iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Exascale computing is a performance threshold: one exaflop is 1018 floating-point operations per second. In the TOP500 June 2026 edition, LineShine led the HPL ranking at 2.1984 exaflops, ahead of four other systems that also reached at least one exaflop on that benchmark. The lead has changed since Frontier became the first system to cross the threshold in 2022, and the machines serve different institutional missions.
What does exascale mean?
An exaflop is one quintillion, or 1018, floating-point operations per second. It is a rate of computation, not a measure of storage capacity or a promise that every application will run at that speed. Whether a system reaches the threshold depends on the benchmark being reported.
The rankings here use HPL, the High-Performance Linpack benchmark used by TOP500. A reported HPL result is a measured benchmark score; a system’s theoretical peak is a different specification and should not be substituted for it.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchPC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11How did the exascale race develop?
2022: Frontier crosses first
Oak Ridge National Laboratory’s Frontier debuted in 2022 with an HPL result of 1.102 exaflops, making it the first system to cross the exascale threshold. Its later HPL result rose to 1.353 exaflops after remeasurement and tuning documented by the Oak Ridge Leadership Computing Facility in November 2024. Frontier’s arrival established that exascale performance had moved from a target to an operating benchmark result.
#1 Best Overall
2023: Aurora joins while commissioning
Argonne National Laboratory’s Aurora became the second system TOP500 described as officially breaking the threshold. In TOP500’s account of its 63rd edition, Aurora recorded 1.012 exaflops HPL while it was still being commissioned and was not yet fully complete. That qualification matters: the result marked a milestone, but the system’s commissioning status was part of the context at the time.
2024: El Capitan brings exascale to NNSA
Lawrence Livermore National Laboratory’s El Capitan became the first exascale system for the National Nuclear Security Administration (NNSA), whose mission includes ensuring the safety, security and reliability of the U.S. nuclear deterrent. LLNL described the system as fully operational in its December 2024 account. It also reported a peak-performance specification of 2.79 exaflops; that is not El Capitan’s measured HPL result.
2025–2026: JUPITER reaches the threshold; LineShine takes the lead
JUPITER Booster at Germany’s Jülich Supercomputing Centre was still commissioning on a partial system when TOP500 reported its preliminary 793.4-petaflop HPL result in June 2025. In TOP500’s June 2026 edition, it reached 1.000 exaflop HPL and became the first European system in the list’s exascale group.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →In that same June 2026 edition, LineShine, installed at the National Supercomputing Centre in Shenzhen, China, ranked first. El Capitan, Frontier and Aurora occupied the next three positions, with JUPITER Booster fifth. The top position is therefore a dated benchmark result, not a permanent label for one machine.
Which systems led the TOP500 in June 2026?
The figures below are TOP500’s June 2026 HPL results, ranks and reported power values. One exaflop equals 1,000 petaflops. The listed components and sites are those given in that edition.
| Rank | System and site | June 2026 HPL result | Components listed by TOP500 | Reported power |
|---|---|---|---|---|
| 1 | LineShine — National Supercomputing Centre in Shenzhen, China | 2.1984 exaflops | LingKun platform; LX2 processors; LingQi interconnect; Kylin OS | 42,220 kW |
| 2 | El Capitan — Lawrence Livermore National Laboratory, United States | 1.809 exaflops | AMD 4th-generation EPYC and Instinct MI300A; Slingshot-11 | 29,685 kW |
| 3 | Frontier — Oak Ridge National Laboratory, United States | 1.353 exaflops | AMD 3rd-generation EPYC and Instinct MI250X; Slingshot-11 | 24,607 kW |
| 4 | Aurora — Argonne National Laboratory, United States | 1.012 exaflops | Intel Xeon CPU Max and Data Center GPU Max; Slingshot-11 | 38,698 kW |
| 5 | JUPITER Booster — Jülich Supercomputing Centre, Germany | 1.000 exaflop | Grace Hopper Superchips; BullSequana XH3000 | 15,794 kW |
Why can two benchmark scores tell different stories?
HPL and HPCG are separate benchmarks, designed to represent different computational workloads. TOP500 describes HPCG as a complement to HPL; the scores should not be treated as measurements of the same work or compared on a shared scale. In TOP500’s June and November 2025 reporting, El Capitan’s HPCG result was 17.41 petaflops, while its November 2025 HPL result was 1.809 exaflops. The difference in both benchmark and unit is essential context, not evidence that one figure replaces the other.
Likewise, a peak-performance figure describes a system specification rather than an HPL result. For El Capitan, LLNL’s reported 2.79-exaflop peak and TOP500’s HPL score answer different questions: the former is peak capability, while the latter is performance measured on the HPL benchmark.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
What does a TOP500 rank leave out?
A single HPL rank is useful for following one benchmark race, but it does not summarize every aspect of a supercomputer. The June 2026 list also provides architecture and reported power, while site and mission help explain why systems were built. Frontier and Aurora are national laboratory systems; El Capitan is the first exascale system for NNSA; JUPITER is European research infrastructure. Those differences make a rank an incomplete basis for judging which system is best for a particular scientific or institutional workload.
Power figures also need careful interpretation. The kilowatt values in the table are the values TOP500 reports for the systems; they are not a complete comparison of the facilities’ total energy use. They should not be read as a full accounting of cooling, supporting infrastructure or energy consumed over time.
What the race shows
The recent history is a sequence of milestones rather than a single finish line: Frontier crossed the threshold first, Aurora followed, El Capitan extended exascale into NNSA’s mission, and JUPITER brought a European system to the threshold. By the TOP500 June 2026 HPL edition, LineShine held the lead. Each of those statements describes a particular date, system and measure; none makes “world’s fastest” an undated or all-purpose verdict.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Recommended Free Tools
