As we saw last week in our special report on EDA startups, deep learning acceleration startups are more numerous and are getting much more funding. It’s therefore interesting to read the following comment by processor analyst Linley Gwennap: “Well-funded startups, including several unicorns, have been unable to demonstrate any advantage over Nvidia’s Ampere products, much less the upcoming Hopper generation. (…) Cerebras, Groq, and SambaNova, along with leading Chinese startups Enflame and Iluvatar, are in production but have published few or no benchmarks, probably owing to some combination of deficient hardware and unoptimized software. Of the best-funded AI-chip startups, only Graphcore has provided official MLPerf results, falling well short of Ampere in per-chip performance and power efficiency.” Let’s now move to this week’s news round-up, catching up on some of the updates from the last twenty days or so.
Cadence launches a computational fluid dynamics software suite
Cadence has recently introduced its Fidelity CFD Software, a suite of computational fluid dynamics solutions for multiple markets, including automotive, turbomachinery, marine, aerospace and others. The suite builds upon the expertise and technology that Cadence has gained from the Numeca and Pointwise acquisitions.