Supercomputers/Systems/SLAC S3DF
USA · operational · mixed
SLAC S3DF
Also known as SLAC Shared Science Data Facility; Rubin USDF host
Operated by SLAC National Accelerator Laboratory .
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 1540 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 |
|---|---|---|---|---|---|
| Accelerator | NVIDIA H200 SXM Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W NVIDIA H200, 3 hopper nodes with 4 GPUs each | NVIDIA | 12 reported | Reported | s3df.slac.stanford.edu |
| Accelerator | NVIDIA L40S Accelerators CUDA (Ada Lovelace) · 350 W NVIDIA L40S, 19 ada nodes with 10 GPUs each | NVIDIA | 190 reported | Reported | s3df.slac.stanford.edu |
| Accelerator | - NVIDIA Tesla A100 40GB, 42 ampere nodes with 4 GPUs each | NVIDIA | 168 reported | Reported | s3df.slac.stanford.edu |
| Accelerator | - NVIDIA GeForce 2080Ti, 27 turing nodes with 10 GPUs each | NVIDIA | 270 reported | Reported | s3df.slac.stanford.edu |
| CPU | AMD EPYC 7713 (Milan) CPUs x86-64 · 64C · 2 GHz · 7 nm · 225 W AMD Milan EPYC 7713, 270 milano nodes | AMD | - | Reported | s3df.slac.stanford.edu |
| CPU | - AMD Rome 7702, 131 roma nodes; AMD Turin 9555, 52 torino nodes; Genoa 9454 on ada | AMD | - | Reported | s3df.slac.stanford.edu |
| Storage | WEKA Data Platform Storage Parallel filesystem, software-defined All-flash WEKA based filesystem | WEKA | - | Reported | isdci.slac.stanford.edu |
The read
Shared compute, storage and network facility serving LCLS and LCLS-II, the Vera C. Rubin Observatory's US Data Facility, UED and the Stanford-SLAC cryo-EM centre. SLAC's 2022 release places it in SRCF-II, the second building of the Stanford Research Computing Facility (construction began November 2021, completion then expected in the second half of 2023, 6 MW total for both buildings). The batch documentation lists seven Slurm partitions: torino (52 nodes, AMD Turin 9555), roma (131, EPYC Rome 7702), milano (270, EPYC Milan 7713), ampere (42 nodes with four A100 40GB), hopper (3 nodes with four H200, Turin 9575F), ada (19 nodes with ten L40S) and turing (27 nodes with ten GeForce RTX 2080 Ti). The three CPU-only partitions give 54,360 usable cores at 120 per node. SLAC's description adds an all-flash WEKA filesystem with Ceph object storage, Lustre, GPFS and tape. No HPL figure exists, so FLOPS are blank.
Timeline
No dated events recorded.
Change history
- 2026-10-18 Added SLAC S3DF (SLAC National Accelerator Laboratory)