Supercomputers/Systems/Abel
USA · operational · hpc
Abel
Operated by PGS at PGS Houston Mega Processing Center .
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
- 4.04 PFlop/s
- Rpeak
- 5.37 PFlop/s
- Rmax ÷ Rpeak
- 75.2%
- Cores
- 145,920
- Power
- 1.80 MW
- Per watt
- 2.2 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 | - Cray XC (TOP500 labels it XC30; GeekWire/NextPlatform/HPCwire described the order as an XC40) | Cray HPENYSE
rolls up to Hewlett Packard Enterprise | - | Verified | top500.orggeekwire.com |
| CPU | Intel Xeon E5-2698 v3 CPUs x86-64 · 16C · 2.3 GHz · 22 nm · 135 W Xeon E5-2698 v3 16C 2.3GHz nodes totaling 145,920 cores | Intel | - | Reported | top500.org |
| Interconnect | Cray Aries Interconnect Dragonfly · About 10 GB/s per direction · Around 1 microsecond Aries interconnect | Cray HPENYSE
rolls up to Hewlett Packard Enterprise | - | Verified | top500.orgnextplatform.com |
The read
PGS's seismic-imaging supercomputer at its Houston Mega Processing Center, named after Norwegian mathematician Niels Henrik Abel. Ordered from Cray in March 2015 as a roughly 5 PFlop/s liquid-cooled system with Aries interconnect (GeekWire, NextPlatform and HPCwire all covered the deal), used for Reverse Time Migration and Full Waveform Inversion processing including the PGS Triton survey in the Gulf of Mexico. TOP500 lists the installed machine as Rmax 4.04 PFlop/s, Rpeak 5.37 PFlop/s, 145,920 Xeon E5-2698 v3 cores, and labels the system type Cray XC30 even though contemporary press described the order as an XC40; that label discrepancy is unresolved in the sources found. First appeared on the June 2015 TOP500 list at rank 13 and was still listed as of November 2025 at rank 320. PGS itself was acquired by TGS ASA in July 2024, so the operator company row (pgs) is marked acquired with tgs as parent.
Timeline
- 2015-03 Announced source
- 2015-06 List debut at #13 (June 2015) source
- 2015-06 First operational 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
PGS Houston Mega Processing Center
- Location
- Houston, TX, USA
- Commissioned
- 2015
Change history
- 2026-09-27 Abel added, PGS's (now TGS) Cray seismic-imaging supercomputer at its Houston Mega Processing Center
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 |
|---|---|---|
| top500.org | names system and part | Intel Xeon E5-2698 v3, Cray Aries |
| geekwire.com | could not be fetched | - |
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.