Penguin Compute Gets Smart About Capital Needs In HPC

As history reveals, building a thriving systems business in HPC is no simple task. …

Penguin Compute Gets Smart About Capital Needs In HPC was written by Timothy Prickett Morgan at .

Arista Runs Barefoot With Tofino Programmable Switch Chips

If Andy Bechtolsheim, the chief technology officer at datacenter switching upstart Arista Networks, wanted to design ASICs to try to take a bigger piece of the switch pie – or more precisely, thought that this was a good idea at all – rest assured, Arista would be spending money engineering its own chips and fighting for capacity at the four remaining foundries that have advanced processes. …

Arista Runs Barefoot With Tofino Programmable Switch Chips was written by Timothy Prickett Morgan at .

The Old Switcheroo

The cost of servers keeps going up and up, thanks in large part to memory, flash, and GPU prices rising as too much demand chases too little supply and also due in part to the rising cost of processors. …

The Old Switcheroo was written by Timothy Prickett Morgan at .

AMD Coils For 7 Nanometer Leap Over Intel And Nvidia

With Intel having significant difficulties in ramping up its 10 nanometer manufacturing processes and not really talking much about its plans for 7 nanometers, there has never been a better time for its few remaining rivals in chip manufacturing to give their respective CPU and GPU customers and edge to carve out some market share in the datacenter and on the desktop, which helps cover the cost of being in the datacenter because it helps ramp advanced processes. …

AMD Coils For 7 Nanometer Leap Over Intel And Nvidia was written by Timothy Prickett Morgan at .

Cisco Gets Modular With Servers In Epyc Fashion

Believe it or not, Cisco Systems has a bunch of customers for its UCS blade and rack servers that are in the gaming industry, which has its share of near-hyperscale players who have widely geographically distributed clusters spread around the globe so players can get very low latency access over the Internet to games running on that infrastructure. …

Cisco Gets Modular With Servers In Epyc Fashion was written by Timothy Prickett Morgan at .

The Server Boom Town Is Built On High Component Prices

On the face of it, if you just look at the top level numbers, the server market is booming like we have not seen since the recovery in the wake of the Great Recession for a few quarters here and there between late 2009 and early 2011. …

The Server Boom Town Is Built On High Component Prices was written by Timothy Prickett Morgan at .

Nvidia Takes More Control Of Its GPU Compute Platform

Nvidia got a little taste of hardware, and the company’s top brass have decided that they like having a lot of iron in their financial diet. …

Nvidia Takes More Control Of Its GPU Compute Platform was written by Timothy Prickett Morgan at .

We Fight, Get Beat, Rise, And Fight Again

Hewlett Packard built up its conglomerate in the 2000s in good faith, trying to be a larger and more profitable supplier of IT products and services. …

We Fight, Get Beat, Rise, And Fight Again was written by Timothy Prickett Morgan at .

A Peek Inside That Intel Xeon-FPGA Hybrid Chip

Last week at the Fujitsu Forum in Tokyo, Lisa Spelman, who is general manager of Xeon products and Data Center Marketing at Intel, did a soft announcement of the hybrid Xeon CPU-Arria 10 FPGA hybrid chip that the company has been talking about for years and that is now available to selected customers. …

A Peek Inside That Intel Xeon-FPGA Hybrid Chip was written by Timothy Prickett Morgan at .

Weather Forecasting Gets A Big Lift In Japan

It has been a long time since the Japan Meteorological Agency has deployed the kind of supercomputing oomph for weather forecasting that the island nation would seem to need to improve its forecasts. But JMA, like its peers in the United States, Europe, and India, is investing heavily in new supercomputers to get caught up, and specifically, has just done a deal with Cray to get a pair of XC50 systems that will have 18.2 petaflops of aggregate performance.

This is a lot more compute capacity than JMA has had available to do generic weather forecasting as well as do …

Weather Forecasting Gets A Big Lift In Japan was written by Timothy Prickett Morgan at The Next Platform.

It’s Called Distributed Computing, Even When It Shouldn’t Be

Success can be its own kind of punishment in this world.

Since the dawn of modern computing 130 years ago with tabulating machines derived from looms, there have always been issues of scale when it comes to compute and storage. While all modern businesses worry about the IT infrastructure and how dependent they are on it, there are special classes of systems that are at organizations that have intense computing and storage demands, and usually also severe networking requirements, and they of necessity push the boundaries of what can be done simply because things need to be done.

They have …

It’s Called Distributed Computing, Even When It Shouldn’t Be was written by Timothy Prickett Morgan at The Next Platform.

A Hard Rain’s A-Gonna Fall In Public Cloud

Way back in the early days of the commercial Internet, when we all logged into what seemed to be new but what was actually a quite old service used by academic institutions and government agencies that rode on the backbones of the telecommunications network, there were many, many thousands of Internet service providers who provided the interface between our computers and the network capacity that was the onramp of the information superhighway.

Most of these ISPs are gone today, and have been replaced by a few major telco, cable, and wireless network operators who provide us with our Internet service. …

A Hard Rain’s A-Gonna Fall In Public Cloud was written by Timothy Prickett Morgan at The Next Platform.

