Merge remote-tracking branch 'origin/develop' into tile

a72a5762 · Chao Liu · b00ae5df · 209baee2 · a72a5762 · a72a5762
Commit a72a5762 authored Feb 24, 2023 by Chao Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_mk_nk_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/device_grouped_conv3d_fwd_xdl_ndhwgc_kzyxgc_ndhwgk_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f32_instance.cpp
--- a/profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_add_relu_add_layernorm_impl.hpp
--- a/profiler/include/profiler/profile_layernorm_impl.hpp
+++ b/profiler/include/profiler/profile_layernorm_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_gemm_add_relu_add_layernorm.cpp
+++ b/profiler/src/profile_gemm_add_relu_add_layernorm.cpp
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
--- a/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp
+++ b/test/batched_gemm_softmax_gemm_permute/test_batched_gemm_softmax_gemm_permute_bf16.cpp
--- a/test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp
+++ b/test/elementwise_normalization/test_elementwise_layernorm_fp16.cpp
--- a/test/gemm_layernorm/CMakeLists.txt
+++ b/test/gemm_layernorm/CMakeLists.txt
--- a/test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp
+++ b/test/gemm_layernorm/test_gemm_add_relu_add_layernorm_fp16.cpp
--- a/test/normalization/CMakeLists.txt
+++ b/test/normalization/CMakeLists.txt