China Sets Ambitious Goal to Reach Exascale by 2020

By Tiffany Trader

May 2, 2016

At the 12th HPC Connections Workshop in Wuhan, China, Beihang University Professor Depei Qian disclosed new information regarding HPC development in China and exascale plans that are shaping up under China’s 13th five-year plan (2016-2020). Since 1996 Professor Professor Qian has served on the expert committee for the National High-tech Research & Development Program (the 863 program). Currently, he is the chief scientist of the 863 key project on high productivity computer and application service environment.

Professor Qian acknowledged that despite export restrictions on processor and software technology imposed by the US, work continues on two 100 petaflops (peak) systems: the next iteration of Tianhe-2, installed at the National Supercomputer Center in Guangzhou, and the upcoming Sunway system coming to the Jiangnan Institute of Computer Technology in Wuxi, China, near Shanghai. The official line is that these systems will be ready “by the end of the year,” but there have been rumblings that one or both of these systems will be introduced during the ISC’16 event in June.

In a Tuesday session at ISC, Professor Dr. Guangwen Yang, the director of the National Supercomputer Center at Wuxi, China, is slated to deliver talk titled “The New Sunway Supercomputer System at Wuxi.” Dr. Yang will describe the hardware and software elements that make up the system and some of the applications that will be deployed on it. A notice for that talk mentions that the system will be formally announced this summer.

China has been known to play its cards close to the vest before and launched its current supercomputing star, Tianhe-2, two years ahead of schedule. With a theoretical peak speed of 54.9 petaflops and a LINPACK rating of 33.86 petaflops, Tianhe-2 (the name means “Milky Way”) has been the world’s fastest number-cruncher since it debuted on the June 2013 TOP500 list.

The implementation scheme of the second phase of Tienhe-2 was evaluated and approved in July 2014. The original plan was to use next-generation Intel Xeon Phi (Knights Landing) processors for the upgrade path but due to export blocks put in place by the US, China was stimulated to accelerate its native chip development efforts. The new plan relies on Chinese made processors. “The development of the new FeiTeng processor is underway and we are waiting for the processor to upgrade the Tianhe-2 system,” said Professor Quin.

The second 100 petaflops system (Sunway) will use the next-generation Chinese-made ShenWei chips and will be implemented together with a general purpose cluster system of 1 petaflops performance. This configuration is designed to meet a wide variety of application requirements.

Both systems were developed under the auspices of China’s 12th five-year plan (2011 to 2015). Also under this program, China has been exploring new operation models and mechanism for CNGrid (China’s national HPC environment) and developing cloud-like application villages over CNGrid to promote applications.

CNGrid

The CNGrid service environment is a major resource of computing and storage across China. Currently, this environment is enabled by the CNGrid Suite, a software package used for the operation of the environment, Qian noted. There are 14 nodes altogether, more than 8 petaflops aggregated computing power and more than 15 petabytes of storage. The organizers have deployed more than 400 software applications and tools and also use this environment to support more than 1,000 projects.

Domain-oriented application villages are being established on top of CNGrid to provide services to the users. There are three current application villages under development: industrial product design and optimization, new drug discovery and digital media.

China has also deployed a number of parallel software development efforts to support fusion simulation, CFD for aircraft design, drug discovery, rendering for digital media, structural mechanics for large machinery, and simulation for electro-magnetic environment. The level of parallelism required is more than 300,000 cores with an efficiency of more than 30 percent.

Challenges

Depei Qian ASC16 China WeaknessProfessor Qian provided an overview of China’s main weaknesses, the most significant being a gap in kernel technologies and the lack of a suitable accelerator for the Tienhe-2 upgrade on account of the US embargo. “Currently there is no available accelerator to upgrade the system and it’s a major issue from the point of view of the Chinese government,” he said. “We had to change our plan and rely on our own processors. We are in urgent need for the system software, for the domestic processor, for the tool software and also the application software. Without an ecosystem around the domestic processors, we will not succeed in this respect.”

