Semiconductor & Computer Engineering
From WikiChip
Difference between revisions of "supercomputers/olcf-6"
(add info) |
|||
| (One intermediate revision by one other user not shown) | |||
| Line 1: | Line 1: | ||
| − | {{sc title|OLCF-6}} | + | {{sc title|Discovery (OLCF-6)}} |
{{supercomputer | {{supercomputer | ||
|name=Discovery | |name=Discovery | ||
|sponsor=U.S. Department of Energy | |sponsor=U.S. Department of Energy | ||
| + | |designer=AMD | ||
| + | |designer 2=Cray | ||
|operator=Oak Ridge National Laboratory | |operator=Oak Ridge National Laboratory | ||
|introduction=2025 | |introduction=2025 | ||
|peak dpflops=2-4 exaFLOPS | |peak dpflops=2-4 exaFLOPS | ||
| − | |predecessor=Frontier | + | |predecessor=Frontier (OLCF-5) |
|predecessor link=supercomputers/olcf-5 | |predecessor link=supercomputers/olcf-5 | ||
|successor=OLCF-7 | |successor=OLCF-7 | ||
| Line 12: | Line 14: | ||
}} | }} | ||
| − | '''OLCF-6''' ('''Discovery''') is the successor to {{\\|Frontier}}, a planned exascale [[supercomputer]] that will be operated by the [[DoE]] ORNL ([[Oak Ridge National Laboratory]]). Discovery is expected to go into operation in the | + | '''OLCF-6''' ('''Discovery''') is the successor to {{\\|Frontier}}, a planned exascale [[supercomputer]] that will be operated by the [[DoE]] ORNL ([[Oak Ridge National Laboratory]]). Discovery is expected to go into operation in the 2027-2028 timeframe and will feature a peak performance of 2 to 4 [[exaFLOPS]]. |
== Models== | == Models== | ||
| Line 26: | Line 28: | ||
== History == | == History == | ||
Discovery is part of Oak Ridge 10-year facility plan. Expected to be delivered around the 2024-2026 timeframe, the system will have around 2 to 4 [[exaFLOPS]]. | Discovery is part of Oak Ridge 10-year facility plan. Expected to be delivered around the 2024-2026 timeframe, the system will have around 2 to 4 [[exaFLOPS]]. | ||
| − | |||
:[[File:olcf6 roadmap.png|700px]] | :[[File:olcf6 roadmap.png|700px]] | ||
| + | :;Roadmap | ||
:[[File:ornl-exascape-frontier-roadmap.png|800px]] | :[[File:ornl-exascape-frontier-roadmap.png|800px]] | ||
| + | :;[[Frontier]] | ||
:[[File:ornl-summit-historical-roadmap.png|800px]] | :[[File:ornl-summit-historical-roadmap.png|800px]] | ||
| + | :;[[Summit]] | ||
== TOP500 == | == TOP500 == | ||
| Line 75: | Line 79: | ||
</pre> | </pre> | ||
| + | == See also == | ||
| + | *[[AMD]] • [[EPYC]] | ||
| + | *[[Intel]] • [[Xeon]] | ||
| + | *[[IBM]] • [[NVIDIA]] | ||
| + | *[[DoE]] • [[NERSC]] | ||
[[Category:supercomputers]] | [[Category:supercomputers]] | ||
[[Category:all supercomputers]] | [[Category:all supercomputers]] | ||
Latest revision as of 13:50, 30 October 2025
| Edit Values | |
| Discovery | |
| General Info | |
| Sponsors | U.S. Department of Energy |
| Designers | AMD, Cray |
| Operators | Oak Ridge National Laboratory |
| Introduction | 2025 |
| Peak FLOPS | 2-4 exaFLOPS |
| Succession | |
OLCF-6 (Discovery) is the successor to Frontier, a planned exascale supercomputer that will be operated by the DoE ORNL (Oak Ridge National Laboratory). Discovery is expected to go into operation in the 2027-2028 timeframe and will feature a peak performance of 2 to 4 exaFLOPS.
Contents
Models[edit]
- Supercomputers • ORNL • DoE
- OLCF-1 (Phoenix) • 2004
- OLCF-2 (Jaguar) • 2005/2009
- OLCF-3 (Titan) • 2012
- OLCF-4 (Summit) • 2018 ° 2025/06 (20) ^
- OLCF-5 (Frontier) • 2021 ° 2025/06 (2) ^ (TOP2!)
- OLCF-6 (Discovery) • 2025 (?)
- OLCF-7 (?) • 2026 (?)
History[edit]
Discovery is part of Oak Ridge 10-year facility plan. Expected to be delivered around the 2024-2026 timeframe, the system will have around 2 to 4 exaFLOPS.
- Roadmap
TOP500[edit]
DOE/SC/Oak Ridge National Laboratory URL: http://computing.ornl.gov Segment Research City: Oak Ridge Country/Region: United States System Year Vendor • Cores • Rmax (GFlop/s) • Rpeak (GFlop/s) *Discovery (OLCF-6) - HPE :2025 *Frontier (OLCF-5) - HPE Cray EX235a, AMD Optimized 3rd Generation :EPYC 64C 2GHz, AMD Instinct MI250X, Slingshot-11, HPE Cray OS :2021 HPE • 9,066,176 • 1,353,000,000 • 2,055,716,990 *Frontier (TDS) - HPE Cray EX235a, AMD Optimized 3rd Generation :EPYC 64C 2GHz, AMD Instinct MI250X, Slingshot-11 :2021 HPE • 120,832 •19,200,000 • 23,105,540 *Summit (OLCF-4) - IBM Power System AC922, IBM POWER9 22C 3.07GHz, :NVIDIA Volta GV100, Dual-rail Mellanox EDR Infiniband :2018 IBM • 2,414,592 • 148,600,000 • 200,794,880 *Titan - Cray XK7, Opteron 6274 16C 2.200GHz, Cray Gemini interconnect, NVIDIA K20x :2012 Cray/HPE • 560,640 • 17,590,000 • 27,112,550 *Jaguar - Cray XK6, Opteron 6274 16C 2.200GHz, Cray Gemini interconnect, NVIDIA 2090 :2009 Cray/HPE • 298,592 • 1,941,000 • 2,627,600 *Jaguar - Cray XT5 QC 2.3 GHz :2008 Cray/HPE • 150,152 • 1,059,000 • 1,381,400 *Jaguar - Cray XT4 QuadCore 2.1 GHz :2008 Cray/HPE • 30,976 • 205,000 • 260,200 *Jaguar - Cray XT4/XT3 :2006 Cray/HPE • 23,016 • 101,700 • 119,350 *Jaguar - Cray XT3, 2.6 GHz Dual Core :2006 Cray/HPE • 10,424 • 43,480 • 54,204 *Jaguar - Cray XT3, 2.4 GHz :2005 Cray/HPE • 5,200 • 20,527 • 24,960 *Phoenix - Cray X1E (2GB) :2005 Cray/HPE • 1,014 • 14,955 • 18,333
See also[edit]
Facts about "Discovery (OLCF-6) - Supercomputers"
| designer | AMD + and Cray + |
| introductory date | 2025 + |
| name | Discovery + |
| operator | Oak Ridge National Laboratory + |
| sponsor | U.S. Department of Energy (DoE) + |