It has been becoming increasingly clear – anecdotally at least – just how expensive it is to train large language models and recommender systems, which are arguably the two most important workloads driving AI into the enterprise. …
Changing the compute paradigm in the datacenter, or even extending it or augmenting it in some fashion, is no easy task. …
When we last focused on Untether AI in 2021, the AI inferencing hardware startup had just secured $125 million in funding, which came a year after the company officially launched with its first-generation runAI200 devices and its unique at-memory inferencing approach. …
In March, Nvidia introduced its GH100, the first GPU based on the new “Hopper” architecture, which is aimed at both HPC and AI workloads, and importantly for the latter, supports an eight-bit FP8 floating point processing format. …
When it comes to building any platform, the hardware is the easiest part and, for many of us, the fun part. …
UPDATED* Perhaps Janet Jackson should be the official spokesperson of the supercomputing industry. …
We have been excited about the possibilities of adding tiers of memory to systems, particularly persistent memories that are less expensive than DRAM but offer similar-enough performance and functionality to be useful. …
Exascale supercomputing is just as important to Europe as it is to the United States and China, but each of these geopolitical regions on Earth has its own way of developing architectures, funding their development and production, and figuring out where the best HPC centers are to host such machines to maximize their effectiveness. …
Nvidia is not the only company that has created specialized compute units that are good at the matrix math and tensor processing that underpins AI training and that can be repurposed to run AI inference. …
There is increasing competition coming at Nvidia in the AI training and inference market, and at the same time, researchers at Google, Cerebras, and SambaNova are showing off the benefits of porting sections of traditional HPC simulation and modeling code to their matrix math engines, and Intel is probably not far behind with its Habana Gaudi chips. …
All Content Copyright The Next Platform