IBM’s new AI Hardware Composer tool aims to boost the performance of analog AI hardware.

The tool is being released on the second anniversary of the IBM Research AI Hardware Center. IBM’s pioneering centre launched in 2019 with the aim of improving AI hardware compute efficiency by 2.5 times every year for a decade.

AI Hardware Composer claims to help both novice and experienced developers to create neural networks and tune analog devices to build accurate AI models.

The new tool can be used with IBM’s existing Analog Hardware Acceleration Kit (AIHWKIT), an open-source Python toolkit for exploring and using the capabilities of in-memory computing devices in the context of artificial intelligence.

IBM says AI researchers can use Composer and AIHWKIT to test the company’s neural network optimisation tools and design analog hardware-aware models.

The AI Hardware Center has, so far, been exceeding its 2.5 times per year performance improvement target.

In a paper presented at the 2021 International Solid-State Circuits Virtual Conference (ISSCC), IBM explained how it doubled its training projection and outperformed its inference target sixfold.

Six companies joined IBM in founding the AI Hardware Center—Samsung, Synopsys, Tokyo Electron Limited, Applied Materials, SUNY Polytechnic Institute, and Rensselaer Polytechnic Institute (RPI). As of writing, the centre now boasts 16 industry and academic members.

(Image Credit: IBM)

Interested in hearing industry leaders discuss subjects like this? Attend the co-located 5G Expo, IoT Tech Expo, Blockchain Expo, AI & Big Data Expo, and Cyber Security & Cloud Expo World Series with upcoming events in Silicon Valley, London, and Amsterdam.

Tags: ai, aihwkit, analog hardware acceleration kit, artificial intelligence, Featured, hardware, hardware composer, ibm, python