external api for gemm + layernorm (#285)

* Extract base class for elementwise * Refactor interface of DeviceGemmReduce. Do not use tuple in interface * [What] Rename d into reduce in gemm + reduction related code [Why] Prepare to add d term for add * Unify base class of gemm + reduce and gemm + bias + add + reduce * 1. Rename gemm_bias_add_reduce for external api 2. Refine cmake * Add normalize device operation * [What] Reorder the argument [Why] Because d0 is also the input of c. * Add type string * Add example of gemm_bias_add_layernorm via external api * Refactor example code * clang-format * Fix compile error * clang-format * Add external api for gemm_add_add_layernorm and normalize * Add client example * clang-format

external api for gemm + layernorm (#285)
* Extract base class for elementwise * Refactor interface of DeviceGemmReduce. Do not use tuple in interface * [What] Rename d into reduce in gemm + reduction related code [Why] Prepare to add d term for add * Unify base class of gemm + reduce and gemm + bias + add + reduce * 1. Rename gemm_bias_add_reduce for external api 2. Refine cmake * Add normalize device operation * [What] Reorder the argument [Why] Because d0 is also the input of c. * Add type string * Add example of gemm_bias_add_layernorm via external api * Refactor example code * clang-format * Fix compile error * clang-format * Add external api for gemm_add_add_layernorm and normalize * Add client example * clang-format
12235112 · rocking5566 · GitHub · aebd211c · 12235112 · 12235112
Unverified Commit 12235112 authored Jun 28, 2022 by rocking5566 Committed by GitHub Jun 27, 2022
6 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
--- a/profiler/include/profile_batched_gemm_reduce_impl.hpp
+++ b/profiler/include/profile_batched_gemm_reduce_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_reduce_impl.hpp
+++ b/profiler/include/profile_gemm_reduce_impl.hpp