With AMX, Intel Adds AI/ML Sparkle to Sapphire Rapids
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| 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| 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| The Next Platform
Arm is hosting its annual Tech Day shindig, virtually (again) thanks to the coronavirus pandemic, and is providing a lot more insight into the future| The Next Platform
Many of us have been wracking our brains why Nvidia would spend a fortune – a whopping $40 billion – to acquire Arm Holdings, a chip architecture| The Next Platform
The “Milan” Epyc 7003 processors, the third generation of AMD’s revitalized server CPUs, is now in the field, and we await the entry of the “Ice Lake”| The Next Platform
There isn’t really a systems business so much as a collection of them, all unique and all facing their own particular challenges. Among all of the current| The Next Platform
When you have 54.2 billion transistors to play with, you can pack a lot of different functionality into a computing device, and this is precisely what| The Next Platform
Big Blue has become a big believer in using differential signaling to attach everything – and we mean everything – to the processor. There is an upcoming| The Next Platform
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| The Next Platform
The lines between the CPU, its main memory, the memory of accelerators, and various external storage class memories have been blurring for years, and the| The Next Platform
When IBM started to use the word "open" in conjunction with its Power architecture more than three years with the formation of the OpenPower Foundation| The Next Platform
When it comes to energy-efficient supercomputing, sometimes less is more. That was illustrated this week by Fujitsu with its A64FX prototype, which| The Next Platform
The days when the X86 processor could do just about every kind of processing in the datacenter are gone. It’s hard to believe it is true, but one need| The Next Platform
When you are always looking for what platform architecture will be mainstream, you have to look at what those on the bleeding edge are doing to see what| The Next Platform
One reason China has a good chance of hitting its ambitious goal to reach exascale computing in 2020 is that the government is funding three separate| The Next Platform
As expected, Intel will be the prime contractor for the first exascale supercomputer in the United States, which Argonne National Laboratory expects to be| The Next Platform
It would not have been an Architecture Day, as it was earlier this week at the former estate of Intel co-founder Robert Noyce, if the chip giant did not| The Next Platform
With Moore’s Law running out of steam, the chip design wizards at Intel are going off the board to tackle the exascale challenge, and have dreamed up a| The Next Platform
When it comes to systems, the first thing that most people think of is compute. But if HPC is teaching us anything about system design – and one that is| The Next Platform
In the story we broke this morning about the forthcoming “Aurora” supercomputer set to be installed at Argonne National Laboratory—one of three| The Next Platform
It has been clear for some time that Japan wants to have a certain amount of economic and technical independence when it comes to cloud computing in the| The Next Platform
It’s fall, so that means it is the annual Super Computing conference that has been held in the United States by the Association for Computing Machinery| 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. And it| The Next Platform
If you thought it took a lot of compute and storage to build Facebook’s social network, you ain’t seen nothing yet. The immersive and AI-enhanced| The Next Platform
Within a year or so, with the launch of the “Grace” Arm server CPUs, it will not be heresy for anyone at Nvidia to believe, or to say out loud, that not| The Next Platform
D-Wave executives stirred up some controversy earlier this year when they claimed a smaller version of its Advantage 2 annealing quantum system, armed| The Next Platform
Making a graphics card for gamers is one thing, but manufacturing a rackscale supercomputer with over 600,000 components that burns 120 kilowatts of| The Next Platform
Each time that the United States has figured out that it needed to do export controls on massively parallel compute engines to try to discourage China| The Next Platform
Arm chip designers who make processors for mobile devices, such as Apple, Samsung, and Qualcomm, that do not have pre-existing server businesses have been| The Next Platform
Businesses have always relied on data, but they never were able to get full value out of them when they were siloed by structure, system, or storage.| The Next Platform
Normally, when we look at a system, we think from the compute engines at a very fine detail and then work our way out across the intricacies of the nodes| The Next Platform
Big Blue was one of the system designers that caught the accelerator bug early and declared rather emphatically that, over the long haul, all kinds of| 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| The Next Platform
It must have been something in the cosmic ether. Apopros of nothing except the need to fill a blank page with something interesting back when we were| The Next Platform
