NHWC conv 2d: bwd fp32/fp16/bfp16/int8, Device level tuning and host API (#92)

* start conv2d bwd api

* kernel running

* add bwd reference

* change to no shuffle

* fix bwd reference

* pass verification

* add Filter1x1Stride1Pad0 and start testing

* change some tuning parameter

* fix test error

* add fp16 tuning parameter

* add bf16 tuning parameter

* add int8 tuning parameters

* change fp32 tuning parameter

* add bwd to profiler

* fix bug for bwd profiler

* fix ckProfiler bug

* change conv2d_bwd_xdl to fp16

* fix bug in comments

* fix precompile id

* fix enum conv name

* chage _bwd_ to _bwd_data_

* change conv2d_bwd example id

* bwd to bwd data

* fix prehead

* fix MakeDefaultBlock2CTileMap ,import form merge develop

* format bwd instance

* bwd to bwd data

* change name bwd to bwd data

* change name bwd to bwd data in example

* formate code

* change conv2d bwd data id in example

* rewrite readme for example

* fix CalculateMagicNumbers about div zero

* add workaround CK_WORKAROUND_SWDEV_325164

* change test_conf2d_bwd_data show info

* format

* fix bug for workaround:CK_WORKAROUND_SWDEV_325164

* formate tuning parameters

* formate tuning parameters again

* formate tuning parameters 3

* formate tuning parameters 4

* remove add function template

* format

* update comment

Co-authored-by: ltqin <letaoqin@amd.com>
Co-authored-by: Chao Liu <chao.liu2@amd.com>

[ROCm/composable_kernel commit: c254e5abd2]
This commit is contained in:
ltqin
2022-03-04 14:08:26 +08:00
committed by GitHub
parent be4f3d119b
commit 0180bb825c
22 changed files with 2652 additions and 94 deletions

View File

@@ -24,6 +24,7 @@ set(GEMM_XDL_ALPHA_BETA_SOURCE 8_gemm_xdl_alpha_beta/gemm_xdl_alpha_beta.cpp)
set(CONV2D_FWD_XDL_INT8_SOURCE 9_conv2d_fwd_xdl_int8/conv2d_fwd_xdl_int8.cpp)
set(CONV3D_FWD_XDL_SOURCE 10_conv3d_fwd_xdl/conv3d_fwd_xdl.cpp)
set(CONVND_FWD_XDL_SOURCE 11_convnd_fwd_xdl/convnd_fwd_xdl.cpp)
set(CONV2D_BWD_DATA_XDL_SOURCE 12_conv2d_bwd_data_xdl/conv2d_bwd_data_xdl.cpp)
add_executable(gemm_xdl ${GEMM_XDL_SOURCE})
add_executable(gemm_xdl_bias_relu ${GEMM_XDL_BIAS_RELU_SOURCE})
@@ -36,6 +37,7 @@ add_executable(gemm_xdl_alpha_beta ${GEMM_XDL_ALPHA_BETA_SOURCE})
add_executable(conv2d_fwd_xdl_int8 ${CONV2D_FWD_XDL_INT8_SOURCE})
add_executable(conv3d_fwd_xdl ${CONV3D_FWD_XDL_SOURCE})
add_executable(convnd_fwd_xdl ${CONVND_FWD_XDL_SOURCE})
add_executable(conv2d_bwd_data_xdl ${CONV2D_BWD_DATA_XDL_SOURCE})
target_link_libraries(gemm_xdl PRIVATE host_tensor)
target_link_libraries(gemm_xdl_bias_relu PRIVATE host_tensor)
@@ -48,3 +50,5 @@ target_link_libraries(gemm_xdl_alpha_beta PRIVATE host_tensor)
target_link_libraries(conv2d_fwd_xdl_int8 PRIVATE host_tensor)
target_link_libraries(conv3d_fwd_xdl PRIVATE host_tensor)
target_link_libraries(convnd_fwd_xdl PRIVATE host_tensor)
target_link_libraries(conv2d_bwd_data_xdl PRIVATE host_tensor)