Germany · planned · mixed

Herder

Also known as HLRS Herder

Operated by HLRS at HLRS, University of Stuttgart .

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	- HPE Cray Supercomputing GX5000 platform	Hewlett Packard Enterprise HPENYSE	-	Verified	hlrs.de heise.de
Accelerator	AMD Instinct MI430X Accelerators 1,488 AMD Instinct MI430X GPUs, eight per node	AMD AMDNASDAQ	1,488 reported	Reported	heise.de hlrs.de
CPU	- 372 AMD EPYC Venice CPUs, two per node	AMD AMDNASDAQ	372 reported	Reported	heise.de
Interconnect	- HPE Slingshot 400 switches	Hewlett Packard Enterprise HPENYSE	-	Reported	hlrs.de
Storage	- Lustre-based HPE Cray Supercomputing Storage Systems E2000	Hewlett Packard Enterprise HPENYSE	-	Reported	hlrs.de

The read

HLRS's next flagship, an HPE Cray GX5000 system with AMD Instinct MI430X GPUs and EPYC Venice CPUs on Slingshot 400 with a Lustre-based E2000 storage tier and fully direct-liquid cooling, due to arrive in the second half of 2027 and be operational by the end of 2027, funded by the federal research ministry (through the Gauss Centre) and Baden-Wurttemberg. HLRS gives the architecture and schedule and promises more than seven times Hunter's performance; heise reports 1,488 MI430X GPUs and 372 Venice CPUs (two CPUs and eight GPUs per node), 432 GB HBM4 per GPU, at least 340 PFlop/s FP64 and about EUR 100 million. The counts and peak rest on heise alone, so the tier is reported and no FLOPS are recorded for a machine not yet built.

Timeline

No dated events recorded.

Site & facility

HLRS, University of Stuttgart

Location: Stuttgart, Germany
Cooling: Direct liquid cooling
Commissioned: 1996

hlrs.de

Change history

2026-10-02 Added Herder, HLRS's planned MI430X system

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
heise.de	names system, part and count	AMD Instinct MI430X · counts: 1488
hlrs.de	names system and part	AMD Instinct MI430X

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