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

07a673c6 · carlushuang · c0f698d5 · ac0d8066 · 07a673c6 · 07a673c6
Commit 07a673c6 authored Apr 14, 2022 by carlushuang
20 changed files
--- a/library/include/ck/library/obselete_driver_offline/driver_convolution_maxpool_forward_implicit_gemm_v5r1_dlops_nc0hwc1_kc0yxc1_nk0hwk1.hpp
+++ b/library/include/ck/library/obselete_driver_offline/driver_convolution_maxpool_forward_implicit_gemm_v5r1_dlops_nc0hwc1_kc0yxc1_nk0hwk1.hpp
--- a/library/include/ck/library/obselete_driver_offline/driver_gemm_dlops_v1r2.hpp
+++ b/library/include/ck/library/obselete_driver_offline/driver_gemm_dlops_v1r2.hpp
--- a/library/include/ck/library/obselete_driver_offline/driver_gemm_dlops_v1r3.hpp
+++ b/library/include/ck/library/obselete_driver_offline/driver_gemm_dlops_v1r3.hpp
--- a/library/include/ck/library/obselete_driver_offline/driver_gemm_xdlops_v2r3.hpp
+++ b/library/include/ck/library/obselete_driver_offline/driver_gemm_xdlops_v2r3.hpp
--- a/library/include/ck/library/obselete_driver_offline/driver_gemm_xdlops_v2r4.hpp
+++ b/library/include/ck/library/obselete_driver_offline/driver_gemm_xdlops_v2r4.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_backward_weight.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_backward_weight.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp
--- a/test/include/test_util.hpp
+++ b/test/include/test_util.hpp
--- a/include/ck/tensor_operation/gpu/device/conv_utils.hpp
+++ b/include/ck/tensor_operation/gpu/device/conv_utils.hpp
--- a/library/src/host_tensor/host_tensor.cpp
+++ b/library/src/host_tensor/host_tensor.cpp
--- a/library/src/obselete_driver_offline/conv_add_fwd_driver_offline_nchwc.cpp
+++ b/library/src/obselete_driver_offline/conv_add_fwd_driver_offline_nchwc.cpp
--- a/library/src/obselete_driver_offline/conv_bwd_driver_offline.cpp
+++ b/library/src/obselete_driver_offline/conv_bwd_driver_offline.cpp
--- a/library/src/obselete_driver_offline/conv_fwd_driver_offline.cpp
+++ b/library/src/obselete_driver_offline/conv_fwd_driver_offline.cpp
--- a/library/src/obselete_driver_offline/conv_fwd_driver_offline_nchwc.cpp
+++ b/library/src/obselete_driver_offline/conv_fwd_driver_offline_nchwc.cpp
--- a/library/src/obselete_driver_offline/conv_maxpool_fwd_driver_offline_nchwc.cpp
+++ b/library/src/obselete_driver_offline/conv_maxpool_fwd_driver_offline_nchwc.cpp