The Procyon text-to-image AI Benchmark provides a consistent, accurate, and understandable workload for measuring the inference performance of powerful on-device AI accelerators such as high-end discrete GPUs. The benchmark features several AI inference engines from different vendors and was built in partnership with multiple key industry members to ensure it produces fair and comparable results across all supported hardware.
Please note:
Having the OpenCL compatibility pack installed on your system may cause additional duplicate devices to be available in the accelerator selection options. These duplicate devices may produce results that do not accurately reflect performance or outright fail. We recommend uninstalling the OpenCL compatibility pack to avoid this issue.