Supercomputers/Systems/iREMB
South Korea · operational · hpc
iREMB
Also known as DGIST iREMB
Operated by DGIST Supercomputing & Big Data Center .
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
- 470.00 TFlop/s
- Rpeak
- 980.00 TFlop/s
- Rmax ÷ Rpeak
- 48.0%
- Cores
- 14,400
- 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 iREMB, and those in South Korea. 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 | 470.00 TFlop/s | #190 of 242 · bottom 23% | #21 of 32 · bottom 36% |
| Rmax ÷ Rpeak | 48.0 % | #230 of 238 · bottom 4% | #31 of 32 · bottom 4% |
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 Cluster Platform DL380 | Hewlett Packard Enterprise | - | Reported | top500.org |
| Accelerator | - NVIDIA Tesla K40 | NVIDIA | - | Reported | top500.orgdhnews.co.kr |
| CPU | - Intel Xeon E5-2650v3 10C 2.3GHz | Intel | - | Reported | top500.org |
The read
iREMB is the open GPU cluster of the DGIST Supercomputing and Big Data Center for education and research. A Korean news report of 16 November 2016 says it ranked 351st on the November 2016 TOP500 at 470 TFlop/s, up 53 percent from June after a GPU upgrade and optimisation, and was the top South Korean open system for pure education and research; DGIST planned a 10 Gbps KOREN link. TOP500 lists an HPE Cluster Platform DL380 with Xeon E5-2650v3 10C 2.3 GHz, 10G Ethernet and NVIDIA Tesla K40: 10,244 cores at 456th in June 2016, then 14,400 cores at 352nd in November 2016 and 456th in June 2017, with 0.47 PFlop/s Rmax and 0.98 PFlop/s Rpeak (rank figures differ by one from the news report).
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
- 2026-10-18 iREMB added from its source pages
Nearby in scale
The machines closest to iREMB by Rmax, smaller to larger.
- Weta Digital Apollo 6000 · New Zealand, upgraded · 0.47 PFlop/s
- Shadow (Mississippi State) · USA, operational · 0.46 PFlop/s
- Kukai · Japan, operational · 0.46 PFlop/s
- Mesabi · USA, operational · 0.47 PFlop/s
- Shepard · USA, operational · 0.48 PFlop/s
- BlueGene/L · USA, decommissioned · 0.48 PFlop/s