The latest Procyon AI benchmark

(Auszug aus der Pressemitteilung)

This week, we published a news post looking at how Artificial Intelligence (AI) is changing the way we work. A creative disrupter, AI is growing rapidly and changing the kinds of autonomous work that needs to be performed by a person.

Many technology publications and reviewers predict that AI features will soon be embedded into future laptops and PCs, further simplifying and automating human-led tasks throughout our working days.

The newest Procyon® AI benchmark

Our recently launched AI Inference Benchmark for Windows addresses the demand for ways to better measure the performance of AI capabilities. Developed for industry vendors developing and using the latest advances in AI technology, this Procyon Benchmark provides a neutral industry standard tool for measuring and comparing the performance of dedicated AI hardware. Software development kits (SDKs) used to measure the AI interference performance include Microsoft® Windows ML, Qualcomm® SNPE, Intel® OpenVINO™ and NVIDIA® TensorRT™.

A benchmark that can provide insights for the next generation of technology

The Procyon AI Inference Benchmark for Windows runs performance tests, comparing different accelerators like CPUs, GPUs and dedicated accelerators and providing data surrounding inference performance of integer and floating-point accuracy. These comparisons can help you decide which inference engine will give you optimal performance in your use case, with results providing critical insights for the next generation of personal and professional devices.

The benchmark currently supports using image classification, image segmentation, object detection and super-resolution as its AI workloads. The development of this benchmark is ongoing to guarantee it stays industry relevant, with additional tests added as new AI use cases emerge.