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

6dfb4e78 · carlushuang · 397a68f2 · 1ced00a5 · 6dfb4e78 · 6dfb4e78
Commit 6dfb4e78 authored Jun 12, 2022 by carlushuang
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_blockwise_second_call.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_blockwise_second_call.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_atomic_add.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_atomic_add.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.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/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/gridwise_2d_reduction_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_partial_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_partial_reduce.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_atomic_add.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_atomic_add.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_5ary_Elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_5ary_Elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp