Supercomputers/Systems/ASPIRE 2A+
Singapore · operational · ai training
ASPIRE 2A+
Operated by National Supercomputing Centre Singapore at NSCC (NUS i4.0 Data Centre) .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 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
- 14.20 PFlop/s
- Rpeak
- 21.73 PFlop/s
- Rmax ÷ Rpeak
- 65.3%
- Cores
- 46,720
- 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.
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 | - NVIDIA DGX SuperPOD, 40 DGX H100 compute nodes | NVIDIA | - | Verified | top500.orgnsccsg.github.io |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W eight NVIDIA H100 SXM5 80GB per node, 40 nodes | NVIDIA | 320 estimated | Verified | top500.orgnsccsg.github.io |
| CPU | Intel Xeon Platinum 8480C CPUs x86-64 · 56C · 2 GHz · Intel 7 · 350 W two Intel Xeon Platinum 8480C per node, 40 nodes | Intel | 80 estimated | Verified | top500.orgnsccsg.github.io |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds NVIDIA Quantum-2 NDR InfiniBand, eight ConnectX-7 ports per node | NVIDIA | - | Verified | top500.orgnsccsg.github.io |
| Operating system | Ubuntu Server Operating systems Linux distribution · Open source, free with paid support tiers Ubuntu 22.04 | Canonical | - | Reported | top500.org |
The read
Singapore's newest AI-dedicated national system, an NVIDIA DGX SuperPOD of 40 DGX H100 nodes (320 NVIDIA H100 SXM5 80GB GPUs) on NVIDIA Quantum-2 NDR InfiniBand, launched on 25 October 2024 alongside the CPU-based ASPIRE 2A as part of a S$270 million government commitment to next-generation supercomputing named at the launch by Singapore's Deputy Prime Minister. NSCC's own system-specifications page independently names the same DGX H100 node count and 320-GPU total that TOP500 records; it was 90th on the November 2024 TOP500 list. It sits beside, and does not replace, ASPIRE 2B's later GPU partition, already in this dataset. TOP500 is the only source for Rmax, Rpeak and core count, so the tier is reported.
Timeline
- 2024-10 Announced source
- 2024-10 First operational source
- 2024-11 List debut at #90 (November 2024) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
NSCC (NUS i4.0 Data Centre)
- Location
- Singapore, Singapore
- Commissioned
- 2024
Change history
- 2026-09-23 Added; a second, all-GPU Singapore national system alongside ASPIRE 2B
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| nsccsg.github.io | names system, part and count | Intel Xeon Platinum 8480C, NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2), Ubuntu Server · counts: 80 |
| top500.org | names system, part and count | Intel Xeon Platinum 8480C, NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2), Ubuntu Server · counts: 80 |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
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.