TECH TALK

AI > A Deep Dive into a Deep Learning Library for the A64FX Fugaku CPU – Meet the Developer

Kentaro Kawakami will share the development story to get oneAPI oneDNN on Arm for the A64FX Fugaku CPU. Fujitsu managed to make full use of Arm SVE architecture, and succeeded in improving performance by 9.2 times in training and 7.8 times in inference. Using the oneAPI oneDNN Open Source, Fujitsu managed to achieve the best performance as a CPU with MLPerf HPC v0.7. Kawakami and his team optimized and ported the oneDNN DL process library software (which continues to be developed as OSS) for the Armv8-A instruction set so that it can run at high speed on the Fugaku supercomputer. The new Fugaku supercomputer has been delivered to Port Island located off the coast of Kobe. Developed jointly by RIKEN and Fujitsu, this supercomputer has entered the trial run phase. As of June 2020, it had already won four “firsts” in worldwide supercomputer rankings (TOP500, HPCG, HPL-AI, Graph500), so it is off to a very promising start.

Download Ketaro Kawakami, AI A Deep Dive into a Deep Learning Library for the A64FX Fugaku CPU Presentation

For background, please see the following blogs and press releases:

https://blog.fltech.dev/entry/2020/11/19/fugaku-onednn-deep-dive-en

https://github.com/oneapi-src/oneAPI-tab/blob/main/tab-ai/presentations/oneAPI_development_of_oneDNN_for_Armv8-A_SVE_20210210_v4.pdf

https://www.fujitsu.com/global/about/resources/news/press-releases/2020/1119-02.html

×

Learn DPC++ for Free

Learn More