Fujitsu Launches M12 Servers; Emphasizes Commitment to SPARC

By John Russell

April 4, 2017

Delivering on their promised SPARC roadmap, Fujitsu and Oracle today introduced two new servers – the M12-2 and M12-2S – featuring the new SPARC64 XII chip announced last year and a new hybrid liquid/vapor cooling system. The new servers, says Fujitsu, “achieve the world’s highest per CPU core performance in arithmetic processing, offering dramatic improvements for a wide range of database workloads, from mission-critical systems on premises to big data processing in the cloud.”

A big part of the intended message here is that Fujitsu’s commitment to the SPARC ecosystem remains strong. “We feel this is a good empirical marker to show we are continuing to invest in the SPARC platform. This is not a softball product release. These are all significant advances and represent a lot of time and effort,” said Alex Lam, vice president and head of North America strategy.

Fujitsu, of course, is a major chip supplier and systems builder. The company notably jumped from the SPARC chip, which it used in building Japan’s K computer, to ARM for the post K computer now under development as part of Japan’s Flagship 2020 Project. The latter project has experienced delay which many observers attributed to challenges adapting the ARM architecture for supercomputing (see HPCwire article, Japan’s Post-K Computer Hits 1-2 Year Speed Bump). In any case, delivering on its SPARC roadmap may reassure the SPARC camp, including a large Oracle customer base, that Fujitsu isn’t planning to walk away from them.

Fujitsu M12 Servers

Akira Kabemoto, Fujitsu senior vice president, is quoted in the official release saying, “In addition to the Fujitsu SPARC M12, which is a result of close collaboration between Fujitsu and Oracle, Fujitsu will continue to develop cutting-edge technology that contributes to the creation of new value and supports customers in expanding their businesses.”

The M12-2 and M12-2S replace the M10 top-of-the-line servers and are aimed primarily at enterprise applications. That said, Fujitsu also sees opportunity for the new offerings in deep learning applications, according to Lam.

It’s probably worth noting that SPARC technology is not widely used in traditional HPC today.

“The HPC industry was at one point dominated by RISC processors, but x86 took over in the Beowulf cluster revolution. IBM POWER is the most noteworthy RISC processor still in the market, followed by SPARC systems from Fujitsu. Most of the original volume of SPARC came from Sun Microsystems, but Oracle (which acquired Sun) rarely sells HPC systems. With a new SPARC server, Fujitsu can continue to serve its existing customer base, but it is difficult to recapture market share from x86. IBM has at least addressed one major hurdle by making POWER “endian” compatible with x86 in data handling, which makes the migration easier,” noted Addison Snell, CEO, Intersect360 Research

Given the blurring of lines between traditional HPC and data-driven computing with deep learning as a centerpiece, perhaps SPARC may find room to grow amid a frothy landscape of alternative processors all seeking inroads.

Among improvements to the new servers are increased clock rates – 4.25 GHz in the M12-2S and 3.9GHz in the M12-2 – which contribute to performance gains of up to 2.5X over the M10 servers according to Lam. Combined with SPARC64’s flexible core activation the higher performance should allow reduced software licensing costs and time-to-solution. With core-level CPU activation, a minimum of just two processor cores must be activated initially. Core resources can be gradually expanded, as needed, in increments of a single core using activation keys. Benchmarks supporting Fujitsu’s “World’s highest performing core” claim are shown at the end of the article.

The M12-2S is positioned as a highly scalable platform while the M12-2S as a mid-range server. Both have core-based CPU activation, the hybrid cooling system, and Fujitsu’s Software-on-Chip instructions designed to enhance any applications such as encryption and data base acceleration Here’s a brief snapshot:

  • M12-2S. Up to 32 12-core, 4.25 GHz SPARC64 XII processors for a total of 384 cores and 3,072 threads. Main memory configurations range from 64 GB to 32 TB and support mixed DIMM capacities. Fujitsu says the M12-2S offers, “superior performance for mission-critical enterprise workloads and cloud computing. Employing proven Fujitsu supercomputer technology for highly parallel computing and an innovative cooling technology to achieve low latency access time between memory and CPU, the Fujitsu SPARC M12 servers can process large amounts of data in a short period of time.” Summary data sheet shown below.
  • M12-2. It is available in single- and dual-processor configurations that can scale to 24 cores and 192 threads. Flexible main memory configurations range from 64 GB to 2 TB and supporting mixed DIMM capacities. The server is a 4U form factor. Fujitsu says, “It is an ideal server for traditional enterprise-class workloads such as online transaction processing (OLTP), business intelligence and data warehousing (BIDW), enterprise resource planning (ERP), and customer relationship management (CRM), as well as new environments in cloud computing or big data processing.”


The enhanced M12 cooling system is called Vapor Liquid and Loop Cooling (or VLLC for short). It is twice as effective as the earlier liquid only system used on the M10. Think of the new system as a two chamber approach, explained Lam. The liquid flows through one, but a fraction is allowed to seep out into a second chamber where it vaporizes absorbing more heat before being returned to the main flow.

“The system’s liquid is essentially water, which is the same base liquid used in the M10. The difference in the M12 is the inclusion of a pressurized VLLC chamber which has a lower air pressure. So while water normally vaporizes at 100 degree Celsius (212 degree Fahrenheit), in the VLLC the water is able to vaporize at a much lower temperature (e.g., 50 degrees C) due to the lower air pressure,” said Lam.

