merge develop

1dbdab56 · Jing Zhang · d2e49b23 · bac7df8f · 1dbdab56 · 1dbdab56
Commit 1dbdab56 authored Aug 18, 2022 by Jing Zhang
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
--- a/include/ck/tensor_operation/gpu/device/device_binary_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_binary_elementwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_cgemm_4gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_cgemm_4gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
@@ -13,7 +13,6 @@
 #include "ck/tensor_operation/gpu/device/device_conv_bwd_weight.hpp"
 #include "ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_unary_elementwise_1d.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"


--- a/include/ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.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_elementwise_base.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_base.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_layernorm.hpp