A number of chip companies — importantly Intel and IBM, but also the Arm collective and AMD — have come out recently with new CPU designs that feature native Artificial Intelligence (AI) and its related machine learning (ML). …
Doing The Math On CPU-Native AI Inference was written by Mark Funk at The Next Platform.
Five years ago, Western Digital, known for its hard disk drive (HDD) storage technologies, doled out $19 billion in cash and stock for SanDisk and its solid state drive (SDD) product portfolio, giving it deep expertise in the non-volatile flash memory space at a time when enterprises were looking for expanded storage options in the wake of the rise of the cloud and the edge. …
Hybrid Disk/Flash Storage Isn’t New, But It Is Getting Better was written by Jeffrey Burt at The Next Platform.
Perhaps the National Security Agency (NSA) in the U.S. is over procuring and maintaining some of its on-prem supercomputers. …
NSA Makes Another Cloud Jump with $2 Billion HPE Deal was written by Nicole Hemsoth at The Next Platform.
UPDATE: One of the reasons why Intel spent $16.7 billion to acquire FPGA maker Altera six years ago was because it was convinced that its onload model — where big parts of the storage and networking stack were running on CPUs — was going to go out of favor and that companies would want to offload this work to network interface cards with lots of their own much cheaper and much more energy efficient processing. …
Intel’s Best DPU Will Be Commercially Available — Someday was written by Timothy Prickett Morgan at The Next Platform.
Expect to hear increasing buzz around graph neural network use cases among hyperscalers in the coming year. …
The Graph Neural Network Behind Your ETA was written by Nicole Hemsoth at The Next Platform.
Many of the largest retailers and social networks are seeing a narrowing path for scaling of AI training capabilities. …
Amazon AI Weighs Optimization Options for GNNs was written by Nicole Hemsoth at The Next Platform.
Artificial intelligence is taking center stage in the IT industry, fueled by the massive growth in the data being generated and the increasing need in HPC and mainstream enterprises for capabilities ranging from analytics and automation. …
DOE AI Expert Says New HPC Architecture Is Needed was written by Jeffrey Burt at The Next Platform.
It is not news that China wants a rich, native, diverse semiconductor ecosystem to feed its largest consumers of compute. …
The AI Training Chip Tencent Has an Eye On was written by Nicole Hemsoth at The Next Platform.
When money is really no object and the budget negotiations involve taking a small slice of your personal net worth of $7.5 billion out of one pocket and putting it into another, and you have the technical chops to understand the complexities of molecular dynamics and have a personal mission to cure disease, then you can build any damned supercomputer you want. …
The Huge Payoff Of Extreme Co-Design In Molecular Dynamics was written by Timothy Prickett Morgan at The Next Platform.
Facebook has to keep digging into ever-lower levels of its architecture to efficiently make use of endlessly growing training data. …
ML Training Growing Pains at Facebook was written by Nicole Hemsoth at The Next Platform.
If not for delays, the long-awaited Aurora supercomputer at Argonne National Lab would likely just be coming online. …
Argonne Deploying GPU-Dense Testbed Supercomputer was written by Nicole Hemsoth at The Next Platform.
It is pretty obvious to everyone who watches the IT market that Intel needs an architectural win that leads to a product win in datacenter compute. …
Intel’s “Ponte Vecchio” GPU Better Not Be A Bridge Too Far was written by Timothy Prickett Morgan at The Next Platform.
What is that famous maxim in computer science about something that doubles on a regular cadence? …
Cerebras Shifts Architecture to Meet Massive AI/ML Models was written by Nicole Hemsoth at The Next Platform.
Everyone knows that machine learning inference is going to be a big deal for commercial applications in the years ahead, but no one is precisely sure how much inference is going to be needed. …
IBM Bets Big On Native Inference With Big Iron was written by Timothy Prickett Morgan at The Next Platform.
While it might not happen anytime soon, traditional supercomputing could be in for a sea change with wider acceptance of lower-precision calculations. …
More Proof Points for Low Precision HPC was written by Nicole Hemsoth at The Next Platform.
When the top brass at Intel say that the “Sapphire Rapids” Xeon SP CPUs and “Ponte Vecchio” Xe HPC GPUs that are coming out early next year represent the “largest architectural shift in over a decade,” they ain’t kidding. …
Intel Finally Gets Chiplet Religion With Server Chips was written by Timothy Prickett Morgan at The Next Platform.
All processor designs are the result of a delicate balancing act, perhaps most touchy in the case of a high performance CPU that needs to be all things to users, whether they’re running large HPC simulations, handling transaction processing, dispatching training runs or whipping out inference results. …
With AMX, Intel Adds AI/ML Sparkle to Sapphire Rapids was written by Nicole Hemsoth at The Next Platform.
Graph processing at hyperscale has historically been a challenge because of the sheer complexity of algorithms and graph workflows. …
How Alibaba Architects Around Massive Graph Complexity was written by Nicole Hemsoth at The Next Platform.
It is hard to imagine how anyone could run Nvidia better than it is being run right now. …
Maybe Nvidia Should Buy VMware Instead Of Intel? was written by Timothy Prickett Morgan at The Next Platform.
For much the three decades that Rambus has existed, it has largely focused on its patent portfolio and licensing its designs of memory interface technologies for a broad array of computer products. …
Rambus Gets On The CXL Gravy Train was written by Jeffrey Burt at The Next Platform.