Merge branch 'develop' into lwpck-537

7d3c5ea4 · zjing14 · GitHub · 981b8549 · 3b18f1e3 · 7d3c5ea4
Unverified Commit 7d3c5ea4 authored Jun 25, 2023 by zjing14 Committed by GitHub Jun 25, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.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_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.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_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_xdl_waveletmodel_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_xdl_waveletmodel_cshuffle.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_conv_bwd_data_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_index_pool_bwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_index_pool_bwd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp