ClareNow
Search
ClareNow
Toggle sidebar
Technology → Neutral

New Chinese System Takes Top Supercomputer Spot

China's LineShine has surpassed El Capitan in key ways, using domestic CPUs, demonstrating exascale performance despite export controls.

Forbes 3 min read 8/10
New Chinese System Takes Top Supercomputer Spot
Key Takeaways
  • LineShine achieved 1.2 exaflops on the LINPACK benchmark, surpassing El Capitan's 1.1 exaflops to claim the #1 spot on the TOP500 list.
  • The supercomputer uses entirely domestically produced SW26010-Pro processors, built by Shanghai-based Loongson and fabricated at SMIC on a 7nm-class node.
  • Export controls imposed by the US in 2022–2023 were intended to prevent China from acquiring chips required for exascale computing.
  • LineShine consumes 35 megawatts, making it more power-efficient than earlier exascale systems like Frontier (21 MW) and El Capitan (estimated 40 MW).
  • China has announced plans for a successor system targeting 5 exaflops by 2028, doubling down on domestic supply chains.
Despite years of US export controls designed to throttle China's access to advanced chips, a new Chinese supercomputer named LineShine has seized the top spot in global rankings—built entirely with domestically produced CPUs and achieving exascale performance. On June 24, 2026, the TOP500 list confirmed that LineShine, developed by China's National Supercomputing Center in Wuxi, surpassed America's El Capitan system by delivering sustained performance of over 1.2 exaflops. The achievement marks a watershed moment in the supercomputing race, proving that Chinese engineers can design and manufacture cutting-edge processors without relying on foreign technology.

LineShine represents a direct response to the Biden administration's 2022 and 2023 export controls, which barred China from buying advanced semiconductors from US companies like Nvidia and AMD. Rather than stalling China's progress, the restrictions accelerated domestic innovation. The system uses a custom architecture based on the SW26010-Pro processor—a successor to the chip used in China's earlier Sunway TaihuLight supercomputer—combined with a new high-speed interconnect network. This allows LineShine to handle complex simulations for climate modeling, drug discovery, and artificial intelligence training.

During a press conference in Beijing, officials from the National Supercomputing Center confirmed that LineShine achieved 1.2 exaflops on the LINPACK benchmark, edging out El Capitan's 1.1 exaflops. The system is housed in Wuxi and consumes just over 35 megawatts of power, making it relatively energy-efficient for its class. Notably, every component—from CPUs to interconnects to cooling systems—is sourced from Chinese suppliers, including the Shanghai-based chipmaker Loongson and the state-run Semiconductor Manufacturing International Corporation (SMIC).

Analysts say LineShine's success undermines the core assumption behind US export controls: that cutting off high-end chip access would permanently cripple China's high-performance computing ambitions. "What we're seeing is a classic case of unintended consequences," said Dr. Emily Zhao, a supercomputing expert at the Center for Strategic and International Studies. "The US restrictions created a powerful incentive for Chinese fabless chip designers and fabs to close the gap faster than anyone expected."

Looking ahead, China is already planning the next-generation system—rumored to exceed 5 exaflops by 2028—while the US Department of Energy has accelerated its own research into novel architectures. The competition is now as much about software ecosystems and energy efficiency as raw speed. LineShine proves that the era of US-led supercomputing dominance is over, replaced by a bipolar landscape where both powers can push the boundaries of computational science. The question is no longer whether China can build world-class supercomputers, but how the rest of the world will adapt to this new reality.

Frequently Asked Questions

LineShine is a Chinese exascale supercomputer developed by the National Supercomputing Center in Wuxi. It achieved the top spot on the TOP500 list in June 2026 by delivering 1.2 exaflops using entirely domestically produced processors.

LineShine reached 1.2 exaflops on the LINPACK benchmark, slightly surpassing El Capitan's 1.1 exaflops. Both are exascale systems, but LineShine took the lead in raw performance and energy efficiency.

LineShine uses the SW26010-Pro processor, a homegrown design by Loongson fabricated at SMIC. This represents a significant advancement from earlier Chinese supercomputers like Sunway TaihuLight.

China developed its own processor architecture and manufacturing capabilities, relying on domestic companies like Loongson and SMIC to produce advanced chips despite restrictions on foreign technology imports.

Exascale computing enables simulations and data processing at speeds exceeding one exaflop, crucial for climate modeling, drug discovery, nuclear weapons simulation, and large-scale AI training. It is a key indicator of national technological strength.

LineShine signals that US export controls may have accelerated China's self-reliance in high-performance computing. The global supercomputing landscape is now bipolar, with both the US and China capable of leading-edge exascale systems.

Original source

www.forbes.com

Read original

Discussion

Join the discussion

Sign in to post a comment or reply.

No comments yet. Be the first to share your thoughts!

Sign in
Enter your email to receive a one-time sign-in code. No password needed.
Email address