Nvidia CEO promises sustainability salvation in the cult of accelerated computing
Having built the hardware, its clear that Nvidia's next step is to go after and build software libraries to accelerate workloads in every industry that relies on CPUs today — in effect creating new markets for its hardware. The company's new computational lithography libraries are
of just that, with Huang claiming that TSMC could replace its 40,000 CPU nodes with as few as 500 DGX H100 servers while cutting power consumption from 35MW to 5MW in the process.
AMD's answer to this involves a variety of compute architectures and design principles, including several, like chiplets, that it pioneered. Using these technologies AMD is working to embed accelerators of all kinds into its platforms. For example, the company's upcoming MI300 APU melds Zen 4 CPU cores with its CDNA3 GPUs and a boatload of high bandwidth memory.
The x86 contender is also working to build FPGAs, AI accelerators, and DPUs, acquired from Xilinx and Pensando, into their chips to accelerate more workloads and improve compute efficiency.dies are already consumed by dedicated accelerators for machine learning, cryptography, compression, data-streaming, analytics, and security.
Intel is also working on an APU of its own — though it prefers the term XPU — called Falcon Shores, though that platform has beenNvidia is therefore far from the only chipmaker advocating more use of accelerators. ®
Australia Latest News, Australia Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Pro overclocker bricks AMD's best gaming chip without really tryingMaybe don't overvolt the Ryzen 9 7950X3D past 1.35V, just in case.
Read more »
Oops! Leaked RTX 4070 and 4060 GPUs spoil Nvidia’s partyRTX 4070 and 4060 accidently revealed – and Nvidia must be fuming
Read more »
Watch Nvidia's GTC 2023 keynote right here todayIt's going to be AI as far as the digital eye can see at Nvidia's GTC keynote today. Kicking off in 10 minutes time!
Read more »
Nvidia just took two H100 cards and glued them togetherDon’t need a 700W fire-breathing GPU? It also launched an itty-bitty AI chip too
Read more »
Nvidia hooks TSMC and friends on GPU accelerated chip designWhat's next – AI designing AI chips? Oh wait... that's exactly what's next
Read more »
Nvidia says its new AI tools are like a chip foundry for large language modelsNvidia's bringing us a new way to integrate AI language models into businesses.
Read more »