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/include/ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_2d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_2d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_activation.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_activation.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_activation_add.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_activation_add.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_splitk_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_blockwise_second_call.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_blockwise_second_call.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_atomic_add.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_atomic_add.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_reduce_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_reduce_operation.hpp