Cray Adds GPU Powerhouse to CS Supercomputer Lot

By Nicole Hemsoth

August 26, 2014

The CS family of Cray systems was graced with a new addition today with the arrival of a dense, memory-loaded GPU offering that adds big acceleration to select HPC workloads.

The new CS-Storm, which offers up to 8 NVIDIA K40s per 2U server and a peak performance of 11 teraflops per Ivy Bridge-outfitted node, is set to push key applications that require more GPU scalability to new heights.

The system, which is based on the Cray CS300 super, is designed to keep the accelerators cool enough to operate at full speed. The 48U standard rack can accommodate 22 of the 2U nodes, which means that with 2 Ivy Bridges and the GPUs, users are looking at around 250 teraflops per rack or a petaflop of performance for a 4-cabinet purchase. Cray’s Barry Bolding told us that the company will release more information on future Intel generations for the host processor.

It’s not just about adding GPUs into the dense mix with this system, however. Cray has tuned the GPU workloads they’re targeting for maximum bandwidth and accelerator performance on the cooling and data movement fronts with a couple of notable features.

While these are air-cooled systems, as the graphic below shows, the emphasis is on cooling through front to back airflow to keep the GPUs humming without overheating or without having to run them at reduced wattage. In addition to airflow, this allows for expandability options since it will be possible to add future generations of accelerators into the box while still allowing the desired density and the ability to cool all 8 of the GPUs at the same time.

crayconfig

 

As you can see, these are also outfitted with more memory than the CS systems and features bandwidth-maximizing for these applications via the centered mothered with 2 CPUs and 4 GPUs on either side of the 2U configuration. Again, this aids in cooling and expandability but also note how they are running the PCI off each side of both sockets, which means they can run these through a PCI switch and split the PCI Gen 3s into 8s to run them at full bandwidth. While this isn’t a novel design necessarily, for the purposes of a system like this, it’s required.

csarch

“We’ve seen a number of customer requirements in the energy, high frequency trading, and government sectors as well as for a number of different use cases,” said Bolding. He pointed to other areas that are feeding demand for high-density GPU systems, including machine learning, seismic processing, and image processing.

Although pressed for a sense of pricing on the new CS-Storm supercomputer system, Bolding merely said that these are in early manufacturing and production and will be available for limited shipping immediately with volume shipping in Q4 of this year. He said that when compared to their CS system line in general, the GPUs will add to the cost of any configuration—meaning these are likely about the same cost of the air-cooled CS line, with the addition of the GPUs since aside from this addition and some of the software additions (OpenACC support and other GPU-based features) there isn’t a lot of custom engineering cooked in.

On that note, Cray is using essentially the same software environment one would expect with a CS300, but there are libraries that are GPU accelerated with adapted runtimes that will allow for GPU acceleration. While it’s not shown, as one would expect, they are carrying compilers that are OpenACC optimized and also supporting the expected Intel and NVIDIA software required for running accelerated workloads.

When Cray sets about designing a new product for a larger set of users, the company evaluates demand potential based on customer conversations and market data. Bolding says this is not a one-customer or custom designed product and that GPUs are a mature offering that is pushing customers to look to larger, more powerful accelerated systems now that they’ve had success with adding GPU nodes and tuning their applications.

“The CS family is a market-driven one, but it’s flexible, which means we can quickly design new form factor boards and server units. What we’ve seen is a growing demand for 8 GPUs and internally, we ran a business case on how big we think that market is see if it justified the development of a new offering,” said Bolding.

“This one was relatively new as a design,” he continued, “it was not in our portfolio before but we thought we could combine the hardware and software better than the competition.”

“Adding a GPU-dense, air-cooled option to the already-extensive lineup of Cray’s CS300 offerings will further expand the market for this standards-based cluster supercomputer product,” said Steve Conway, IDC research vice president for high performance computing. “IDC research showed that the proportion of sites employing accelerators and other coprocessors in their HPC systems jumped from 28.2 percent in 2011 to 76.9 percent in 2013, and GPUs are the clear leaders in this category. Cray has been on a roll, and ramped-up sales of its Cray CS300 line have helped.”

 

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension around the potential changes that could affect or disrupt Lustre Read more…

By Carlos Aoki Thomaz

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and received a patent for a "processor design, which allows rep Read more…

By Tiffany Trader

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitive computing, memory-centric computing, high-speed communicat Read more…

By John Russell

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

US Seeks to Automate Video Analysis

January 16, 2018

U.S. military and intelligence agencies continue to look for new ways to use artificial intelligence to sift through huge amounts of video imagery in hopes of freeing analysts to identify threats and otherwise put their Read more…

By George Leopold

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension aroun Read more…

By Carlos Aoki Thomaz

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitiv Read more…

By John Russell

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

The @hpcnotes Predictions for HPC in 2018

January 4, 2018

I’m not averse to making predictions about the world of High Performance Computing (and Supercomputing, Cloud, etc.) in person at conferences, meetings, causa Read more…

By Andrew Jones

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Nvidia, Partners Announce Several V100 Servers

September 27, 2017

Here come the Volta 100-based servers. Nvidia today announced an impressive line-up of servers from major partners – Dell EMC, Hewlett Packard Enterprise, IBM Read more…

By John Russell

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

  • arrow
  • Click Here for More Headlines
  • arrow
Share This