Supercomputers/Systems/Todi
Switzerland · decommissioned · hpc
Todi
Also known as Tödi; CSCS Todi Cray XK7
Operated by CSCS .
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: 1263 of 1345 systems have a readable citation that names them, and 56 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
- 273.70 TFlop/s
- Rpeak
- 392.88 TFlop/s
- Rmax ÷ Rpeak
- 69.7%
- Cores
- 8,160
- Power
- 129.4 kW
- Per watt
- 2.1 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 | - Cray XK7 (listed as XK6 in 2011) hybrid system | Cray HPENYSE
rolls up to Hewlett Packard Enterprise | - | Verified | top500.orgcscs.ch |
| Accelerator | NVIDIA Tesla K20X Accelerators CUDA (Kepler GK110) · 2,688C · 0.732 GHz · 28 nm · 235 W NVIDIA Tesla K20X GPU, one per node, 272 nodes | NVIDIA | 272 reported | Reported | cscs.chtop500.org |
| CPU | - AMD Opteron 6272 16-core 2.1 GHz | AMD | - | Reported | top500.orgcscs.ch |
| Interconnect | Cray Gemini Interconnect 3D torus · About 6 GB/s per direction per link · Around 1 microsecond Cray Gemini interconnect | Cray HPENYSE
rolls up to Hewlett Packard Enterprise | - | Reported | top500.org |
| Operating system | Cray Linux Environment Operating systems Linux, Cray-customised · Proprietary layer over open-source Linux Cray Linux Environment | Cray HPENYSE
rolls up to Hewlett Packard Enterprise | - | Reported | top500.org |
The read
CSCS's first GPU/CPU hybrid supercomputer, a Cray XK7 named for the Tödi peak in the Glarus Alps. CSCS's decommissioned-systems page describes 272 nodes, each with a 16-core AMD Opteron CPU, 32 GB of DDR3 and one NVIDIA Tesla K20X GPU, for 4,352 cores and 272 GPUs, and lists Tödi under 2009 to 2015. TOP500 lists Todi as a Cray XK6 (Opteron 6272 16C 2.1 GHz, Gemini, NVIDIA 2090) at 5,632 cores on its first appearance in November 2011 (330th), then as a Cray XK7 with Tesla K20 at 8,160 cores, 273.70 TFlop/s Rmax, 392.88 TFlop/s Rpeak and 129.4 kW, 91st in November 2012 and 375th in November 2015, its last list. TOP500's core counts differ from CSCS's node description, which is unresolved, so the TOP500 figures are used and the tier is reported. Installation year 2011 is TOP500's.
Timeline
- 2011 First operational source
- 2012-11 List debut at #91 (November 2012) source
- 2015 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
- 2026-10-09 Todi added from its source pages
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 |
|---|---|---|
| cscs.ch | does not name this system | NVIDIA Tesla K20X · counts: 272 |
| top500.org | names system, part and count | NVIDIA Tesla K20X, Cray Gemini, Cray Linux Environment · counts: 272 |
Checked 2026-10-13 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
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.