Improve external interface for GEMM and GEMM+add+add+fastgelu (#311)

* interface for GEMM and GEMM+add+add+fastgelu * rename namespace * instance factory * fix build * fix build; add GEMM client example * clean

Improve external interface for GEMM and GEMM+add+add+fastgelu (#311)
* interface for GEMM and GEMM+add+add+fastgelu * rename namespace * instance factory * fix build * fix build; add GEMM client example * clean
0dcb3496 · Chao Liu · GitHub · fa9a0a5c · 0dcb3496 · 0dcb3496
Unverified Commit 0dcb3496 authored Jun 30, 2022 by Chao Liu Committed by GitHub Jun 30, 2022
20 changed files
--- a/profiler/include/profile_batched_gemm_reduce_impl.hpp
+++ b/profiler/include/profile_batched_gemm_reduce_impl.hpp
--- a/profiler/include/profile_conv_bwd_weight_impl.hpp
+++ b/profiler/include/profile_conv_bwd_weight_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
--- a/profiler/include/profile_convnd_bwd_data_impl.hpp
+++ b/profiler/include/profile_convnd_bwd_data_impl.hpp
--- a/profiler/include/profile_gemm_add_add_fastgelu_impl.hpp
+++ b/profiler/include/profile_gemm_add_add_fastgelu_impl.hpp
--- a/profiler/include/profile_gemm_bias_2d_impl.hpp
+++ b/profiler/include/profile_gemm_bias_2d_impl.hpp
--- a/profiler/include/profile_gemm_bias_add_reduce_impl.hpp
+++ b/profiler/include/profile_gemm_bias_add_reduce_impl.hpp
--- a/profiler/include/profile_gemm_bias_relu_add_impl.hpp
+++ b/profiler/include/profile_gemm_bias_relu_add_impl.hpp
--- a/profiler/include/profile_gemm_bias_relu_impl.hpp
+++ b/profiler/include/profile_gemm_bias_relu_impl.hpp
--- a/profiler/include/profile_gemm_impl.hpp
+++ b/profiler/include/profile_gemm_impl.hpp
--- a/profiler/include/profile_gemm_reduce_impl.hpp
+++ b/profiler/include/profile_gemm_reduce_impl.hpp
--- a/profiler/include/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profile_gemm_splitk_impl.hpp
--- a/profiler/include/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profile_grouped_gemm_impl.hpp
--- a/profiler/include/profile_normalization_impl.hpp
+++ b/profiler/include/profile_normalization_impl.hpp
--- a/profiler/include/profile_reduce_impl.hpp
+++ b/profiler/include/profile_reduce_impl.hpp
--- a/profiler/src/profile_gemm_add_add_fastgelu.cpp
+++ b/profiler/src/profile_gemm_add_add_fastgelu.cpp
--- a/script/docker-rocm4.1.sh
+++ b/script/docker-rocm4.1.sh
--- a/script/docker-rocm4.3.1.sh
+++ b/script/docker-rocm4.3.1.sh
--- a/test/conv2d_bwd_data/conv2d_bwd_data.cpp
+++ b/test/conv2d_bwd_data/conv2d_bwd_data.cpp