GeneralJune 23, 2026 · 4:37 PM2 min read

    Return to the top: China’s LineShine beats US El Capitan in Top500 supercomputer rankings

    China has reclaimed the world’s fastest supercomputer crown for the first time since 2017, according to the latest TOP500 rankings released at the International Supercomputing Conference in Hamburg, Germany, on Tuesday. LineShine, built by the National Supercomputing Centre in Shenzhen, achieved 2.1

    By Ling Xin

    Return to the top: China’s LineShine beats US El Capitan in Top500 supercomputer rankings

    China has reclaimed the world’s fastest supercomputer crown for the first time since 2017, according to the latest TOP500 rankings released at the International Supercomputing Conference in Hamburg, Germany, on Tuesday.
    LineShine, built by the National Supercomputing Centre in Shenzhen, achieved 2.198 exaflops of performance – nearly 2.2 quintillion calculations per second – surpassing the previous champion, El Capitan, at California’s Lawrence Livermore National Laboratory, which reached 1.809 exaflops.
    It is also the first supercomputer to exceed two exaflops using only central processing units (CPUs), without relying on graphics processing units (GPUs) that power most of today’s leading supercomputers.
    “This is the first time a computer with only CPUs has reached exascale,” TOP500 co-founder and Turing Award winner Jack Dongarra told the South China Morning Post.

    Most exascale systems, including El Capitan, depend heavily on GPUs, which excel at handling many calculations simultaneously. The chips have become a focal point of US efforts to curb China’s advances in AI and supercomputing.
    “China can adapt to develop its own version of technology as good as – or maybe even better than – existing technology, despite US export controls,” Dongarra said.
    Speaking at the conference in Hamburg, LineShine chief designer Lu Yutong said the system abandoned the conventional CPU-GPU architecture. Instead, it relies on domestically developed processors with built-in AI acceleration, high-speed memory, a proprietary interconnect network, and liquid-cooling technology.
    The design was intended to support both traditional scientific simulations and AI workloads while improving energy efficiency, she said.
    Huang Xiaohui, the centre’s deputy director, said in April that LineShine had achieved full-stack independence, from underlying hardware to core software. By the end of 2025, the system had completed deployment and activation, with sustained performance exceeding two exaflops, Huang said.
    Since entering service, LineShine has already supported applications ranging from climate modelling and engineering simulations to drug discovery, neuroscience and AI, according to the centre.
    “LineShine’s success in both benchmark performance and practical applications marks a historic step forward for China’s supercomputing industry in building an independent hardware and software ecosystem despite foreign technology restrictions,” the centre said on its official WeChat account.
    China’s previous TOP500 champion was Sunway TaihuLight, which debuted at No 1 in 2016 and held the title again in 2017, before being overtaken by the US-built Summit system in 2018.

    In the years that followed, China’s presence on the list became increasingly opaque. Amid US export restrictions and growing concerns over technology controls, leading Chinese supercomputers stopped submitting benchmark results to the TOP500 list.
    According to The New York Times, LineShine was developed without public funding, allowing its designers to submit the system for TOP500 benchmarking this year.
    LineShine now leads a growing club of exascale machines. The latest TOP500 rankings include five systems above the exascale threshold, with Frontier and Aurora in the United States and Jupiter Booster in Germany rounding out the top five.

    Source: South China Morning Post · General
    Read Original