“Water in the VLLC (M12) is vaporized by the heat of CPU because the air pressure in the VLLC chamber is low, whereas in the M10 there isn’t this pressurized chamber, hence the much higher boiling point of the liquid.” It a little hard to visualize but the result, said Lam, is a 2X efficiency improvement.

Both systems are available now. Pricing depends on the configuration. Lam said a base configuration of the M12-2 systems would be in the $35,000 range.

CPU Core Performance Benchmark

  • Comparison based on registered results per core in the SPECint_rate2006 and SPECfp_rate2006 benchmark tests.
  • SPECint_rate2006 performance results and measurement environment: Fujitsu SPARC M12-2S Performance result (peak): 102 per CPU core Measurement environment: SPARC64 XII (4.25GHz) x1 core, Oracle Solaris 11.3, Version 12.6 of Oracle Developer Studio
  • SPECfp_rate2006 performance results and measurement environment: Fujitsu SPARC M12-2S Performance result (peak): 102 per CPU core Measurement environment: SPARC64 XII (4.25GHz) x1 core, Oracle Solaris 11.3, Version 12.6 of Oracle Developer Studio
  • These performance results were submitted to SPEC (The Standard Performance Evaluation Corporation) on April 3, 2017.

Link to the Fujitsu press release: http://www.fujitsu.com/global/about/resources/news/press-releases/2017/0404-01.html

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!

Dell EMC will Build OzStar – Swinburne’s New Supercomputer to Study Gravity

August 16, 2017

Dell EMC announced yesterday it is building a new supercomputer – the OzStar – for the Swinburne University of Technology (Australia) in support the ARC Centre of Excellence for Gravitational Wave Discovery (OzGrav) Read more…

By John Russell

Microsoft Bolsters Azure With Cloud HPC Deal

August 15, 2017

Microsoft has acquired cloud computing software vendor Cycle Computing in a move designed to bring orchestration tools along with high-end computing access capabilities to the cloud. Terms of the acquisition were not Read more…

By George Leopold

HPE Ships Supercomputer to Space Station, Final Destination Mars

August 14, 2017

With a manned mission to Mars on the horizon, the demand for space-based supercomputing is at hand. Today HPE and NASA sent the first off-the-shelf HPC system into space aboard the SpaceX Dragon Spacecraft to explore if Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

Leveraging Deep Learning for Fraud Detection

Advancements in computing technologies and the expanding use of e-commerce platforms have dramatically increased the risk of fraud for financial services companies and their customers. Read more…

AMD EPYC Video Takes Aim at Intel’s Broadwell

August 14, 2017

Let the benchmarking begin. Last week, AMD posted a YouTube video in which one of its EPYC-based systems outperformed a ‘comparable’ Intel Broadwell-based system on the STREAM benchmark and on a test case running ANS Read more…

By John Russell

Microsoft Bolsters Azure With Cloud HPC Deal

August 15, 2017

Microsoft has acquired cloud computing software vendor Cycle Computing in a move designed to bring orchestration tools along with high-end computing access capa Read more…

By George Leopold

HPE Ships Supercomputer to Space Station, Final Destination Mars

August 14, 2017

With a manned mission to Mars on the horizon, the demand for space-based supercomputing is at hand. Today HPE and NASA sent the first off-the-shelf HPC system i Read more…

By Tiffany Trader

AMD EPYC Video Takes Aim at Intel’s Broadwell

August 14, 2017

Let the benchmarking begin. Last week, AMD posted a YouTube video in which one of its EPYC-based systems outperformed a ‘comparable’ Intel Broadwell-based s Read more…

By John Russell

Deep Learning Thrives in Cancer Moonshot

August 8, 2017

The U.S. War on Cancer, certainly a worthy cause, is a collection of programs stretching back more than 40 years and abiding under many banners. The latest is t Read more…

By John Russell

IBM Raises the Bar for Distributed Deep Learning

August 8, 2017

IBM is announcing today an enhancement to its PowerAI software platform aimed at facilitating the practical scaling of AI models on today’s fastest GPUs. Scal Read more…

By Tiffany Trader

IBM Storage Breakthrough Paves Way for 330TB Tape Cartridges

August 3, 2017

IBM announced yesterday a new record for magnetic tape storage that it says will keep tape storage density on a Moore's law-like path far into the next decade. Read more…

By Tiffany Trader

AMD Stuffs a Petaflops of Machine Intelligence into 20-Node Rack

August 1, 2017

With its Radeon “Vega” Instinct datacenter GPUs and EPYC “Naples” server chips entering the market this summer, AMD has positioned itself for a two-head Read more…

By Tiffany Trader

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. 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

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

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

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

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 cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

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

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

Leading Solution Providers

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of Read more…

By Alex Woodie

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

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 Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

IBM Clears Path to 5nm with Silicon Nanosheets

June 5, 2017

Two years since announcing the industry’s first 7nm node test chip, IBM and its research alliance partners GlobalFoundries and Samsung have developed a proces Read more…

By Tiffany Trader

Messina Update: The US Path to Exascale in 16 Slides

April 26, 2017

Paul Messina, director of the U.S. Exascale Computing Project, provided a wide-ranging review of ECP’s evolving plans last week at the HPC User Forum. Read more…

By John Russell

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