Supercomputers/Systems/ASPIRE 2A (CPU Partition)
Singapore · operational · hpc
ASPIRE 2A (CPU Partition)
Also known as ASPIRE 2A CPU; NSCC HPE Cray EX425 CPU nodes
Operated by National Supercomputing Centre Singapore .
Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1581 systems have a readable citation that names them, and 64 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- 2.58 PFlop/s
- Rpeak
- 3.11 PFlop/s
- Rmax ÷ Rpeak
- 83.0%
- Cores
- 98,304
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
How it compares
Ranked against the other machines in this dataset that report the same figure: those that first came into service within two years of ASPIRE 2A (CPU Partition), and those in Singapore. Computed from our tables; a metric is ranked only when at least eight peers report it.
| Metric | Value | Against its era | Against its country |
|---|---|---|---|
| Rmax | 2.58 PFlop/s | #236 of 257 · bottom 9% | #7 of 9 · bottom 26% |
| Rmax ÷ Rpeak | 83.0 % | #58 of 256 · top 22% | #2 of 9 · top 12% |
Every metric is ranked largest-first, so a high power-draw rank means a big power draw, not a good one. Rmax ÷ Rpeak uses HPL-measured results only. Rankings move as machines are added; they describe this dataset, not the world.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - HPE Cray EX425 | Hewlett Packard Enterprise | - | Reported | top500.orgnscc.sg |
| CPU | AMD EPYC 7713 (Milan) CPUs x86-64 · 64C · 2 GHz · 7 nm · 225 W 768 standard Cray EX nodes with 2 x AMD EPYC 7713 64C 2GHz | AMD | 1,536 estimated | Reported | help.nscc.sgtop500.org |
| Interconnect | HPE Slingshot-10 Interconnect Dragonfly · 100 Gb/s per port HPE Slingshot-10, dragonfly topology | Hewlett Packard Enterprise | - | Reported | top500.orghelp.nscc.sg |
| Operating system | Red Hat Enterprise Linux Operating systems Linux distribution · Open source, commercial support subscription RHEL 8.3 | Red Hat | - | Reported | top500.org |
The read
The CPU partition of NSCC's ASPIRE 2A, which NSCC describes as Singapore's next-generation HPE Cray EX supercomputer; it sits beside the GPU partition (aspire-2a-gpu) and the later ASPIRE 2A+ (aspire-2a-plus). NSCC's help site lists 768 standard dual-socket Cray EX nodes with AMD EPYC 7713, 128 cores and 512 GB per node, on Slingshot in a dragonfly topology; 768 times 128 is exactly the 98,304 cores TOP500 reports, with Rmax 2.58 and Rpeak 3.11 PFlop/s, RHEL 8.3 and HPE Cray MPICH, and no power figure. NSCC's ASPIRE 2A page counts 105,984 EPYC 7713 cores (828 nodes by simple division), so the benchmark presumably used a subset of the nodes. NSCC states 'up to 10 PFlops' for the whole system, not the CPU nodes alone, and that ASPIRE 2A was made available to researchers on 1 July 2023; TOP500 had listed it since June 2022 (247th, its best rank). The entry recorded here is 429th in November 2024; it last appears at 499th in November 2025. ASPIRE 1 (aspire-1) was decommissioned on 31 August 2023. The hosting site is not stated on the pages read, so no site is attached.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-11-01 Added ASPIRE 2A (CPU Partition)
Nearby in scale
The machines closest to ASPIRE 2A (CPU Partition) by Rmax, smaller to larger.
Related systems
Same operator
- ASPIRE 2A (GPU Partition) · Singapore, operational, 2023
- ASPIRE 2A+ · Singapore, operational, 2024
- ASPIRE 2B (CPU Partition) · Singapore, operational, 2026
- ASPIRE 2B (GPU Partition) · Singapore, operational, 2026
- ASPIRE 1 · Singapore, decommissioned, 2016
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Latency-optimised versus throughput-optimised processors, NUMA, and the end of the host-to-device copy.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.