Supercomputers/Systems/Casper
USA · operational · mixed
Casper
Also known as NCAR Casper; Casper data analysis and machine learning cluster
Operated by NCAR .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 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 | - Supermicro 7049GP-TRT SuperWorkstations in the data-analysis group | Supermicro | 22 reported | Reported | ncar-hpc-docs.readthedocs.io |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA V100: 4 nodes of four plus 6 nodes of eight (derived from the NCAR node table) | NVIDIA | 64 reported | Reported | ncar-hpc-docs.readthedocs.io |
| Accelerator | - NVIDIA A100 (8 nodes of four plus 3 data-analysis nodes) and H100 (2 nodes of four) | NVIDIA | - | Reported | ncar-hpc-docs.readthedocs.io |
| CPU | - AMD EPYC 9554P 64-core workstation nodes in the high-throughput group | AMD | 64 reported | Reported | ncar-hpc-docs.readthedocs.io |
| Interconnect | - Mellanox ConnectX adapters, 100 GbE and/or HDR InfiniBand | NVIDIA | - | Reported | ncar-hpc-docs.readthedocs.io |
The read
NCAR's heterogeneous data-analysis, visualization, machine-learning and high-throughput cluster that accompanies Derecho, documented by the NCAR HPC docs as four node groups. Data analysis and visualization: 22 Supermicro 7049GP-TRT nodes (Xeon Gold 6140, 384 GB, 9 with Quadro GP100 and 3 with A100 40GB) plus 6 AMD EPYC nodes with L40 GPUs. Machine learning: 4 nodes of four V100, 6 nodes of eight V100, 8 nodes of four A100 on EPYC Milan and 2 nodes of four H100. High-throughput: 134 nodes including 64 AMD EPYC 9554P workstations. Plus 4 Research Data Archive nodes. Mellanox ConnectX adapters (100 GbE and/or HDR InfiniBand) link every node to the GLADE storage, with 2 TB of local NVMe each. The page states only 'over 100 nodes' and no peak, HPL, start date or site, so those fields are blank.
Timeline
No dated events recorded.
Change history
- 2026-10-04 Added Casper (ncar)
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| ncar-hpc-docs.readthedocs.io | names system, part and count | NVIDIA Tesla V100 · counts: 64 |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.