Grace Blackwell<\/a> platforms, plus Quantum InfiniBand networking, and new software for accelerating discovery.<\/p>\nThe latter comprises ALCHEMI, DAQIRI, and cuPhoton. The first is described by Nvidia as a domain-specific toolkit for chemical and material discoveries, using the BGR microservice for simulating millions of molecules and structures.<\/p>\n
DAQIRI is designed for the next-generation scientific instruments, connecting sensors directly to real-time AI inference points, Harris says. \u201cAt CERN’s ATLAS experiment, less than 2 percent of collision data can typically be stored. DAQIRI introduces a GPU accelerated AI trigger pipeline allowing FPGAs to handle low latency routing while GPUs run deep learning models to ensure we learn from significantly more data,\u201d he explained.<\/p>\n
Finally, cuPhoton is built to process petabytes of camera and telescope data to help scientists analyze massive cosmic data sets in minutes rather than months.<\/p>\n
\u201cIn testing with 32 Grace Blackwell superchips simulating data from the Rubin Observatory, cuPhoton loaded and read images 15,000 times faster and accelerated signal processing and analysis by up to 8,000 times,\u201d Harris claimed.<\/p>\n
But Nvidia is pitching its next-gen silicon as the platform for agentic supercomputing. Due to be available in Q4 this year, the Vera Rubin NVL rack will cram in up to 144 GPUs per rack, and deliver 5 petaFLOPS of FP64 floating-point performance.<\/p>\n
Because many high-performance computing workloads are often bound by memory performance, Vera Rubin increases memory bandwidth by 2.8 times compared to Blackwell, Harris says, using 41 TB of HBM4 memory per rack to achieve three petabytes per second of bandwidth.<\/p>\n
Systems that are getting Vera Rubin include the Mission and Vision systems at LANL. These stack up to 2,160 Rubin GPUs plus 1,080 Vera CPUs, in the case of Mission, while Vision has a more modest 1,298 Rubins and 648 Veras.<\/p>\n
\u201cThen there’s Veritas, which is being announced at ISC, which deploys 576 Rubin GPUs, along with 288 Vera CPUs,\u201d Harris says.<\/p>\n
We asked Nvidia what the purpose is of embedding agentic AI into scientific computing, much of which is about research driven by human curiosity.<\/p>\n
\u201cAgentic AI, or in fact any AI, is not required to do science,\u201d Harris told The Register.<\/p>\n
\u201cBut Nvidia believe agentic AI is already emerging as a powerful tool to do science at a scale that isn\u2019t possible when human scientists alone drive the process. Agents don\u2019t need to sleep, or eat, or take breaks.\u00a0 They can consume thousands or millions of technical papers and remember the details, and in some cases, they benefit from PhD-level understanding across diverse fields from astrophysics to zoology,\u201d he said.<\/p>\n
Nvidia\u2019s vision is that human scientists will have a team of agents running around the clock, able to do investigations they couldn\u2019t themselves perform.<\/p>\n
\u201cBut agents require foundation models, LLMs, and connections to data and tools to perform science.\u00a0 They run on CPUs, but access tools, many of which need GPUs to run at maximum performance and efficiency,\u201d Harris added.<\/p>\n
Nvidia claims that Europe is now a hotspot for HPC, with 35 new supercomputers brought online in the past year, all using Nvidia tech. These include Jupiter<\/a>, Europe\u2019s exascale system, MareNostrum 5 at the Barcelona supercomputing center, Bavaria AI’s Blue Swan, HammerHAI at the University of Stuttgart, and Italy\u2019s CINECA. \u00ae<\/p>\n","protected":false},"excerpt":{"rendered":"Nvidia is pushing agentic AI for scientific computing, and says that this requires a new scientific computing stack,…\n","protected":false},"author":2,"featured_media":653267,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-653266","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/653266","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=653266"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/653266\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/653267"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=653266"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=653266"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=653266"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}