ScaleMP Brings AMD Opteron Support to Its Virtual SMP Portfolio

By Michael Feldman

September 20, 2011

After five years of shipping Intel Xeon-supported products for its virtual SMP platform, ScaleMP has added support for AMD’s Opteron CPU. Starting in this fall, customers will be able to aggregate as many as 128 servers encompassing up to 512 Opteron processors and 64 TB of memory into a single shared memory system. The decision to bring Opterons into the fold was driven by customer interest in the new Interlagos Bulldozer processor that started shipping this summer.

ScaleMP, has been enjoying fairly steady growth since 2006 when it first launched its vSMP Foundation product. vSMP is essentially a software replacement for SGI’s Altix UV SMP offering, but in this case using x86 commodity cluster hardware aggregated by ScaleMP software. As such vSMP can offer many of the advantages of its hardware competition, but at a fraction of the price.

In tests at Aachen University, ScaleMP aggregated servers (either Harpertown Xeons or Nehalem-EP Xeon with QDR InfiniBand) outperformed SGI Altix UV (Nehalem UV and NUMAline5 interconnect) configurations with 32, 64 and 128 threads. The application was an OpenMP-based shared memory application (in this case, an analysis of a 3D passive scalar field transported by a turbulent flow) written in Fortran.

According to ScaleMP CEO and founder Shai Fultheim, vSMP generally attracts two types of customers: those with typical MPI codes, but who don’t want to deal with the complexity of cluster management; and those who have shared memory applications, but are looking to migrate to less expensive, industry-standard hardware. In both cases, the users are being motivated to reduce total cost of ownership (TCO) either through less software complexity, in the first case, and through less expensive servers, in the second.

More recently, a third customer profile has emerged in which a single infrastructure is built to serve all applications. ScaleMP’s vSMP technology lets them do that as well, by allowing multiple virtual SMPs to be built up and torn down dyanmically across a datacenter. That type of flexibility is particularly important when a customer’s application set requires different sized systems — CPU count or memory size.

Up until now though, it all of the underlying compute hardware had to inhabited by on Intel Xeon chips. By bringing Opterons into the mix, vSMP can now access a broader hardware ecosystem. “We believe this is a game-changer,” Fultheim told HPCwire.

Support will extend to both the Magny-Cours (6100 Series) and new Interlagos (6200 Series) Opterons. But it was the latter chip that brought the customers running. According to Fultheim, starting at the end of 2010, he started getting inquiries about support for Interlagos. In particular a couple of “very significant customers” approached ScaleMP and AMD and basically told them if you build it, they will come. ScaleMP now has about 10 customers in the pipeline for the AMD product and expects more coming, thanks to some impressive attributes of the revamped Opteron.

Based on the new Bulldozer architecture, Interlagos should deliver very competitive performance. Coming in both 12-core and 16-core versions, the integer and floating point performance is expected to stack up quite well against the 8-core Sandy Bridge Xeon EP. A 16-core Interlagos can retire 64 floating operations per cycle, compared to 32 FP ops for an 8-core Sandy Bridge. Note that while the 8-core Xeon can also hit 64 FP operations with the new AVX floating point instructions, not all applications will be able to take advantage of AVX — at least not right away.

Memory bandwidth performance should be competitive on Opteron-equipped virtual SMPs as well. Early ScaleMP tests with vSMP on Magny-Cours-based servers with the Triad benchmark (measuring memory bandwidth) yielded decent results. On a two-socket server, for example, the Triad run delivered nearly 52K MB/sec — about the same as what is expected from the upcoming Sandy Bridge Xeons. On a 12-socket Magny-Cours SMP, that scaled to nearly 280K MB/sec. It is likely that Interlagos-based machines will deliver even greater bandwidth.

While no one expects the new Opterons to overwhelm Intel’s upcoming server chips, Interlagos may be able to carve out enough of a market to make it worthwhile for ScaleMP. The fact that the company finally pulled the Operton trigger after five years of Intel-only support may portend happier days for AMD’s new server CPUs.

Even without an AMD offering, ScaleMP seems to been doing quite well. They now have over 300 customers spread across 23 countries. According to Fultheim, they expect more than double revenue in this latest quarter, compared to recent quarters. While their biggest vertical (39 percent of revenue) is in higher ed/research, they also have respectable footprint in manufacturing (19 percent), and government (11 percent)

They’ve accomplished all this by hooking up with system vendors like IBM, HP, Dell, Supermicro, and Dell, among others, who offer vSMP-certified x86 servers. Last week, they added Fujitsu to the club, who certified a couple of its PRIMERGY servers for the vSMP technology. “We will continue to grow the list,” says Fultheim.

They’re also looking at adding additional microprocessor support for vSMP, although Fultheim would not say what was under consideration. Since the technology is processor-agnostic, ScaleMP just needs a viable business case to justify additional ports. Given that, it wouldn’t be too much of a stretch to see future virtual SMP machines based on IBM’s Power7 chip, Intel’s Atom CPU, ae ARM server CPU, or perhaps even the Chinese-made Godson processor.

A limited release of vSMP Foundation that supports the 6100 and 6200 Opterons will be available on October 1. General availability is slated for November 21. No pricing was announced.

