Search Results For: petaflops
NVIDIA's Blackwell GB200 is an absolutely monstrous processor with up to 10 petaflops of dense FP4 tensor compute and 192GB of lightning-fast HBM3e memory delivering 8 TB/second of bandwidth per GPU. That number, though, that 192GB, is still limiting for hyperscalers building the latest, greatest AI models. For...
Read more...
Building out the datacentersor as NVIDIA calls them, "AI factories"required for training and operating state-of-the-art AI models is extremely expensive. So much so that even hyperscalers like Google and Microsoft are going to have to plan these purchases well in advance. To that end, NVIDIA offered a sneak peek of...
Read more...
The NVIDIA GTC AI Development conference started yesterday, but the big announcements are coming in fast and furious today. This one is all about some powerful AI development hardware, known as DGX Spark and DGX Station. These names come out of left field, but the technology upon which they are built is a known...
Read more...
In the market for a PC upgrade and looking for the most powerful rig to mine cryptocurrency, simulate black holes, or something you can run an incredible AI model off of? If you just so happen to have $75,000, if not more, and the space and power requirements for it, the National Center For Atmospheric Research (NCAR)...
Read more...
Some people have claimed that AI is a fad, or a flash in the pan. It's easy to understand the perspective; the hype around the explosion of generative AI feels similar to the hype around previous fads, like 3D TVs or the metaverse. AI isn't a fad, though. It is already transforming every single part of the tech...
Read more...
Although Intel and Argonne National Laboratory declared the Aurora supercomputer to be finally complete earlier this year, apparently it's not fully up and running just yet. It's only running with half of its 21,248 Xeon Max Sapphire Rapids CPUs and 63,744 Ponte Vecchio GPUs, which allowed it to snag second place in...
Read more...
Modern scientific breakthroughs aren't solely relegated to a lab these days, but also come by way of the massive compute resources that modern data centers full of servers can muster. For researchers, maintaining open access to these invaluable complexes has been vital. The Stampede and Stampede2 supercomputer...
Read more...
Intel's Data Center Max products are very impressive, but you may have had a hard time getting your hands on one even though they officially launched way back in November of last year. How come? Because they've all been going to Argonne National Laboratory. The Aurora supercomputer hosted there was planned to host...
Read more...
Back in the 1990s, NVIDIA got its start selling graphics adapters for desktop PCs. After a rocky start with the NV1, NVIDIA established itself as a performance leader soon thereafter with the release of the TwiN-Texel (TNT) chip, and with the original GeForce 256, as a technology leader, too.
That's all ancient...
Read more...
Intel has announced a launch date for its mobile family of Arc A-series GPUs, and answered three of the top questions concerning its upcoming Arc GPUs. In an online event at the end of the month, the tech company will showcase Intel technologies such as Intel Deep Link, XeSS and more.
Intel announced earlier this...
Read more...
Mark Zuckerberg and the gang over at Meta, the parent company to Facebook, have a new and powerful toy to play with courtesy of a collaboration with NVIDIA. Meta designed and NVIDIA built what is called the AI Research SuperCluster (RSC), a massive supercomputer that once fully deployed will rank as the largest...
Read more...
NVIDIA is quite literally taking its cloud game streaming service, GeForce NOW, to the next level by adding vastly upgraded game servers to the mixor as NVIDIA calls them, GeForce NOW SuperPODs. These SuperPODs purportedly deliver "GeForce RTX 3080-class gaming" on the company's cloud service, and are being made...
Read more...
Most people would be happy just to get their mitts on a single GPU, in the current landscape. The US Department of Energy's Argonne National Laboratory is much more fortunate, having procured a whopping 2,240 NVIDIA A100 Tensor Core GPUs (based on Ampere) for its Polaris supercomputer to "supercharge researcher and...
Read more...
Though it has been more than a few weeks, and we have long since passed the end of 2020, the U.Ks most powerful supercomputer is now operational. Powered by NVIDIA hardware, the Cambridge-1 is a $100 million, 400 petaflop beast of a computer that ranks among the worlds top 50 fastest computers and is powered by 100...
Read more...
Have you ever had a friend or family member casually drop big news on you, as if the subject they are talking about is an everyday occurrence? For example, "Yeah, the weather was great this weekend, I got a lot of yard work done. Next month I'm going to the moon with Elon Musk. Oh, I bought a new hedge trimmer at...
Read more...
NVIDIA's A100 based on Ampere was already considered the go-to GPU for high performance computing (HPC), but lest any challengers seek to knock the part off its perch, they will now have to contend with a version that has twice as much high bandwidth memory as before, with a massive 80GB HBM2e memory buffer. Yeah...
Read more...
A few weeks ago, Azure received an NVIDIA A100 upgrade to its virtual machines. Announced at GTC, NVIDIA is now building its supercomputer with the A100 platform across the pond. This behemoth, dubbed Cambridge-1, will be the most powerful supercomputer operating within the United Kingdom. It will become available to...
Read more...
NVIDIA has partnered with the University of Florida (UF) to build an artificial intelligence (AI) supercomputer that will be the fastest in all of academia. Or more specifically, it will be capable of a whopping 700 petaflops of AI performance, made possible by enhancing the university's existing HiPerGator...
Read more...
The 55th edition of the Top500 supercomputers list was published, and a supercomputer from Japan has taken the top spot on the list. The supercomputer is called Fugaku, and it turned in a High Performance Linpack (HPL) result of 415.5 petaflops beating the Summit supercomputer by a factor of 2.8 times to take...
Read more...
The Coronavirus pandemic has been depressing on multiple levels (not the least of which is the loss of life), and who knows if we will still be collectively cooped up this summer. Even if so, there is something look forward tothe potential launch of next generation GPUs from both AMD and NVIDIA, at the tail end of...
Read more...
We've been hearing about NVIDIA's next-generation Ampere for the past two years, but the company is finally ready to talk about its next-generation GPU architecture. Though you won't hear any info today aboutGeForce RTX 30 Seriesof consumer gaming graphics cards, NVIDIA is discussing details about Ampere for machine...
Read more...
Unless all of the leaks and rumors have it wrong, NVIDIA will eventually roll out Ampere, it's next-generation GPU architecture for high-performance computing (HPC) workloads and presumably consumer applications as well (GeForce RTX 3080 Ti, anyone?). As it pertains to the former, an interesting trademark application...
Read more...
