Merge remote-tracking branch 'origin/develop' into lwpck-367

a1841d55 · Chao Liu · 127bf7f4 · 500fa995 · a1841d55 · a1841d55
Commit a1841d55 authored Aug 01, 2022 by Chao Liu
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_backward_weight.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_backward_weight.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_convnd_bwd_data_xdl_ndhwc_kzyxc_ndhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_bwd_data_xdl_ndhwc_kzyxc_ndhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_convnd_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
--- 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.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_bias_add_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_bias_add_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_bias_c_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_bias_c_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_bias_c_permute_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_bias_c_permute_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_xdl_cshuffle.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_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_cshuffle.hpp