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!

Doug Kothe on the Race to Build Exascale Applications

May 29, 2017

Ensuring there are applications ready to churn out useful science when the first U.S. exascale computers arrive in the 2021-2023 timeframe is Doug Kothe’s job Read more…

By John Russell

PRACEdays Reflects Europe’s HPC Commitment

May 25, 2017

More than 250 attendees and participants came together for PRACEdays17 in Barcelona last week, part of the European HPC Summit Week 2017, held May 15-19 at t Read more…

By Tiffany Trader

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurr Read more…

By Doug Black

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

HPE Extreme Performance Solutions

Exploring the Three Models of Remote Visualization

The explosion of data and advancement of digital technologies are dramatically changing the way many companies do business. With the help of high performance computing (HPC) solutions and data analytics platforms, manufacturers are developing products faster, healthcare providers are improving patient care, and energy companies are improving planning, exploration, and production. Read more…

Nvidia CEO Predicts AI ‘Cambrian Explosion’

May 25, 2017

The processing power and cloud access to developer tools used to train machine-learning models are making artificial intelligence ubiquitous across computing pl Read more…

By George Leopold

PGAS Use will Rise on New H/W Trends, Says Reinders

May 25, 2017

If you have not already tried using PGAS, it is time to consider adding PGAS to the programming techniques you know. Partitioned Global Array Space, commonly kn Read more…

By James Reinders

Exascale Escapes 2018 Budget Axe; Rest of Science Suffers

May 23, 2017

President Trump's proposed $4.1 trillion FY 2018 budget is good for U.S. exascale computing development, but grim for the rest of science and technology spend Read more…

By Tiffany Trader

Hedge Funds (with Supercomputing help) Rank First Among Investors

May 22, 2017

In case you didn’t know, The Quants Run Wall Street Now, or so says a headline in today’s Wall Street Journal. Quant-run hedge funds now control the largest Read more…

By John Russell

Doug Kothe on the Race to Build Exascale Applications

May 29, 2017

Ensuring there are applications ready to churn out useful science when the first U.S. exascale computers arrive in the 2021-2023 timeframe is Doug Kothe’s job Read more…

By John Russell

PRACEdays Reflects Europe’s HPC Commitment

May 25, 2017

More than 250 attendees and participants came together for PRACEdays17 in Barcelona last week, part of the European HPC Summit Week 2017, held May 15-19 at t Read more…

By Tiffany Trader

PGAS Use will Rise on New H/W Trends, Says Reinders

May 25, 2017

If you have not already tried using PGAS, it is time to consider adding PGAS to the programming techniques you know. Partitioned Global Array Space, commonly kn Read more…

By James Reinders

Exascale Escapes 2018 Budget Axe; Rest of Science Suffers

May 23, 2017

President Trump's proposed $4.1 trillion FY 2018 budget is good for U.S. exascale computing development, but grim for the rest of science and technology spend Read more…

By Tiffany Trader

Cray Offers Supercomputing as a Service, Targets Biotechs First

May 16, 2017

Leading supercomputer vendor Cray and datacenter/cloud provider the Markley Group today announced plans to jointly deliver supercomputing as a service. The init Read more…

By John Russell

HPE’s Memory-centric The Machine Coming into View, Opens ARMs to 3rd-party Developers

May 16, 2017

Announced three years ago, HPE’s The Machine is said to be the largest R&D program in the venerable company’s history, one that could be progressing tow Read more…

By Doug Black

What’s Up with Hyperion as It Transitions From IDC?

May 15, 2017

If you’re wondering what’s happening with Hyperion Research – formerly the IDC HPC group – apparently you are not alone, says Steve Conway, now senior V Read more…

By John Russell

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference Read more…

By Tiffany Trader

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

Since our first formal product releases of OSPRay and OpenSWR libraries in 2016, CPU-based Software Defined Visualization (SDVis) has achieved wide-spread adopt Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Last week, Google reported that its custom ASIC Tensor Processing Unit (TPU) was 15-30x faster for inferencing workloads than Nvidia's K80 GPU (see our coverage Read more…

By Tiffany Trader

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a ne Read more…

By Tiffany Trader

Leading Solution Providers

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is Read more…

By Tiffany Trader

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which w Read more…

By Tiffany Trader

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling Read more…

By Steve Campbell

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Eng Read more…

By Tiffany Trader

US Supercomputing Leaders Tackle the China Question

March 15, 2017

As China continues to prove its supercomputing mettle via the Top500 list and the forward march of its ambitious plans to stand up an exascale machine by 2020, Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu's Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural networ Read more…

By Tiffany Trader

DOE Supercomputer Achieves Record 45-Qubit Quantum Simulation

April 13, 2017

In order to simulate larger and larger quantum systems and usher in an age of "quantum supremacy," researchers are stretching the limits of today's most advance Read more…

By Tiffany Trader

Knights Landing Processor with Omni-Path Makes Cloud Debut

April 18, 2017

HPC cloud specialist Rescale is partnering with Intel and HPC resource provider R Systems to offer first-ever cloud access to Xeon Phi "Knights Landing" process Read more…

By Tiffany Trader

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