Merge branch 'develop' into lwpck-759

9efb5cc4 · Rostyslav Geyyer · GitHub · af52fe33 · 40365904 · 9efb5cc4
Unverified Commit 9efb5cc4 authored Jun 05, 2023 by Rostyslav Geyyer Committed by GitHub Jun 05, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/device_base.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_base.hpp
--- 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_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm.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_multi_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.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_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.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_cgemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_cgemm.hpp