apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Backend] support bechmark mode for runtime and backend (#1201)

Browse Source 
* [backend] support bechmark mode for runtime and backend

* [backend] support bechmark mode for runtime and backend

* [pybind11] add benchmark methods pybind

* [pybind11] add benchmark methods pybind

* [Other] Update build scripts

* [Other] Update cmake/summary.cmake

* [Other] update build scripts

* [Other] add ENABLE_BENCHMARK option -> setup.py

* optimize backend time recording

* optimize backend time recording

* optimize trt backend time record

* [backend] optimze backend_time recording for trt

* [benchmark] remove redundant logs

* fixed ov_backend confilct

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] remove use_gpu option from ort backend option

* [benchmark] update benchmark_ppdet.py

* [benchmark] update benchmark_ppcls.py

* fixed lite backend conflicts

* [Lite] fixed lite xpu

* add benchmark macro

* add RUNTIME_PROFILE_LOOP macros

* add comments for RUNTIME_PROFILE macros

* add comments for new apis

* add comments for new apis

* update benchmark_ppdet.py

* afixed bugs

* remove unused codes

* optimize RUNTIME_PROFILE_LOOP macros

* optimize RUNTIME_PROFILE_LOOP macros

* add comments for benchmark option and result

* add docs for benchmark namespace
This commit is contained in:
DefTruth
2023-02-06 14:29:35 +08:00
committed by GitHub
parent 42d14e7119
commit f73a538f61
34 changed files with 741 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
fastdeploy/fastdeploy_model.h
View File

@@ -75,7 +75,7 @@ class FASTDEPLOY_DECL FastDeployModel {
return runtime_initialized_ && initialized;
}
/** \brief This is a debug interface, used to record the time of backend runtime
/** \brief This is a debug interface, used to record the time of runtime (backend + h2d + d2h)
*
* example code @code
* auto model = fastdeploy::vision::PPYOLOE("model.pdmodel", "model.pdiparams", "infer_cfg.yml");
@@ -98,7 +98,7 @@ class FASTDEPLOY_DECL FastDeployModel {
enable_record_time_of_runtime_ = true;
}
/** \brief Disable to record the time of backend runtime, see `EnableRecordTimeOfRuntime()` for more detail
/** \brief Disable to record the time of runtime, see `EnableRecordTimeOfRuntime()` for more detail
*/
virtual void DisableRecordTimeOfRuntime() {
enable_record_time_of_runtime_ = false;
@@ -113,6 +113,11 @@ class FASTDEPLOY_DECL FastDeployModel {
virtual bool EnabledRecordTimeOfRuntime() {
return enable_record_time_of_runtime_;
}
/** \brief Get profile time of Runtime after the profile process is done.
*/
virtual double GetProfileTime() {
return runtime_->GetProfileTime();
}
/** \brief Release reused input/output buffers
*/
@@ -153,13 +158,13 @@ class FASTDEPLOY_DECL FastDeployModel {
bool CreateTimVXBackend();
bool CreateKunlunXinBackend();
bool CreateASCENDBackend();
bool IsSupported(const std::vector<Backend>& backends,
Backend backend);
std::shared_ptr<Runtime> runtime_;
bool runtime_initialized_ = false;
// whether to record inference time
bool enable_record_time_of_runtime_ = false;
// record inference time for backend
std::vector<double> time_of_runtime_;
};