LineShine returns China to No. 1 on the TOP500 at 2.198 Exaflop/s, built entirely on domestic CPUs
LineShine, at the National Supercomputing Centre in Shenzhen, hit 2.198 Exaflop/s on HPL using 13.79 million Phytium LX2 cores — no GPU accelerators, no Western silicon — displacing El Capitan and ending China's nine-year absence from the top spot. Its mixed-precision speedup of 3.6x over HPL trails El Capitan's 9.2x, a real gap for AI training workloads; the sharper fact is that China has crossed the exascale threshold on domestic hardware alone, without Nvidia or any Western accelerator.
Source: top500.org ↗
LineShine achieved 2.198 Exaflop/s on HPL — about 80 percent of its 2.736 Exaflop/s theoretical peak — making it the first system on the TOP500 to exceed two exaflops of sustained double-precision performance using CPUs only.
TOP500 project
Why this matters
- → China achieves exascale computing without Western accelerators or GPUs.
- → First CPU-only system to lead TOP500 since 2017 Chinese dominance.
- → Signals viable alternative architectures beyond AMD/NVIDIA duopoly.
China's domestic exascale