{"id":156,"date":"2019-02-04T16:55:17","date_gmt":"2019-02-04T15:55:17","guid":{"rendered":"http:\/\/blog.zhaw.ch\/high-performance\/?p=156"},"modified":"2019-04-01T11:06:26","modified_gmt":"2019-04-01T09:06:26","slug":"intedgperf-a-new-ai-benchmark-for-embedded-processors","status":"publish","type":"post","link":"https:\/\/blog.zhaw.ch\/high-performance\/2019\/02\/04\/intedgperf-a-new-ai-benchmark-for-embedded-processors\/","title":{"rendered":"IntEdgPerf: A new AI benchmark for embedded processors"},"content":{"rendered":"\n

IntEdgPerf is a new benchmark for running machine learning algorithms on embedded devices. It was developed at the Institute of Embedded Systems (InES) at the Z\u00fcrich University of Applied Sciences. IntEdgPerf is a framework that allows a fair comparison between different embedded processors that can be used for executing neural networks. <\/p>\n\n\n\n

The area of embedded AI is a quickly emerging market where many hardware manufacturers provide accelerators and platforms. So far, metrics and benchmarks provided by the manufacturers are not usable for comparison.<\/p>\n\n\n\n

<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

IntEdgPerf incorporates a collection of multiple TensorFlow AI models. It measures the time for the computations of the machine learning algorithm on embedded devices. The benchmark is dynamically extendable by allowing new machine learning models to be integrated. Hardware specific calls can be implemented as modules and integrated in the benchmark. <\/p>\n\n\n\n

The benchmark was verified on multiple processors and machine learning accelerators such as Nvidia Quadro K620 GPU, Nvidia Jetson TX1 & TX2 and an Intel Xeon E3-1270V5. Also hardware accelerators, without a direct interface to TensorFlow, such as the Intel Movidius Neural Compute Stick were benchmarked. All tests used unoptimized networks and systems.<\/p>\n\n\n\n

The following convolutional models were used in the test: <\/p>\n\n\n\n