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

b79df771 · carlushuang · 05d38218 · 63914743 · b79df771 · b79df771
Commit b79df771 authored Jul 12, 2022 by carlushuang
20 changed files
--- 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_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.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_bwd_data.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_bwd_data.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_conv_fwd_bias_activation.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.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_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_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_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise.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_activation.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_bias_activation.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