Getting Logical About Cavium ThunderX2 Versus Intel Skylake

Any processor that hopes to displace the Xeon as the engine of choice for general purpose compute has to do one of two things, and we would argue both: It has to be a relatively seamless replacement for a Xeon processor inside of existing systems, much as the Opteron was back in the early 2000s, and it has to offer compelling advantages that yield better performance per dollar per watt per unit of space in a rack.

The “Vulcan” ThunderX2 chips, at least based on the initial information that is available in the wake of their launch, appear to do …

Getting Logical About Cavium ThunderX2 Versus Intel Skylake was written by Timothy Prickett Morgan at The Next Platform.

CoreOS Is New Linux, Not A RHEL Classic Killer

One of the most important lessons in marketing is that you don’t change something that is working, but that you also have to be able to carefully and cautiously innovate to protect against changing tastes or practices that might also spell doom for the business.

Two and a half decades ago, Coca-Cola famously made a mistake in trying to push New Coke, a different formula that was sweeter and more like Pepsi, replacing the original Coke, which had to be brought back as Coke Classic and which, eventually, killed off New Coke completely. Coca-Cola was not just changing things for …

CoreOS Is New Linux, Not A RHEL Classic Killer was written by Timothy Prickett Morgan at The Next Platform.

Chewing A Billion By Billion Matrix Crammed Into Gigabytes Of Memory

Sometimes, to appreciate a new technology or technique, we have to get into the weeds a bit. As such, this article is somewhat more technical than usual. But the key message that new libraries called ExaFMM and HiCMA gives researchers the ability to operate on billion by billion matrices using machines containing only gigabytes of memory, which gives scientists a rather extraordinary new ability to run on really big data problems.

King Abdullah University of Science and Technology (KAUST) has been enhancing the ecosystem of numerical tools for multi-core and many-core processors. The effort, which is a collaboration between KAUST, …

Chewing A Billion By Billion Matrix Crammed Into Gigabytes Of Memory was written by Timothy Prickett Morgan at The Next Platform.

Nvidia Hitting On All GPU Cylinders

Even if Nvidia had not pursued a GPU compute strategy in the datacenter a decade and a half ago, the company would have turned in one of the best periods in its history as the first quarter of fiscal 2019 came to a close on April 29.

As it turns out, though, the company has a fast-growing HPC, AI, and cryptocurrency compute business that runs alongside of its core gaming GPU, visualization, and professional graphics businesses, and Nvidia is booming. That is a six cylinder engine of commerce, unless you break AI into training and inference (which is sensible), and …

Nvidia Hitting On All GPU Cylinders was written by Timothy Prickett Morgan at The Next Platform.

Tearing Apart Google’s TPU 3.0 AI Coprocessor

Google did its best to impress this week at its annual IO conference. While Google rolled out a bunch of benchmarks that were run on its current Cloud TPU instances, based on TPUv2 chips, the company divulged a few skimpy details about its next generation TPU chip and its systems architecture. The company changed from version notation (TPUv2) to revision notation (TPU 3.0) with the update, but ironically the detail we have assembled shows that the step from TPUv2 to what we will call TPUv3 probably isn’t that big; it should probably be called TPU v2r5 or something like that. …

Tearing Apart Google’s TPU 3.0 AI Coprocessor was written by Timothy Prickett Morgan at The Next Platform.

What Qualcomm’s Exit From Arm Server Chips Means

Broadcom may not have wanted to be in the Arm server chip business any more, but its machinations since it was acquired by Avago Technology two years ago have certainly sent ripples through that nascent market. It did it in the wake of buying Broadcom, and now it looks like it is doing it again with Qualcomm.

Before it shelled out a stunning $37 billion to buy Broadcom, best known for its datacenter switch ASICs but also an Arm server chip wannabe at the time, Avago was a conglomerate that made chips for optical networking, server networking, and storage controllers …

What Qualcomm’s Exit From Arm Server Chips Means was written by Timothy Prickett Morgan at The Next Platform.

IBM Rounds Out Power9 Systems For HPC, Analytics

Back in the early 1990s, when IBM has having its near-death experience as the mainframe business faltered, Unix systems were making huge inroads into the datacenter, and client/server computing was pulling work off central systems and onto PCs, the company was on the ropes and probably close to bankruptcy. At the time, the Wall Street Journal ran a central A1 column story, where a bunch of CIOs who were unhappy with Big Blue were brutally honest about how they felt.

One of them – and we have never been able to forget this quote – who had moved to other …

IBM Rounds Out Power9 Systems For HPC, Analytics was written by Timothy Prickett Morgan at The Next Platform.

The Pantheon Of Services In Nutanix Acropolis

While there is a battle of sorts going on between hyperconverged architectures and disaggregated ones, it is probably safe to assume that at the scale that most enterprises run, they could care less about which one they choose so long as either architecture does what they need to support applications. Enterprises will find some use for both hyperconverged platforms that merge virtual compute and virtual storage for many years to come, but we would also bet that over the long haul, compute and storage will be disaggregated and connected by fast and vast networks because, frankly, that is how Google …

The Pantheon Of Services In Nutanix Acropolis was written by Timothy Prickett Morgan at The Next Platform.