OpenACC: Things Are Getting Simpler More Quickly

OpenACC is one of the prongs in a multi-prong strategy to get people to port the parallel portions of HPC applications to accelerators. …

OpenACC: Things Are Getting Simpler More Quickly was written by Timothy Prickett Morgan at .

The Widening Gyre Of Supercomputing

The twice-annual ranking of distributed computing systems based on the Linpack parallel Fortran benchmark, a widely used and sometimes maligned test, is as much a history lesson as it is an expectation always looking forward, with anticipation, to the next performance milestones in high performance computing. …

The Widening Gyre Of Supercomputing was written by Timothy Prickett Morgan at .

Competition Finally Comes To Datacenter GPU Compute

AMD’s “Rome” processors, the second generation of Epyc processors that the company will be putting into the field, are a key step for the company on its path back to the datacenter. …

Competition Finally Comes To Datacenter GPU Compute was written by Timothy Prickett Morgan at .

AMD’s Long Road From Naples To Milan Centers On Rome

AMD president and chief executive officer Lisa Su is fond of saying that the road to Rome goes through Naples as a way of reminding everyone that they can’t sit on the sidelines and wait for the second generation “Rome” Epyc processors to come to market in 2019. …

AMD’s Long Road From Naples To Milan Centers On Rome was written by Timothy Prickett Morgan at .

Intel To Challenge AMD With 48 Core “Cascade Lake” Xeon AP

AMD is hosting its “Next Horizon” datacenter event in San Francisco this week, and archrival Intel, which is losing some market share to AMD but not feeling the pain on its books yet thanks to a massive buildout in server infrastructure at hyperscalers, cloud builders, and smaller service providers like telcos, is hitting back by divulging some of its plans for next year’s “Cascade Lake” Xeon lineup. …

Intel To Challenge AMD With 48 Core “Cascade Lake” Xeon AP was written by Timothy Prickett Morgan at .

Compiling History To Understand The Future

If you want to understand where we are going with computer architectures and the compilers that drive them, it is instructive to look at how compilers have made the leap from architecture to architecture starting six decades ago. …

Compiling History To Understand The Future was written by Timothy Prickett Morgan at .

Datacenter 25G Ethernet Upgrade Wave Lifts Mellanox

Having multiple related but distinct product lines turns a company into an economic engine that runs a lot smoother than an it would run with a single cylinder. …

Datacenter 25G Ethernet Upgrade Wave Lifts Mellanox was written by Timothy Prickett Morgan at .

Delivering On The Promise Of Network Function Virtualization

People have been talking about software defined networking and its related network function virtualization for so long that it must appear to many organizations that everyone else is doing it. …

Delivering On The Promise Of Network Function Virtualization was written by Timothy Prickett Morgan at .

Cray Slingshots Back Into HPC Interconnects With Shasta Systems

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 computing architectures became the norm in supercomputing, it has been the interconnects that made all the difference in how well – or poorly – these systems perform. …

Cray Slingshots Back Into HPC Interconnects With Shasta Systems was written by Timothy Prickett Morgan at .

Berkeley Lab First In Line for Cray “Shasta” Supercomputers

For the past five years, supercomputer maker Cray has been diligently at work not only creating a new system architecture that allows for a mix of different interconnects and compute for its future “Shasta” systems, but has also brought long-time Cray chief technology officer, Steve Scott, back into the company after two stints spent at Nvidia and Google to create a new interconnect, called “Slingshot,” that is the beating heart of the Shasta system and that signals a return of the Cray that we know and love. …

Berkeley Lab First In Line for Cray “Shasta” Supercomputers was written by Timothy Prickett Morgan at .

Big Blue Dons A $34 Billion Red Hat

In one fell swoop that is going to cost Big Blue a whopping $34 billion, IBM is going to become a modern software powerhouse in the datacenter that has to be contended with in an entirely different way. …

Big Blue Dons A $34 Billion Red Hat was written by Timothy Prickett Morgan at .

Intel’s Data Center Group Rides A Wave Of Compute Demand

Sometimes, you just have to be amazed by a good stroke of luck in the IT sector. …

Intel’s Data Center Group Rides A Wave Of Compute Demand was written by Timothy Prickett Morgan at .

AMD Inches Up Server Share On The Way To Rome

IT shops are notorious when it comes to avoiding risk, and this is something that we should be grateful for because it increases the odds that this increasingly compute-dependent world keeps working. …

AMD Inches Up Server Share On The Way To Rome was written by Timothy Prickett Morgan at .

The 400G Ethernet Ramp About Radix As Much As Bandwidth

The appetite for network bandwidth is insatiable, as is that of compute and storage, but our enthusiasm to acquire larger and larger chunks of all of these things is curtailed significantly by cost. …

The 400G Ethernet Ramp About Radix As Much As Bandwidth was written by Timothy Prickett Morgan at .

Great Lakes Super To Remove Islands Of Compute

It is hard to say for sure, but there is probably as much aggregate computing capacity in the academic supercomputing centers of the world as there are in the big national labs. …

Great Lakes Super To Remove Islands Of Compute was written by Timothy Prickett Morgan at .

Deep Learning Is Coming Of Age

In the early days of artificial intelligence, Hans Moravec asserted what became known as Moravec’s paradox: “It is comparatively easy to make computers exhibit adult-level performance on intelligence tests or playing checkers, and difficult or impossible to give them the skills of a one-year-old when it comes to perception and mobility.”

This assertion is now unraveling primarily due to the ascent of deep learning. …

Deep Learning Is Coming Of Age was written by Timothy Prickett Morgan at .

Someone Has To Pay To Push The Bleeding Edge Of Systems

When you look at IBM, it is as if you are seeing many different instantiations of Big Blue across time playing out in the present, side by side. …

Someone Has To Pay To Push The Bleeding Edge Of Systems was written by Timothy Prickett Morgan at .

Hadoop And Spark Get A Vector Performance Boost

Ever since the “Aurora” vector processor designed by NEC was launched last year, we have been wondering if it might be used as a tool to accelerate workloads other than the traditional HPC simulation and modeling jobs that are based on crunching numbers in single and double precision floating point. …

Hadoop And Spark Get A Vector Performance Boost was written by Timothy Prickett Morgan at .

A New Datacenter Compels Arm To Create A New Chip Line

The gap between processor architectures in the datacenter server and on the desktop or on our laps or now in our hands thanks to transistor shrinks over the past decade is getting bigger. …

A New Datacenter Compels Arm To Create A New Chip Line was written by Timothy Prickett Morgan at .

Where The FPGA Hits The Server Road For Inference Acceleration

There are an increasing number of ways to do machine learning inference in the datacenter, but one of the increasingly popular means of running inference workloads is the combination of traditional CPUs acting as a host for FPGAs that run the bulk of the inferring. …

Where The FPGA Hits The Server Road For Inference Acceleration was written by Timothy Prickett Morgan at .