The changes to the Xeon server chip architecture and the consequent server platforms are going to be a bit thin here in 2018 after a pretty big jump with| The Next Platform
To a certain extent, the “Knights” family of parallel processors, sold under the brand name Xeon Phi, by Intel were exactly what they were supposed to be:| The Next Platform
We are not shy of playing guessing games here at The Next Platform, as you all well know. And Intel and Cray have left us with a few big ones with regard| The Next Platform
Last fall, supercomputer maker Cray announced that it was getting back to making high performance cluster interconnects after a six year hiatus, but the| The Next Platform
The potent combination of powerful CPUs, floating point laden GPU accelerators, and fast InfiniBand networking are coming to market and reshaping the| The Next Platform
If there is one bright spot in the Xeon SP server chip line from Intel, it is the version of the “Sapphire Rapids” Xeon SP processor that has HBM memory| The Next Platform
There are a lot of things that compute engine makers have to do if they want to compete in the datacenter, but perhaps the most important thing is to be| The Next Platform
China has lots of coal but it does not have a lot of GPUs or other kinds of tensor and vector math accelerators appropriate for HPC and AI. And so as it| The Next Platform
High tech companies always have roadmaps. Whether or not they show them to the public, they are always showing them to key investors if they are in their| The Next Platform
Big Blue might be a little late to the AI acceleration game, but it has a captive audience in its System z mainframe and Power Systems servers. Many of| The Next Platform
Making money from sand is not as easy as making money from oil, and the Emirate of Abu Dhabi, which has been assembling the GlobalFoundries chip making| The Next Platform
As we have seen with various kinds of high bandwidth, stacked DRAM memory to compute engines in the past decade, just adding this wide, fast, and| The Next Platform
There are a lot of new technologies that are available now or are going to be available shortly that have the potential to radically change the compute,| The Next Platform
As the steward of the nuclear weapon arsenal for the United States government, it is probably not an overstatement to say that Lawrence Livermore National| The Next Platform
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| The Next Platform
Whenever one company buys another, every product line, every research project, and every employee is ultimately in play. But when Hewlett Packard| The Next Platform
While processors and now GPUs tend to get all of the glory when it comes to high performance computing, for the past three decades as distributed| The Next Platform
There is nothing quite like great hardware to motivate people to create and tune software to take full advantage of it during a boom time. And as we have| The Next Platform
The most exciting thing about the Top500 rankings of supercomputers that come out each June and November is not who is on the top of the list. That’s fun| The Next Platform
We like datacenter compute engines here at The Next Platform, but as the name implies, what we really like are platforms – how compute, storage,| The Next Platform
If you want to take on Nvidia on its home turf of AI processing, then you had better bring more than your A game. You better bring your A++ game, several| The Next Platform
If you want to buy an exascale-class supercomputer, or a portion of one so you can scale up, there are not a lot of places to go shopping because there| The Next Platform
Every couple of years, Lawrence Livermore National Laboratory gets to install the world’s fastest supercomputer. And thankfully the HPC center usually| The Next Platform
There has been a lot more churn on the November Top500 supercomputer rankings that is the talk of the SC24 conference in Atlanta this week than there was| The Next Platform
It has become a well known fact these days that the switches that are used to interconnect distributed systems are not the most expensive part of that| The Next Platform
It would be hard to find something that is growing faster than the Nvidia datacenter business, but there is one contender: OpenAI. Open AI is, of course,| The Next Platform
Subscribe * indicates required Email Address *First Name Last Name Country United StatesUnited KingdomCanadaAfghanistanÅland IslandsAlbaniaAlgeriaAmerican| The Next Platform
Since the advent of distributed computing, there has been a tension between the tight coherency of memory and its compute within a node – the base level| The Next Platform
For very sound technical and economic reasons, processors of all kinds have been overprovisioned on compute and underprovisioned on memory bandwidth – and| The Next Platform
We have five decades of very fine-grained analysis of CPU compute engines in the datacenter, and changes come at a steady but glacial pace when it comes| The Next Platform
The datacenter industry today looks very different than it did a decade ago. A number of factors have emerged over the past few years: most recently, the| The Next Platform
