China operates a number of supercomputer centers. In the mid-2010s, Chinese supercomputers occupied top spots on the TOP500.^[1] Since 2019, after the U.S. began levying sanctions on several Chinese companies involving with supercomputing, public information on the state of supercomputing in China had become less available.^[2]

The origins of these centers go back to the 1980s,^[3] when the State Planning Commission, the State Science and Technology Commission and the World Bank jointly launched a project to develop networking and supercomputer facilities in China. In addition to network facilities, the project included three supercomputer centers.^[4] The progress of supercomputing in China has been rapid; the country's most powerful supercomputer placed 43rd in November 2002 (DeepComp 1800^[5]), 11th by November 2003 (DeepComp 6800^[6]), 10th by June 2004 (Dawning 4000A^[7]), and by November 2010 (Tianhe-1A^[8]) held top spot. China would go on to fall behind Japan in June 2011 until June 2013 when the country's most powerful supercomputer once again clocked in as the world record.^[9]

Prior to the Sunway TaihuLight, Chinese supercomputers have used "off the shelf" processors, e.g. Tianhe-I uses thousands of Intel and Nvidia chips, and uses the Linux operating system which is open-source software. However, to avoid possible future technology embargo restrictions, the Chinese are developing their own processors such as the Loongson, a MIPS type processor.^[10][9]

According to the MIT Technology Review, the Loongson processor would power the Dawning supercomputers by 2012, producing a line of totally Chinese-made supercomputers that reach petaflop speeds.^[11]

In April 2021, seven Chinese supercomputing entities were added to the Entity List of the United States Department of Commerce's Bureau of Industry and Security.^[12]

The Supercomputing Center of the China Academy of Sciences (SCCAS) is a support service unit affiliated to the Computer Network Information Center (CNIC) of the Chinese Academy of Sciences with the origin going back to the 1980s.^[3] The Supercomputing Center of the China Academy of Sciences (SCCAS) provides academic support functions to the National Centers. SCCAS, which is located in Beijing, is the Northern main node and operation center for China National Grid (CNGrid).^[13]

Yinhe-1 was independently designed and manufactured as the first leading China's supercomputer in 1983 with a performance level of 100 MFLOPS.^[14]

Shanghai Supercomputer Center (SSC) is a high-performance computing facility located in the Zhangjiang Hi-Tech Park in Pudong, Shanghai, China. Established in December 2000, it was the country’s first public high-performance computing service platform open for general use^[15]. The center is funded by the Shanghai Municipal Government and provides advanced supercomputing resources for scientific research and industrial applications^[15]. SSC has housed several notable supercomputers, including the “Shenwei-I” and the “Magic Cube” systems – the latter was the fastest supercomputer in Asia in 2009. The facility plays a key role in China’s computational science infrastructure, serving universities, research institutes, and enterprises across the country.

The Shanghai Supercomputer Center was officially founded on December 28, 2000, as an initiative to bolster China’s scientific computing capabilities^[16]. From its inception, the center’s mission was to offer high-performance computing (HPC) services to a broad community of users, bridging a gap in the national research infrastructure. Located in Shanghai’s Zhangjiang Hi-Tech Park, the center was established with funding from the Shanghai Municipal Government. Upon opening, SSC deployed its first supercomputer, the Shenwei-I, a massively parallel system with a performance peak of 384 GFLOPS (billion floating-point operations per second)^[16]. This period also saw SSC begin serving a handful of high-end users in fields like climate modeling and pharmaceutical research, demonstrating the value of shared supercomputing resources in China’s scientific community^[17].

By late 2003, SSC’s resources were fully utilized, prompting plans for a major upgrade as part of Shanghai’s “Information Port” development project^[18]. This second-phase expansion culminated in the installation of the Dawning 4000A supercomputer, which could complete up to 10 trillion computations per second, at SSC in November 2004^[19]. In June 2004, it was ranked No. 10 on the global TOP500 list of supercomputers, making it the first Chinese supercomputer to enter the world’s top ten^[20]. Continued government support and technological progress led to further upgrades in the late 2000s. On June 15, 2009, SSC officially launched a next-generation supercomputer nicknamed the “Magic Cube,” formally known as Dawning 5000A^[21]. With a maximum performance of 180.6 teraflops, the Magic Cube was the first Chinese supercomputer to exceed 100 trillion calculations per second, representing a significant step toward petascale computing and branding it as the fastest supercomputer in Asia^[22]. By the end of its first decade, the SSC had established itself as a key public HPC hub, meeting its initial objectives of accelerating scientific innovation and providing computational support to industry.

