Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into add_fp16_wmma_conv_instance

Merge branch 'develop' of...
Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into add_fp16_wmma_conv_instance
212b9299 · aska-0096 · 06903279 · d3adc665 · 212b9299 · 212b9299
Commit 212b9299 authored Jun 29, 2023 by aska-0096
20 changed files
--- a/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/welford_helper.hpp
+++ b/include/ck/tensor_operation/gpu/device/welford_helper.hpp
--- a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_reduce_second_half_batchnorm_backward_final.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_multiblock_reduce_first_half.hpp
--- a/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
+++ b/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
--- a/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_gemm_multiple_d_welford_first_half_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gemm_layernorm/gridwise_welford_second_half_layernorm2d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_softmax_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp