Supercomputers/Systems/Garrawarla
Australia · operational · hpc
Garrawarla
Also known as Pawsey MWA GPU cluster
Operated by Pawsey Supercomputing Research Centre at Pawsey Supercomputing Research Centre .
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
- -
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- -
- 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 | - HPE XL190 Gen10, 78 servers | Hewlett Packard Enterprise | - | Verified | pawsey.org.auscientific-computing.com |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA V100, one per server on 78 servers | NVIDIA | 78 estimated | Reported | scientific-computing.com |
| CPU | - Intel Xeon 6230 Cascade Lake 20-core 2.1 GHz, 2 per node | Intel | - | Reported | scientific-computing.com |
The read
Pawsey's dedicated GPU cluster for radio astronomers using the Murchison Widefield Array (MWA), named with the Wajarri word for spider. It was bought from HPE in early 2020 for about $2 million (currency not stated) inside Pawsey's $70 million capital refresh, and a Pawsey article of 31 August 2020 calls it fully operational. Both Pawsey and Scientific Computing World give 78 HPE servers; only the latter lists the node detail: HPE XL190 Gen10 with two 20-core Xeon 6230 Cascade Lake CPUs at 2.1 GHz, 384 GB RAM, 960 GB NVMe, one NVIDIA V100 and 100 Gb/s InfiniBand. Pre-production users reported software running two to eight times faster than on the predecessor, and the MWA archive at Pawsey held over 30 PB. No FLOPS figure is published. Pawsey's 2022 annual-report systems page still lists it as the dedicated MWA system; no later status notice was found, so the 2022 status date is the last evidence. Sister Pawsey GPU machines in the dataset are Topaz and Setonix.
Timeline
- 2020-08 First operational source
Site & facility
Pawsey Supercomputing Research Centre
- Location
- Kensington, Australia
- Commissioned
- 2022
Change history
- 2026-10-29 Added Garrawarla, Pawsey's 78-node V100 cluster for the MWA telescope
Related systems
Same site
- Topaz · Australia, operational, 2020
- Setonix · Australia, operational, 2022
- Magnus · Australia, decommissioned, 2014
- Galaxy · Australia, operational, 2013
Same operator
- Epic (iVEC) · Australia, operational, 2010
Same accelerator
- Atlas (Petrobras) · Brazil, operational, 2020
- Dammam-7 · Saudi Arabia, operational, 2020
- Expanse · USA, operational, 2020
- Flow Type II · Japan, operational, 2020
- Gadi · Australia, operational, 2020
- HPC5 · Italy, operational, 2020