merge develop

1dbdab56 · Jing Zhang · d2e49b23 · bac7df8f · 1dbdab56 · 1dbdab56
Commit 1dbdab56 authored Aug 18, 2022 by Jing Zhang
20 changed files
--- a/example/34_batchnorm/CMakeLists.txt
+++ b/example/34_batchnorm/CMakeLists.txt
+add_example_executable(example_batchnorm_forward batchnorm_forward_nhwc.cpp)
+add_example_executable(example_batchnorm_infer batchnorm_infer_nhwc.cpp)
--- a/example/34_batchnorm/README.md
+++ b/example/34_batchnorm/README.md
--- a/example/34_batchnorm/batchnorm_common.hpp
+++ b/example/34_batchnorm/batchnorm_common.hpp
--- a/example/34_batchnorm/batchnorm_forward_impl.hpp
+++ b/example/34_batchnorm/batchnorm_forward_impl.hpp
--- a/example/34_batchnorm/batchnorm_forward_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_forward_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_infer_impl.hpp
+++ b/example/34_batchnorm/batchnorm_infer_impl.hpp
--- a/example/34_batchnorm/batchnorm_infer_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_infer_nhwc.cpp
--- a/example/31_splitK_gemm/CMakeLists.txt
+++ b/example/31_splitK_gemm/CMakeLists.txt
--- a/example/31_splitK_gemm/splitK_gemm_xdl_bfp16.cpp
+++ b/example/31_splitK_gemm/splitK_gemm_xdl_bfp16.cpp
--- a/example/31_splitK_gemm/splitK_gemm_xdl_fp16.cpp
+++ b/example/31_splitK_gemm/splitK_gemm_xdl_fp16.cpp
--- a/example/31_splitK_gemm/splitK_gemm_xdl_fp32.cpp
+++ b/example/31_splitK_gemm/splitK_gemm_xdl_fp32.cpp
--- a/example/31_splitK_gemm/splitK_gemm_xdl_int8.cpp
+++ b/example/31_splitK_gemm/splitK_gemm_xdl_int8.cpp
--- a/example/CMakeLists.txt
+++ b/example/CMakeLists.txt
--- a/include/ck/tensor_description/tensor_descriptor.hpp
+++ b/include/ck/tensor_description/tensor_descriptor.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
--- a/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_5ary_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_5ary_elementwise.hpp