Will Floating Point 8 Solve AI/ML Overhead?


While the media buzzes about the Turing Test-busting results of ChatGPT, engineers are focused on the hardware challenges of running large language models and other deep learning networks. High on the ML punch list is how to run models more efficiently using less power, especially in critical applications like self-driving vehicles where latency becomes a matter of life or death. AI already ... » read more

Big Changes In AI Design


Semiconductor Engineering sat down to discuss AI and its move to the edge with Steven Woo, vice president of enterprise solutions technology and distinguished inventor at Rambus; Kris Ardis, executive director at Maxim Integrated; Steve Roddy, vice president of Arm's Products Learning Group; and Vinay Mehta, inference technical marketing manager at Flex Logix. What follows are excerpts of that ... » read more

Advantages Of BFloat16 For AI Inference


Essentially all AI training is done with 32-bit floating point. But doing AI inference with 32-bit floating point is expensive, power-hungry and slow. And quantizing models for 8-bit-integer, which is very fast and lowest power, is a major investment of money, scarce resources and time. Now BFloat16 (BF16) offers an attractive balance for many users. BFloat16 offers essentially t... » read more

Making Better Use Of Memory In AI


Steven Woo, Rambus fellow and distinguished inventor, talks about using number formats to extend memory bandwidth, what the impact can be on fractional precision, how modifications of precision can play into that without sacrificing accuracy, and what role stochastic rounding can play. » read more