The Shanghai Supercomputer Center has made significant strides in advancing its infrastructure to support cutting-edge scientific research and industrial applications. The center currently houses the Magic Cube III supercomputer, which delivers a peak performance of 3.3 petaflops, making it one of the most powerful supercomputers in China^[23] . SSC provides essential computational support for a wide array of fields, including artificial intelligence, environmental modeling, and drug discovery, enabling research that addresses complex global challenges. In addition to its powerful hardware, SSC integrates a comprehensive suite of scientific simulation software that enhances its capabilities in fields like climate change modeling and public health forecasting^[23]. The center’s AI platform, for example, facilitates the entire lifecycle of AI development, from data processing to model deployment, fostering innovation in areas such as autonomous systems and machine learning. SSC’s infrastructure is continuously upgraded to meet the growing demand for high-performance computing, and its collaborations with both domestic and international research institutions solidify its position as a key player in global scientific advancements. These ongoing developments highlight SSC’s critical role in supporting China’s drive for technological self-reliance, particularly in the areas of big data analytics, AI, and supercomputing^[24].

Services and Applications

The SSC has a variety of services designed to meet the diverse and great computational needs of many sectors. In terms of the users, SSC serves a wide range of users, including academic researchers, industrial enterprises, and public utilities. About 70% of the users are scientific researchers from universities and research institutions, while the other 30% are industrial users from different sectors like automotive and aviation^[16]. The center’s resources are used across various disciplines, including math, physics, chemistry, biology, aerospace, and more. This multidisciplinary approach allows for advancements in fundamental research and applications as well. In terms of specific services, the SSC has three main services. The first is Computer Power Leasing, which allows users to access the SSC’s high computing resources through a lease, and lets them run complex simulations, data analyses, etc. The second is Consulting Services, where the center offers expert consulting in computational modeling and simulation among other topics. Finally, the last service is Research and Development or R&D Services, where the SSC collaborates on R&D projects and provides technical support and help^[25]. ​Overall, the SSC plays a key role in supporting a wide range of scientific and industrial research and endeavors by providing high performance computing resources.  

In line with China's strategic emphasis on building computational strength, SSC has launched a series of efforts to enhance and expand its facilities. SSC has made significant developments partnering with China Telecom's plan to establish a computing center in Lingang New Area, Shanghai. The center will utilize 40,000 powerful racks for supercomputing and intelligent computing to produce graphics processing units (GPUs)^[26]. This would offset the problems posed by restrictions on the import of GPUs due to tensions between China, the United States, and Taiwan. The efforts made by the SCC to alleviate political tensions demonstrate China's greater initiative towards local innovation.

SSC improvements are aligned with Shanghai's holistic plans to develop into a leading science and technology innovation hub on the global stage. Shanghai has been increasing its research and development expenditure consecutively. It allocated roughly 4.4% of its GDP for R&D purposes in 2024, of which roughly 11% went to basic research^[27]. This investment is a reflection of the city's dedication to improving scientific advancements. Since they have catalyzed their local innovation, China and the SSC have looked to global partnership and innovation. SSC collaborates with international research institutes and participates in international scientific cooperation, facilitating knowledge and expertise exchange. International collaborations enhance SSC's strength and solidify its position as a top supercomputing center. SSC also provides computing facilities to engineers and researchers all over the world, fostering an atmosphere of cooperation that fosters international innovation.

