Fujitsu Continues HPC, AI Push

By Tiffany Trader

July 19, 2017

Summer is well under way, but the so-called summertime slowdown, linked with hot temperatures and longer vacations, does not seem to have impacted Fujitsu’s output. The Japanese multinational has made a raft of HPC and AI-related announcements over the last few weeks. One of the most interesting developments is the advance of a custom AI processor, the Deep Learning Unit (DLU). With only a brief appearance in a 2016 press release, a fuller picture emerged during the International Supercomputing Conference in June.

As revealed in a presentation from Fujitsu’s Takumi Maruyama (senior director, AI Platform business unit), the processor features mixed-precision optimizations (8-bit, 16-bit and 32-bit) and a low power consumption design, with a stated goal of achieving a 10x performance/per watt advantage compared to competitors. The target energy efficiency gain relies on Fujitsu’s “deep learning integer,” which the company says reaches effective precision (on par with 32-bit) using 8- and 16-bit data sizes. The approach is reminiscent of that used by Intel’s Knights Mill processor (see coverage here) with Intel claiming INT32 accuracy with INT16 inputs (using INT32 accumulated output).

Source: Fujitsu (2017)

The massively parallel chip employs a few large master cores connected to many Deep Learning Processing Units (DPUs). One DPU consists of 16 DPEs (Deep learning processing elements). The DPE includes a large register file and wide SIMD execution units. Linked with Fujitsu’s Tofu interconnect technology, the design is scalable for very large neural networks.

Fujitsu’s roadmap for the DLU includes multiple generations over time: a first-gen coprocessor is set to debut in 2018, followed by a second-gen embedded host CPU. More forward-looking are potential specialized processors targeting neuromorphic or combinatorial optimization applications.

Upcoming Installs

National Center for High-performance Computing (NCHC) headquarters

Also at ISC, Fujitsu announced it’s building a nearly 3.5 petaflops (peak) system for Taiwan’s National Center for High-performance Computing, National Applied Research Laboratories (NCHC). The supercomputer is expected to come online in May 2018, at which time it will become the fastest computer in the country.

“The new system will serve as the core platform for research and development in Taiwan, fostering the development and growth of Taiwan’s overall industries and economy,” said Fujitsu in an official statement. In addition to accelerating current research, there will be a focus on accommodating new research fields, such as AI and big data.

The 715 node warm water-cooled cluster will be equipped with Skylake processors and connected with Intel Omni-Path technology. Nvidia P100 GPUs will be installed on 64 nodes, providing over a third (1.35 petaflops) of total theoretical peak performance (3.48 petaflops).

The Information Technology at Kyushu University in Japan has also placed an order for a Fujitsu system, a 10-petaflopper (peak) that is scheduled for deployment in October.

“This system will consist of over 2,000 servers, including the Fujitsu Server PRIMERGY CX400, the next-generation model of Fujitsu’s x86 server….This will also be Japan’s first supercomputer system featuring a large-scale private cloud environment constructed on a front-end sub system, linked with a computational server of a back-end sub system through a high-speed file system,” according to the release.

The new supercomputer will be integrated with three existing HPC systems at the Research Institute for Information Technology. The goal is to create an environment that “extend[s] beyond the current large-scale computation and scientific simulations, to include usage and research that require extremely large-scale computation, such as AI, big data, and data science.”

New AI-Based Algorithm Monitors Heat Stress

As temperatures rise, the health of employees in active outdoor roles, for example security guards or delivery professionals, is threatened. In Japan, 400-500 workplace casualties are attributable to heat stroke each year, leading companies to take measures to safeguard employees working in extreme conditions.

Fujitsu has developed an algorithm to bolster summer safety in the workplace. Based on Fujitsu’s Human Centric AI platform, Zinrai, the algorithm estimates on-going heat stress in workers. Fujitsu will release the algorithm as part of its digital business platform, MetaArc, which uses IoT to support on-site safety management. It is also conducting an internal trial from June to September at its Kawasaki Plant.

Source: Fujitsu (2017)

Says the company, “Sites where security and other duties typically take place may be locations where workers are susceptible to heat stress. However, changes in physical condition vary according to the individual, making it difficult to take uniform measures. This newly developed algorithm makes it possible to estimate the accumulation of heat stress on a per person basis, to tailor ways to protect people based on individual conditions.”

Machine Learning Advances Lung Disease Diagnosis

Fujitsu Laboratories Ltd. in partnership with Fujitsu R&D Center Co., Ltd., has developed a technology to improve the diagnosis for a group of lung diseases that includes pneumonia and emphysema. The technology retrieves similar disease cases from a computed tomography (CT) database based on abnormal shadows implicated in these disease states. The technology is especially needed for diffuse lung diseases like pneumonia, where the abnormal shadows are spread throughout the organ in all directions. These three-dimensional problems require a great deal of knowledge and experience on the clinician’s part to interpret and diagnose.

Source: Fujitsu (2017)

As explained by Fujitsu “the technology automatically separates the complex interior of the organ into areas through image analysis, and uses machine learning to recognize abnormal shadow candidates in each area. By dividing up the organ spatially into periphery, core, top, bottom, left and right, and focusing on the spread of the abnormal shadows in each area, it becomes possible to view things in the same way doctors do when determining similarities for diagnosis.”

Early studies using real-world data indicate a high-accuracy for the approach, which has the potential to save lives by reducing the time it takes to achieve a correct diagnosis.

Promoting open data usage in the Japanese Government

On June 28, Fujitsu announced that it will be part of a project run by the Cabinet Secretariat’s National Strategy Office of Information and Communications Technology to promote the use of open data held by the national or regional public organizations. The goal is to make open data, such as population statistics, industry compositions, and geographic data, more accessible and by doing so strengthen national competitiveness.

Fujitsu will leverage its Zinrai platform to develop a test system that can laterally search for data across multiple government systems, relating texts that have the same meaning. The system will also “learn” from users’ search results such that it can fine-tune its suggestions.

Source: Fujitsu (2017)

The study, “Creating an AI-Based Multi-Database Search and Best-Response Suggestion System (Research Study on Increasing Usability of Data Catalog Sites),” will run through until December 22, 2017. Fujitsu expects the trial to result in a proposal to the Strategy Office of Information and Communications Technology for implementation.

The Zinrai AI framework:

Source: Fujitsu (2016)

 

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!

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understanding on January 10. The MOU represents the continuation of a 1 Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Tennessee), Satoshi Matsuoka (Tokyo Institute of Technology), Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown and Spectre security updates on the performance of popular H Read more…

By Tiffany Trader

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…

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

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understandi Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Te Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown Read more…

By Tiffany Trader

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

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

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 Read more…

By Tiffany Trader

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

Leading Solution Providers

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

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

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

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

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