The Latest News in AI
We publish news articles on Forbes, which are copied here for your convenience.
A Closer Look At Graphcore ML Performance
Greater scalability and new software increases performance by 50-fold over the last twelve months. Graphcore, the UK-based AI Unicorn, submitted a raft of new benchmarks to MLCommons in December, which we covered here. Performance improved significantly with the...
The IBM Research AI Hardware Center: Solid Progress, Aggressive Goals
IBM AI acceleration technologies are becoming so good, most AI chip companies would be better off licensing core AI tech from IBM. Creating and using massive AI networks is quickly becoming unaffordable: Open.AI’s GPT-3 cost over $12M to train using thousands of GPU’s...
NVIDIA Again Claims The Title For The Fastest AI; Competitors Disagree
Intel Habana Labs and Graphcore add scale and software optimizations, while Google skips this round, choosing to put a stake in the ground for half-trillion parameter models. Every six months, the AI hardware community gathers virtually to strut their hardware stuff...
NVIDIA Is Not A Chip Company. It’s A Platform Company.
NVIDIA extends its lead in accelerated computing, announcing platforms for the metaverse, healthcare, enterprise AI, autonomous vehicles, and data center security at the GTC Conference. NVIDIA, probably on its way to becoming a trillion dollar company, has been...
AMD Launches New GPU And EPYC CPU Right Across NVIDIA’s Bow
The Instinct MI200 is nearly five times faster than the NVIDIA A100 for HPC, but is theoretically only 20% faster for AI. One year ago I complained that the newly announced AMD MI100 GPU was great for HPC, but inadequate for most AI workloads. Now AMD has announced...