The National Supercomputing Center in Tianjin is one of the main centers and is the first state-level supercomputing center approved in May 2009.^[28] The center houses the Tianhe-1 supercomputer unveiled by the National University of Defense Technology on October 29, 2009. As a major project under China’s 863 Program, the design of Tianhe-1 began in 2008. With a peak speed of 1,206 trillion operations per second and a measured Linpack performance of 563.1 trillion operations per second, Tianhe-1 ranked first on the TOP500 list.^[29][30] This achievement made China the second country after the United States to develop a supercomputer capable of 10^16 operations per second. To put its speed in perspective, if Tianhe-1 were to compute continuously for one day, a typical microcomputer at that time would require 160 years to match its output. Furthermore, Tianhe-1’s storage capacity is equivalent to the combined holdings of four national libraries.^[30]

The Tianjin Computer Institute had been active as far back as 1984 when it developed the 16-bit TQ-0671 microcomputer system.^[31] A commercial affiliate of the Tianjin center had previously made the PHPC100 personal supercomputer in 2008 which was about twice the size of a normal desktop computer, but had 40 times the speed. In 2010 a second generation model was released.^[32]

The National Supercomputing Center in Shenzhen (NSCS) was approved by the Ministry of Science and Technology in May 2009 as one of China’s first national supercomputing centers in the central-southern region. It is the second national supercomputing center after the one based in Tianjin and houses the second fastest machine in China, and the third fastest in the world.^[33]

Located in Xili Lake International Science & Education City, SSC Phase I occupies 43,400 square meters and is equipped with a world-class supercomputer system. In May 2010 the Nebulae computer in Shenzhen placed second on the Top 500 supercomputer list, after the Cray computer at the Oak Ridge National Laboratory in Tennessee.^[34] To date, SSC has served over 30,000 user teams and completed more than 30 million computing tasks.

Phase II is located in Guangming Science City. It covers 46,000 square meters of land and has a total construction area of 116,800 square meters, including essential research buildings, and is scheduled for completion by 2025.^[35] The center will house a 2E-level supercomputer and work alongside Phase I to provide large-scale scientific computing, industrial computation, big data processing, and intelligent supercomputing services.^[36] In May 2023, its design received Guangming District’s Top Ten High Aesthetic Design Award for 2022. Built to meet "Green Three-Star" standards, the project features a photovoltaic curtain wall that produces nearly 300,000 kWh annually, reduces heat gain, lowers energy consumption, and emits no pollutants.^[37]

The Shenzhen Supercomputing Pingshan Service Platform is the first regional platform established by the National Supercomputing Shenzhen Center, with strong support from the Pingshan District Innovation Bureau. It aims to serve the "9+2" industrial clusters in Pingshan District, promote the development of technology industries in the Pingshan High-tech Zone, and enhance the district’s innovation capacity.^[38]

Foundations for a new major branch of the National Supercomputing Center (国家超级计算中心 Guójiā Chāojíjìsuàn Zhōngxīn) were laid in Hunan University, Changsha on 28 November 2010 as the first National Supercomputing Center in Central China and the third National Supercomputing Center in China apart from the two centers which are located in Tianjin and Shenzhen.^[39] The National Supercomputing Changsha Center is managed and operated by Hunan University.^[40] It operates the Tianhe-1A Hunan Solution – NUDT YH MPP supercomputer which runs at 1342 teraflops.^[41] It was the most powerful supercomputer in the world at that time from its operation in November 2010 to November 2011.^[42][43]

The National Supercomputing Center in Jinan operates the Sunway BlueLight MPP supercomputer that runs at 795 teraflops.^[44]

The National Supercomputer Center in Guangzhou operates the fourth most powerful supercomputer in the world (as of June 2018) Tianhe-2 (MilkyWay-2),^[45] which runs at 33,000 teraflops. It also operates the Tianhe-1A Guangzhou Solution – NUDT YH MPP supercomputer that runs at 211 teraflops.^[46]

The National Supercomputing Center in Wuxi houses the Sunway TaihuLight supercomputer, the 4th most powerful supercomputer in the world as of November 2020. It is in the Binhu District, along the shores of Lake Tai, hence the name.

In December 2020, the National Supercomputing Zhengzhou Center was passed the inspection for operation, becoming the seventh national supercomputing center in China.^[47]

In 2020, the National Supercomputing Kunshan Center successfully passed the acceptance of experts, becoming the second supercomputing center in Jiangsu Province and the eighth supercomputing center in China.^[48]

In September 2020, the Chengdu Supercomputing Center was officially completed and put into operation.^[49]

• History of supercomputing
• Supercomputer architecture