If you were expecting Nvidia to start talking about its future “Einstein” GPUs for Tesla accelerated computing soon just because AMD is getting ready to roll out “Navi” GPUs next year and Intel is working on its Xe GPU cards for delivery next year, too, you are going to have to wait a bit longer. …
Nvidia Readies For Battle In The Datacenter In 2020 was written by Timothy Prickett Morgan at .
In any chip design, the devil – and the angel – is always in the details. …
A Deep Dive Into AMD’s Rome Epyc Architecture was written by Timothy Prickett Morgan at .
As artificial neural networks for natural language processing (NLP) continue to improve, it is becoming easier and easier to chat with our computers. …
Nvidia Elevates The Conversation For Natural Language Processing was written by Michael Feldman at .
After a long wait, now we know. All three of the initial exascale-class supercomputer systems being funded by the US Department of Energy through its CORAL-2 procurement are going to be built by Cray, with that venerable maker of supercomputers being the prime contractor on two of them. …
Cray Runs The Exascale Table In The United States was written by Timothy Prickett Morgan at .
Under two unrelated US Department of Defense procurements, Cray has been awarded a total of $71 million to supply the Air Force and Army with a trio of HPC systems. …
US Military Buys Three Cray Supercomputers was written by Michael Feldman at .
Accelerators of many kinds, but particularly those with GPUs and FPGAs, can be pretty hefty compute engines that meet or exceed the power, thermal, and spatial envelopes of modern processors. …
Xilinx Keeps A Low Profile With Mainstream FPGA Accelerator was written by Michael Feldman at .
AMD had been down this road before. In 2003, the chip maker launched the “SledgeHammer” Opteron, the first 64-bit X86 server processor with backward compatibility to its 32-bit predecessors that came at a time when much larger rival Intel was still pumping up Itanium as the next-generation architecture – and its only 64-bit option. …
With Rome, AMD Will Build Off Momentum For Naples Epyc Chips was written by Jeffrey Burt at .
Nvidia has unveiled GPUDirect Storage, a new capability that enables its GPUs to talk directly with NVM-Express storage. …
Nvidia GPU Accelerators Get A Direct Pipe To Big Data was written by Michael Feldman at .
It has been a long time coming: The day when AMD can put a processor up against any Xeon that Intel can deliver and absolutely compete on technology, price, predictability of availability, and consistency of roadmap looking ahead. …
AMD Doubles Down – And Up – With Rome Epyc Server Chips was written by Timothy Prickett Morgan at .
As the lead engineer on the Power10 processor, Bill Starke already knows what most of us have to guess about Big Blue’s next iteration in a processor family that has been in the enterprise market in one form or another for nearly three decades. …
Talking High Bandwidth With IBM’s Power10 Architect was written by Timothy Prickett Morgan at .
The IT industry is all about evolution, building on what’s been done in the past to address the demands of the future. …
Paving The Way For Two System Architecture Paths was written by Jeffrey Burt at .
Intel has started shipping a new FPGA accelerator card based on the high-end Stratix 10 SX FPGA. …
Stratix 10 SX At The Heart Of Intel’s Most Powerful FPGA Accelerator was written by Michael Feldman at .
The handwriting has been on the wall for some time now, but Intel has quietly dropped its 200 Gb/sec Omni-Path networking from its roadmaps and will be using other technology for interconnects going forward. …
Intel Goes Barefoot As It Leaves The Omni-Path was written by Timothy Prickett Morgan at .
The growing imbalance between computational performance and data access performance has spurred the development of a number of new random access memory (RAM) technologies. …
New Memory Technologies Poised for High Volume Production was written by Michael Feldman at .
The good news about having a diverse product line, as chip maker AMD increasingly does, is that the company operates like a multi-cylinder engine and that not all of the lines need to be firing full bore for the business to accelerate down its roadmap. …
Rome Is The Fulcrum Of AMD’s Datacenter Pivot was written by Timothy Prickett Morgan at .
Enterprises are putting a lot of time, money, and resources behind their nascent artificial intelligence efforts, banking on the fact that they can automate the way application leverage the massive amounts of customer and operational data they are keeping. …
Bringing DevOps Control To Bear On AI Applications was written by Jeffrey Burt at .
Nvidia’s DGX platforms are powerhouses for training neural networks, offering up to 2 petaflops of peak machine learning performance. …
Sometimes, AI Hardware Economics Argues For Colocation was written by Michael Feldman at .
There has never been a better time to wait to buy processors for servers, and in the second quarter of this year, based on the financial results that Intel has turned in, many companies did just that. …
Real Competition Puts Intel Data Center Group In The Pinchers was written by Timothy Prickett Morgan at .
Microsoft is investing $1 billion in AI research company OpenAI to build a set of technologies that can deliver artificial general intelligence (AGI). …
The Singularity Is Nearer: Microsoft Places $1 Billion Bet On Artificial General Intelligence was written by Michael Feldman at .
In the HPC cloud business, Oracle is a relative newcomer. As we reported in November 2018, the company jumped into the fray less than a year ago with HPC bare metal servers hooked together with a 100 Gb/sec RDMA network. …
Bare Metal Cloud Takes the Fight To On-Premise HPC Clusters was written by Michael Feldman at .