Zlobin Vladimir
67d25d7099
* Add sync_bnehcmark * Fix Unix comilation * niter->time * Explain main loop * samples: factor out common * Code style * clang-format -i * return 0; -> return EXIT_SUCCESS;, +x * Update throughput_benchmark * Add READMEs * Fix READMEs refs * Add sync_benchmark.py * Add niter, infer_new_request, -pc * from datetime import timedelta * Fix niter and seconds_to_run * Add disclaimer about benchmark_app performance * Update samples/cpp/benchmark/sync_benchmark/README.md * Add dynamic_shape_bert_benhcmark * Add dynamic_shape_detection_benchmark * Adopt for detr-resnet50 * Remove sync_benchmark2, throughput_benchmark2, perf counters * clang-format -i * Fix flake8 * Add README.md * Add links to sample_dynamic_shape_bert_benchmark * Add softmax * nameless LatencyMetrics * parent.parent -> parents[2] * Add bert_benhcmark sample * Code style * Add bert_benhcmark/README.md * rm -r samples/python/benchmark/dynamic_shape_bert_benhcmark/ * rm -r samples/cpp/benchmark/dynamic_shape_detection_benchmark/ * bert_benhcmark/README.md: remove dynamic shape * Remove add_subdirectory(dynamic_shape_detection_benchmark) * flake8 * samples: Add a note about CUMULATIVE_THROUGHPUT, don’t expect get_property() to throw, don’t introduce json dependency for samples/cpp/common * / namespace * Add article * namespace -> static * Update README, seconds_ro_run 10, niter 10, no inter alinment * percentile->median * benchmark samples: use generate(), align logs, update READMEs * benchmakr samples: remove percentile() * samples/python/benchmark/bert_benhcmark/bert_benhcmark.py: report average sequence length and processing time * Python samples: move requirements.txt to every sample * Remove numpy from requirements.txt * Remove Building section from Python samples, install only required extras from openvino-dev, set up environment for bert_benhcmark, report duration for bert_benhcmark * Install openvino-dev for Hello Reshape SSD C++ Sample
73 lines
2.9 KiB
C++
73 lines
2.9 KiB
C++
// Copyright (C) 2022 Intel Corporation
|
|
// SPDX-License-Identifier: Apache-2.0
|
|
//
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
// clang-format off
|
|
#include "openvino/openvino.hpp"
|
|
|
|
#include "samples/args_helper.hpp"
|
|
#include "samples/common.hpp"
|
|
#include "samples/latency_metrics.hpp"
|
|
#include "samples/slog.hpp"
|
|
// clang-format on
|
|
|
|
using Ms = std::chrono::duration<double, std::ratio<1, 1000>>;
|
|
|
|
int main(int argc, char* argv[]) {
|
|
try {
|
|
slog::info << "OpenVINO:" << slog::endl;
|
|
slog::info << ov::get_openvino_version();
|
|
if (argc != 2) {
|
|
slog::info << "Usage : " << argv[0] << " <path_to_model>" << slog::endl;
|
|
return EXIT_FAILURE;
|
|
}
|
|
// Optimize for latency. Most of the devices are configured for latency by default,
|
|
// but there are exceptions like MYRIAD
|
|
ov::AnyMap latency{{ov::hint::performance_mode.name(), ov::hint::PerformanceMode::LATENCY}};
|
|
|
|
// Create ov::Core and use it to compile a model.
|
|
// Pick a device by replacing CPU, for example AUTO:GPU,CPU.
|
|
// Using MULTI device is pointless in sync scenario
|
|
// because only one instance of ov::InferRequest is used
|
|
ov::Core core;
|
|
ov::CompiledModel compiled_model = core.compile_model(argv[1], "CPU", latency);
|
|
ov::InferRequest ireq = compiled_model.create_infer_request();
|
|
// Fill input data for the ireq
|
|
for (const ov::Output<const ov::Node>& model_input : compiled_model.inputs()) {
|
|
fill_tensor_random(ireq.get_tensor(model_input));
|
|
}
|
|
// Warm up
|
|
ireq.infer();
|
|
// Benchmark for seconds_to_run seconds and at least niter iterations
|
|
std::chrono::seconds seconds_to_run{10};
|
|
size_t niter = 10;
|
|
std::vector<double> latencies;
|
|
latencies.reserve(niter);
|
|
auto start = std::chrono::steady_clock::now();
|
|
auto time_point = start;
|
|
auto time_point_to_finish = start + seconds_to_run;
|
|
while (time_point < time_point_to_finish || latencies.size() < niter) {
|
|
ireq.infer();
|
|
auto iter_end = std::chrono::steady_clock::now();
|
|
latencies.push_back(std::chrono::duration_cast<Ms>(iter_end - time_point).count());
|
|
time_point = iter_end;
|
|
}
|
|
auto end = time_point;
|
|
double duration = std::chrono::duration_cast<Ms>(end - start).count();
|
|
// Report results
|
|
slog::info << "Count: " << latencies.size() << " iterations" << slog::endl
|
|
<< "Duration: " << duration << " ms" << slog::endl
|
|
<< "Latency:" << slog::endl;
|
|
size_t percent = 50;
|
|
LatencyMetrics{latencies, "", percent}.write_to_slog();
|
|
slog::info << "Throughput: " << double_to_string(latencies.size() * 1000 / duration) << " FPS" << slog::endl;
|
|
} catch (const std::exception& ex) {
|
|
slog::err << ex.what() << slog::endl;
|
|
return EXIT_FAILURE;
|
|
}
|
|
return EXIT_SUCCESS;
|
|
}
|