China's LineShine supercomputer tops TOP500 list using homegrown Arm-based processors
By
Simon Sharwood
Summary
The TOP500 supercomputer list has a new leader: China's LineShine machine at the National Supercomputer Center in Shenzhen, achieving 2.198 Exaflop/s without using processors from Nvidia, Intel, or AMD. The system uses Chinese LX2 processors based on Armv9 designs (a British architecture) and runs KylinOS, a Linux distribution. This highlights China's continued reliance on foreign technology (Arm cores and Linux) despite efforts toward self-sufficiency in high-performance computing.
Source
Key quotes
· 3 pulledThe TOP500 list of Earth's mightiest supercomputers has a new leader: the 2.198 Exaflop/s LineShine machine housed at the National Supercomputer Center (NSC) in Shenzhen
the machine's LX2 processors are a local effort but use Armv9 designs – so chalk up a win for Blighty, the home of Arm
Use of Arm cores and Linux mean Beijing hasn't broken away from the world
You might also wanna read
LineShine Supercomputer Takes Number One Spot on TOP500 at ISC 2026
The article reports on the 67th TOP500 list announced at ISC 2026 in Hamburg, revealing a new number one supercomputer: the LineShine system
LineShine Tops 67th TOP500 List as Global Exascale Supercomputing Era Expands
The 67th TOP500 list, announced at ISC 2026 in Hamburg, reveals LineShine — a previously unlisted Chinese supercomputer — as the new No. 1,
top500.org·7d agoAlibaba's Pingtouge PPU AI Chip Surpasses NVIDIA A800, Comparable to H20 in Performance
Alibaba's subsidiary Pingtouge has unveiled a new AI chip called PPU that reportedly surpasses NVIDIA's A800 in all major parameter metrics
Analysis of Arm's X925 Core Design and Its Competitive Position Against x86 Processors
The article analyzes Arm's latest X925 core design, highlighting its significant performance improvements that now enable it to compete with
Chinese Researchers Develop Analog Chip Claimed to Be 1,000 Times Faster Than Nvidia GPUs for Specific Applications
Chinese researchers from Peking University have developed a new analog chip using resistive random-access memory (RRAM) technology that repo
HIVE Digital's Paraguay-based A40 GPUs match Nvidia H100 performance in AI training benchmark
Cryptocurrency miner and digital infrastructure company HIVE Digital Technologies, in collaboration with Columbia University researchers, de

Comments
Sign in to join the conversation.
No comments yet. Be the first.