San Jose, California, December 6, 2023 – GigaIO, provider of open workload-defined infrastructure for AI and accelerated computing, has announced what the company said is the largest order yet for its SuperNODE utilizing tens of thousands of the AMD Instinct MI300X accelerators. GigaIO’s infrastructure will form the backbone of a bare-metal specialized AI cloud code-named […]
Taking on NVIDIA: AMD Announces Availability of MI300 GPU Accelerators
December 6, 2023 by
After years of NVIDIA having its dominant way in the GPU AI chip market — a market that has exploded over the last 12 months with the emergence of generative AI — AMD today announced the availability of the long-awaited and much previewed MI300X accelerator chip (pictured here) that AMD intends to be a worthy competitor with NVIDIA’s H100….
HPC News Bytes 20231204: The New Yorker on NVIDIA, the Open Benchmark Council, Intel and TSMC, Digital Twins for Hydropower
December 4, 2023 by
Here’s a sprint (5:16) through the latest HPC -AI news, including: NVIDIA’s big feature story in The New Yorker, the Open Benchmark Council’s TOP100 lists, Intel and TSMC’s high-end 3 nanometer fab, digital twins for hydropower at ORNL and PNNL.
@HPCpodcast: Tech Analyst Adrian Cockcroft on Trends Driving Future HPC Architectures
November 30, 2023 by
Along with his article to be found on this site, technology analyst Adrian Cockcroft of OrionX (and former AWS vice president) joins Shahin and Doug after SC23 to discuss TOP500 trends, the AI-HPC crossover, liquid cooling, chiplets, and the emergence of UCIe and CXL – some of the anticipated advancements are truly eye-popping. In this podcast, sponsored by Lenovo, the relentless pursuit of higher performance, the acceleration in the pace of change in high performance processing, is examined.
SC23: TOP500 Trends, the AI-HPC Crossover, Chiplet Standardization, the Emergence of UCIe and CXL Advancements
November 29, 2023 by
By Adrian Cockcroft, Partner & Analyst, OrionX Last year the UCIe chiplet standard had just been launched, and since then just about everyone has joined it, about 130 companies. The idea is that to build a complete CPU or GPU you don’t have to put it all on the same chip from the same….
AWS Unveils Graviton4, Trainium2 Chips
November 28, 2023 by
Today at AWS re:Invent, Amazon Web Services announced the next generation of two AWS-designed chip families — AWS Graviton4 and AWS Trainium2 — that the company said delivers advancements in price performance and energy efficiency for such workloads as machine learning (ML) training and generative artificial intelligence (AI) applications.
AMD-based HPC Systems on TOP500 Grows 39%
November 14, 2023 by
SANTA CLARA, Calif., — Nov. 14, 2023 — Today, AMD said its microprocessors now power 140 supercomputers on the latest Top500 list, representing a 39 percent year-over-year increase. Additionally, AMD powers 80 percent of the top 10 most energy efficient supercomputers in the world based on the latest Green500 list. “AMD technology continues to be […]
MLPerf Training and HPC Benchmark Show 49X Performance Gains in 5 Years
November 8, 2023 by
MLCommons said the results highlight performance gains of up to 2.8X compared to 5 months ago and 49X over the first results five years ago, “reflecting the tremendous rate of innovation in systems for machine learning,” the organizations said.
Optical I/O Takes Center Stage at SC23
November 7, 2023 by
[SPONSORED GUEST ARTICLE] Integration of optical I/O with an FPGA is the tip of the iceberg of a new vision to enable new HPC/AI architectural advances through ubiquitous optical interconnects for every piece of compute silicon. If you are attending SC23 November 12-17, be sure to visit Ayar Labs in booth #228 for an exclusive look at the future….
Taming the Exascale Beast: Challenges and Solutions in Architecting JUPITER
November 1, 2023 by
In this sponsored article, Crispin Keable PhD., senior solution architect developing HPC, AI and quantum systems for Eviden (an Atos business), discusses how his philosophy is and always has been to help customers achieve their scientific, technical, and engineering goals by using the best technology now and tomorrow…..
