Merge branch 'amd-develop' into amd-master

fa9da1a4 · Jun Liu · 4c105089 · 457308e3 · fa9da1a4 · fa9da1a4
Commit fa9da1a4 authored Jun 19, 2023 by Jun Liu
20 changed files
--- a/example/33_multiple_reduce/dual_reduce_multiblock.cpp
+++ b/example/33_multiple_reduce/dual_reduce_multiblock.cpp
--- a/example/33_multiple_reduce/dual_reduce_threadwise.cpp
+++ b/example/33_multiple_reduce/dual_reduce_threadwise.cpp
--- a/example/34_batchnorm/batchnorm_backward_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_backward_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_common.hpp
+++ b/example/34_batchnorm/batchnorm_common.hpp
--- a/example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_forward_inferring_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_forward_training_nhwc.cpp
+++ b/example/34_batchnorm/batchnorm_forward_training_nhwc.cpp
--- a/example/34_batchnorm/batchnorm_infer_impl.hpp
+++ b/example/34_batchnorm/batchnorm_infer_impl.hpp
--- a/example/35_splitK_gemm/CMakeLists.txt
+++ b/example/35_splitK_gemm/CMakeLists.txt
--- a/example/35_splitK_gemm/splitK_gemm_xdl_bfp16.cpp
+++ b/example/35_splitK_gemm/splitK_gemm_xdl_bfp16.cpp
--- a/example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp
+++ b/example/35_splitK_gemm/splitK_gemm_xdl_fp16.cpp
--- a/example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp
+++ b/example/35_splitK_gemm/splitK_gemm_xdl_fp32.cpp
--- a/example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp
+++ b/example/35_splitK_gemm/splitK_gemm_xdl_int4.cpp
--- a/example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp
+++ b/example/35_splitK_gemm/splitK_gemm_xdl_int8.cpp
--- a/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
+++ b/example/36_sparse_embedding/sparse_embedding3_forward_layernorm.cpp
--- a/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
+++ b/example/37_batched_gemm_add_add_relu_gemm_add/batched_gemm_add_add_relu_gemm_add_xdl_fp16.cpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt
+++ b/example/38_grouped_conv_bwd_data_multiple_d/CMakeLists.txt
--- a/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
+++ b/example/38_grouped_conv_bwd_data_multiple_d/common.hpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_fp16.cpp
+++ b/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_bias_relu_fp16.cpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_fp16.cpp
+++ b/example/38_grouped_conv_bwd_data_multiple_d/grouped_conv_bwd_data_fp16.cpp
--- a/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc
+++ b/example/38_grouped_conv_bwd_data_multiple_d/run_grouped_conv_bwd_data_bias_relu_example.inc