Merge remote-tracking branch 'origin/develop' into cpu_avx2

b134b7d6 · carlushuang · 090ba885 · 9f71ff48 · b134b7d6 · b134b7d6
Commit b134b7d6 authored May 16, 2022 by carlushuang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/conv1d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv1d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_atomic_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_atomic_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv3d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/convnd_bwd_data/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/convnd_bwd_data/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/device_conv2d.cpp
+++ b/library/src/tensor_operation_instance/gpu/device_conv2d.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp