Merge branch 'develop' into bnorm_bwd_pr

a781d078 · Qianfeng Zhang · fd76c787 · 4c4c7328 · a781d078 · a781d078
Commit a781d078 authored Nov 16, 2022 by Qianfeng Zhang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt