_gemm.cpp
--- a/script/cmake-ck-dev.sh
+++ b/script/cmake-ck-dev.sh
--- a/script/cmake-ck-release.sh
+++ b/script/cmake-ck-release.sh