Also noted were a weakness in novel devices — memory storage and network as well as large-scale parallel algorithms and programs, system software, commercial software. “This is a very special phenomenon in China,” said Qian. “Currently China relies on the imported commercial application software, that software is very expensive and also limited in parallelism and limited by regulations. The center in Guangzhou cannot freely purchase system software from the vendor.” The third weakness is one shared by many countries: a talent shortage. “We don’t have enough people to work in HPC because either they only know the IT side or the domain side. We need more talented people that are also cross-disciplinary,” stated Qian.

13th Five-Year Plan Targets Exascale

After updating the continued supercomputing progress being made under the 12th five-year plan, Qian walked through brand-new elements of China’s 13th five-year plan, which puts into motion one of the most ambitious exascale programs in the world. If successful the program will stand up an exaflops (peak) supercomputer by the end of 2020 within a 35 MW power limit.

China is in the midst of overhauling its national research system and restructuring 100 programs into five tracks: Basic research program; mega-research program; key research and development program; enterprise-oriented research program; research centers and talents program.

The new track that is being focused on in the session is the third one – the key research and development program. A proposal for the track-3 key project on HPC was submitted in September 2015 and launched on February 2016.

The primary pillars for the key project are developing exascale computers, promoting computer industry by technology transfer and a China-controlled HPC technology set. The major tasks are next-generation supercomputing development, CNGrid upgrading and transformation, and domain HPC applications development. A robust supercomputing program is seen as a critical for addressing grand challenge problems spanning the environment, energy, climate, medicine, industry and science.

Depei Qian ASC16 Motivations slide

According to Professor Qian, the number one priority task is the development of an exascale supercomputer, based on a multi-objective optimized architecture that balances performance, energy consumption programmability, reliability and cost.

To achieve this goal, China is funding research into novel high performance interconnects with 3-D chip packaging, silicon photonics and on-chip networks. Programming models for heterogeneous computers will emphasize ease in writing programs and exploitation of performance of the heterogeneous architectures.

The program includes the development of prototype systems for verification of the exascale computer technologies. The computer scientists will explore possible exascale computer architectures, interconnects which can support more than 10,000 nodes, and energy efficiency technologies, as power demand is known to be one of the biggest obstacles toward exascale.

The exascale prototype will be about 512 nodes, offering 5-10 teraflops-per-node, 10-20 Gflops/watt, point to point bandwidth greater than 200 Gbps. MPI latency should be less than 1.5 us, said Qian. Development will also include system software and three typical applications that will be used to verify effectiveness.

From there, work will begin on an energy-efficient computing node and a scheme for high-performance processor/accelerator design.

Depei Qian ASC16 exascale key technology slide

“Based on those key technology developments, we will finally build the exascale system,” said Qian. “Our goal is not so ambitious – it is to have exaflops in peak. We are looking for a LINPACK efficiency of greater than 60 percent. Memory is rather limited, about 10 petabytes, with exabyte levels of storage.

“We don’t think we can reach the 20 megawatts system goal in less than five years so our goal is about 35 megawatts for the system; that means 30 Gflops/watt energy efficiency. The expected interconnect performance is greater than 500 Gbps.”

Depei Qian ASC16 exascale system slide

The final goal of the exascale program is technology transfer. Qian said that China will work to field high-end domain-oriented servers based on exascale system technologies. These servers will take advantage of the advances at the node, the interconnect, scalable I/O, storage, energy savings, reliability and application software.

The professor also spoke at length about China’s software strategies.”We cannot distinguish key technologies from applications, so there will be a joint effort in this direction.” Demo applications span a numerical nuclear reactor, a numerical aircraft, a numerical earth and a numerical engine.

The plan is to transfer some of the software into products to be adopted by a minimum of 50 users. To support this effort, China will establish three national-level research and development centers for HPC application software.

The professor emphasized that China’s “self-control” strategy to eliminate dependence on foreign tech doesn’t just refer to the processor and other hardware. “One of the efforts reflected in our plan is to develop parallel algorithms and parallel libraries for the system to improve the capability of developing modern-scale systems,” he said.

The final new element of China’s renovated program is the development of a platform for education that will provide computing resources and service to undergraduate and graduate students.

A call for proposals for the new key project was issued on February 19, 2016. The proposals will be reviewed over the next two months and then the selected projects will be announced.

Subscribe to HPCwire's Weekly Update!

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

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire