USA · operational · hpc

Stampede3

Operated by Texas Advanced Computing Center at Texas Advanced Computing Center .

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	- Dell Technologies and Intel	Dell Technologies DELLNYSE	-	Reported	tacc.utexas.edu
Accelerator	Intel Data Center GPU Max 1550 Accelerators oneAPI (Xe-HPC) · Intel 7 / TSMC N5 · 600 W Intel Data Center GPU Max nodes	Intel INTCNASDAQ	-	Reported	tacc.utexas.edu
Accelerator	NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 24 nodes of four NVIDIA H100 SXM5	NVIDIA NVDANASDAQ	96 reported	Reported	docs.tacc.utexas.edu
Interconnect	Omni-Path Architecture Interconnect Fat tree · 100 Gb/s per port · About 1 microsecond Omni-Path	Intel INTCNASDAQ	-	Reported	docs.tacc.utexas.edu tacc.utexas.edu
Storage	VAST Data Platform Storage Disaggregated shared-everything shared VAST file system for home and scratch	VAST Data	-	Reported	docs.tacc.utexas.edu

The read

TACC's NSF-funded system, announced in July 2023 and in early use from January 2024, mixing new Xeon Max HBM nodes with retained Skylake and Ice Lake nodes and Intel and NVIDIA GPUs on Omni-Path. The NSF award record independently confirms the funding. TACC's two pages disagree with each other on the number of Intel GPUs (40 or 80) and on the Omni-Path speed (400 or 100 Gb/s), so no Intel GPU count is recorded. It has never submitted to TOP500.

Timeline

2023-07 Announced source
2024-01 First operational source

Site & facility

Texas Advanced Computing Center

Location: Austin, TX, USA
Cooling: Direct liquid cooling
Commissioned: 2007

tacc.utexas.edu

Where sources disagree

We record conflicts instead of picking a winner quietly. All open questions.

Intel GPU count: 40 GPUs in 10 Dell XE9640 servers (press release) against 80 GPUs in 20 nodes of four Max 1550 (docs). Both pages are TACC; no Intel GPU count is recorded.
Omni-Path speed: 400 Gb/s Cornelis CN5000 (press release) against 100 Gb/s with an upgrade planned (docs). The press release may describe the target and the docs the state at the time.

Change history

2026-09-20 Added, funding verified against the NSF award record

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
api.nsf.gov	names system and part	Intel Data Center GPU Max 1550
tacc.utexas.edu	names system, part and count	Intel Data Center GPU Max 1550, Omni-Path Architecture · counts: 96

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.