by Karl Freund | Jun 13, 2023 | In the News
AMD disclosed a few more details on the MI300 GPU, due later this year, with support for 192GB of memory on the MI300X. Here’s what we know. In today’s world of ChatGPT, everyone keeps asking if the NVIDIA A100 and H100 GPUs are the only platforms that can deliver the...
by Karl Freund | May 23, 2023 | In the News
NVIDIA Announces First Arm-Based Supercomputer Without GPUs The fact that NVIDIA is partnering with HPE to build a Grace-based Supercomputer should not surprise anyone. They had previously announced two; a monster machine called Alps at the Swiss National...
by Karl Freund | Apr 7, 2023 | Video
Raja Koduri, ex chief of GPUs at Intel and AMD, has joined the board of directors at Tenstorrent. See what he thinks about the company, and the potential of RISC-V in the data center in this lively interview. More Cambrian-AI Visions Video Interviews Shankar...
by Karl Freund | Jan 23, 2023 | In the News
The upcoming MI300, which will ship Latter this year after NVIDIA’s Grace/Hopper Superchip, certainly has a shot at it. But there remain a lot of unknowns that will determine how well it performs for AI applications. And then there is Software. Yeah, Software. Lots of...
by Karl Freund | Nov 20, 2022 | In the News
While the new H100 GPU shows off its Transformer Engine in MLPerf, Intel advances with Gaudi-2 accelerator, and MosaicML shows A100 results nearly as good as H100 with their software. Every six months, MLCommons orchestrates and publishes on mlcommons.org over one...
