It is hard enough to chase one competitor. Imagine how hard it is to chase two different ones in different but complementary markets while at the same time those two competitors are thinking about fighting each other in those two different markets and thus bringing even more intense competitive pressure on both fronts. …
AMD At A Tipping Point With Instinct MI100 GPU Accelerators was written by Timothy Prickett Morgan at The Next Platform.
Targeting HPC, AI, Analytics trifecta: A100 GPUs get double the memory with 80GB HBM2e for server, DGX, and appliances while Nvidia/Mellanox announce NDR 400G Infiniband.
Nvidia Doubles Down on AI Supercomputing was written by Nicole Hemsoth at The Next Platform.
The HPC world, particularly in the U.S. is waiting for the next series of transitions to far larger machines with exascale capabilities. …
What Put LLNL at the Center of U.S. Supercomputing in 2020? was written by Nicole Hemsoth at The Next Platform.
We have been waiting for years to see the first discrete Xe GPU from Intel that is aimed at the datacenter, and as it turns out, the first one is not the heavy compute engine we have been anticipating, but rather a souped up version of the Iris Xe LP and Iris Max Xe LP graphics cards that were launch at the end of October, which themselves are essentially the GPU extracted from the hybrid CPU-GPU “Tiger Lake” Core i9 processors for PC clients. …
Intel’s First Discrete Xe Server GPU Aimed At Hyperscalers was written by Timothy Prickett Morgan at The Next Platform.
Although hardware gets all the attention during Supercomputing week, much has been happening behind the scenes to make all the software run on the latest, fastest systems. …
Spack Packs Deployment Boost for Top Supercomputers was written by Nicole Hemsoth at The Next Platform.
Researchers at South Korea’s Electronics and Telecommunications Institute (ETRI), in conjunction with Arm, are one step closer to designing and deploying a native CPU that can handle double-precision supercomputing applications and low-precision, low-power AI inference. …
South Korea Funds First Supercomputing CPU Designed for AI, HPC was written by Nicole Hemsoth at The Next Platform.
We have written much over the last four or five years about the role FPGAs might play in the ever-expanding deep learning space, both in training and inference. …
HBM2, Tensor Units Key to Intel’s New AI Centric FPGA was written by Nicole Hemsoth at The Next Platform.
We have nothing against disk drives. Seriously. And in fact, we are amazed at the amount of innovation that continues to go into the last electromechanical device still in use in computing, which from a commercial standpoint started out with the tabulating machines created by Herman Hollerith in 1884 and used to process the 1890 census in the United States, thus laying the foundation of International Machines Machines. …
176 Steps Closer To The Mythical All-Flash Datacenter was written by Timothy Prickett Morgan at The Next Platform.
“GPUs and machine learning are essential to our survival,” says ECMWF lead.
Winds of Change Finally Hitting Large Weather Supercomputers was written by Nicole Hemsoth at The Next Platform.
HPC architects have continued to push the bounds of what is possible with computing, but the underlying architecture they have used has been fairly consistent – bare metal servers, which get bigger and faster over time. …
You Want HPC And You Want Virtualization? Let’s Talk About It was written by David Gordon at The Next Platform.
For more than a decade, as they have watched the amount of data they are generating stack up and technologies like artificial intelligence and analytics come to the forefront, enterprises have turned an eye toward high performance computing equipment and tools to help them get a handle on all of it. …
Making HPC And AI More Accessible To Enterprises was written by Jeffrey Burt at The Next Platform.
If you want to get a sense of what is happening in the high-end of the Ethernet switch and routing market, it is Arista Networks, formerly an upstart and now just one of the bigger vendors taking on the hegemony of Cisco Systems in networking in the datacenter and now on the campus and at the edge, is probably the best bellwether there is. …
Switching Back Into A Higher Gear was written by Timothy Prickett Morgan at The Next Platform.
Not every HPC or analytics workload – meaning an algorithmic solver and the data that it chews on – fits nicely in a 128 GB or 256 GB or even a 512 GB memory space, and sometimes the dataset is quite large and runs best with a larger memory space rather than carving it up into smaller pieces and distributing across nodes with the same amount of raw compute. …
Sometimes HPC Means Big Memory, Not Big Compute was written by Timothy Prickett Morgan at The Next Platform.
If you think HPC architectures have changed rapidly in recent years, brace yourself for the future when things will be moving at light speed. …
Ayar Labs Brings National Lab Architects And Industry Leaders Together To Talk Disaggregation was written by Elyse Silverberg at The Next Platform.
These days, whenever a research firm or industry leader outlines its vision for the future of enterprise technology, edge computing is almost always one of the central trends. …
On The Edge With NVM-Express And Object Storage was written by Gary Ogasawara at The Next Platform.
Is the inclusion of specialized matrix engines in general-purpose processors truly motivated and merited, or is the silicon better invested in other parts?
What’s Really Motivating the Matrix Engine Movement in HPC? was written by Nicole Hemsoth at The Next Platform.
When it comes to data-intensive supercomputing, few centers have the challenges Pawsey Supercomputing Centre faces. …
Pawsey Finds I/O Sweet Spots for Data-Intensive Supercomputing was written by Nicole Hemsoth at The Next Platform.
If hardware doesn’t scale well, either up into a more capacious shared memory system or out across a network of modestly powered nodes, there isn’t much you can do about it. …
Where Latency Is Key And Throughput Is Of Value was written by Timothy Prickett Morgan at The Next Platform.
Standing out in the crowded server inference space is getting more difficult, especially at this late stage of the startup game. …
Server Inference Chip Startup Untethered from AI Data Movement was written by Nicole Hemsoth at The Next Platform.
As an engineering director leading research projects into the application of machine learning (ML) and deep learning (DL) to computational software for electronic design automation (EDA), I believe I have a unique perspective on the future of the electronic and electronic design industries. …
Machine Learning for Future System Designs was written by Elias Fallon at The Next Platform.