Running the benchmark
The release comes with a benchmark script that can be used to measure the performance of the accelerator for a variety of models. The script uses the vollo compiler to compile the models for your accelerator and then runs the models on the accelerator to measure the performance.
-
Install the script dependencies:
sudo apt install python3-venv jqNote, the compiler requires python 3.7 or later.
-
Ensure you have run the setup steps:
cd <vollo-sdk> sudo ./load-kernel-driver.sh source setup.sh export MYRTLE_LICENSE=<your-license-file> -
Run the benchmark:
$VOLLO_SDK/example/benchmark.shWith
RUN_IO_TEST=1it also measures the IO round trip for input and output sizes from 64 B to 16 KiB, using the runtime's defaults. It writeswork/io-test-metrics.csv, to compare with the "User buffers" tables, andwork/io-test-raw-buffer-metrics.csv, to compare with the "Raw DMA buffers" tables. -
You can cross reference your numbers with those in the benchmarks section of the documentation.