Supercomputers/Systems/Brown (Purdue)
USA · decommissioned · hpc
Brown (Purdue)
Also known as Brown community cluster
Operated by Purdue University .
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
- 790.00 TFlop/s
- Rpeak
- 1.08 PFlop/s
- Rmax ÷ Rpeak
- 73.1%
- Cores
- 12,960
- Power
- 240 kW
- Per watt
- 3.3 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 Brown (Purdue), and those in USA. 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 | 790.00 TFlop/s | #178 of 234 · bottom 25% | #189 of 332 · bottom 44% |
| Energy efficiency | 3.3 GF/W | #67 of 158 · top 42% | #59 of 162 · top 36% |
| Rmax ÷ Rpeak | 73.1 % | #102 of 229 · top 44% | #180 of 331 · bottom 47% |
| Power draw | 240 kW | #122 of 161 · bottom 25% | #122 of 171 · bottom 30% |
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 | - Dell PowerEdge R640 nodes | Dell Technologies | - | Reported | rcac.purdue.edutop500.org |
| CPU | - Two 12-core Intel Xeon Gold 6126 (Skylake) per node, 24 cores | Intel | - | Reported | rcac.purdue.edutop500.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds 100 Gbps EDR InfiniBand on all nodes | Mellanox NVDANASDAQ
rolls up to NVIDIA | - | Reported | rcac.purdue.edutop500.org |
The read
Brown was a Purdue Rosen Center community cluster for tightly coupled science and engineering codes, built with Dell and Intel and installed on 1 October 2017. RCAC's page describes Dell nodes with two 12-core Xeon Gold (Skylake) processors, 96 GB of memory and 100 Gbps EDR InfiniBand on every node, with a five-year warranty, and records its retirement on 13 December 2023. TOP500 lists the PowerEdge R640 system at 12,960 cores, 0.79 PFlop/s Rmax, 1.08 PFlop/s Rpeak and 240 kW, 303rd in November 2017 and 422nd in June 2018 (two lists). It belongs to the same RCAC family as Conte (conte), Carter (carter-purdue) and Rice (purdue-rice).
Timeline
- 2017-10 First operational source
- 2017-11 List debut at #303 (November 2017) source
- 2023-12-13 Decommissioned source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-18 Brown (Purdue) added from its source pages
Nearby in scale
The machines closest to Brown (Purdue) by Rmax, smaller to larger.
- XStream · USA, decommissioned · 0.78 PFlop/s
- Zin · USA, decommissioned · 0.77 PFlop/s
- Tianhe-1A Hunan Solution · China, decommissioned · 0.77 PFlop/s
- Draco · Germany, operational · 0.79 PFlop/s
- Sunway BlueLight MPP · China, operational · 0.8 PFlop/s
- Suiren2 · Japan, operational · 0.8 PFlop/s
Related systems
Same operator
- Rice (Purdue) · USA, decommissioned, 2015
- Bell (Purdue) · USA, operational, 2020
- Conte · USA, decommissioned, 2013
- Anvil · USA, operational, 2022
- Carter (Purdue) · USA, decommissioned, 2011
- Gautschi AI · USA, operational, 2024
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.