Add param to execute infer requests at a fixed frequency

Signed-off-by: Maciej Falkowski <[email protected]>
Signed-off-by: Ooi, Boon Sin <[email protected]>

samples/cpp/benchmark_app/benchmark_app.hpp

@@ -65,6 +65,11 @@ static const char cache_dir_message[] = "Optional. Enables caching of loaded mod
 static const char load_from_file_message[] = "Optional. Loads model from file directly without read_model."
                                              " All CNNNetwork options (like re-shape) will be ignored";
 
+/// @brief message for run frequency
+static const char run_frequency_message[] =
+    "Execute at a fixed frequency. Note if the targeted rate per second cannot be reached, "
+    "the benchmark would start the next run immediately, trying its best to catch up.";
+
 /// @brief message for execution time
 static const char execution_time_message[] = "Optional. Time in seconds to execute topology.";
 
@@ -307,6 +312,9 @@ DEFINE_string(api, "async", api_message);
 /// @brief Number of infer requests in parallel
 DEFINE_uint64(nireq, 0, infer_requests_count_message);
 
+/// @brief Execute infer requests at a fixed frequency
+DEFINE_double(rfreq, 0, run_frequency_message);
+
 /// @brief Number of streams to use for inference on the CPU (also affects Hetero cases)
 DEFINE_string(nstreams, "", infer_num_streams_message);
 
@@ -388,6 +396,7 @@ static void show_usage() {
     std::cout << "    -hint  <performance hint> (latency or throughput or cumulative_throughput or none)   "
               << hint_message << std::endl;
     std::cout << "    -niter  <integer>             " << iterations_count_message << std::endl;
+    std::cout << "    -rfreq \"<float>\"            " << run_frequency_message << std::endl;
     std::cout << "    -t                            " << execution_time_message << std::endl;
     std::cout << std::endl;
     std::cout << "Input shapes" << std::endl;

samples/cpp/benchmark_app/main.cpp

@@ -9,6 +9,7 @@
 #include <string>
 #include <utility>
 #include <vector>
+#include <thread>
 
 // clang-format off
 #include "openvino/openvino.hpp"
@@ -1153,6 +1154,11 @@ int main(int argc, char* argv[]) {
 
             execTime = std::chrono::duration_cast<ns>(Time::now() - startTime).count();
             processedFramesN += batchSize;
+
+            if (FLAGS_rfreq > 0) {
+                int64_t nextRunFinishTime = 1/FLAGS_rfreq * processedFramesN * 1.0e9;
+                std::this_thread::sleep_for(std::chrono::nanoseconds(nextRunFinishTime - execTime));
+            }
         }
 
         // wait the latest inference executions