News
DealsCorvex agrees USD 103 million take-or-pay deal to perform AI inference with Mid-Atlantic GPUsSovereignNeysa scales AI infrastructure in India with AMD Instinct MI350X GPUs on TytanSovereignNeysa Deploys AMD GPU Cluster in Mumbai for AI Training and InferenceInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersDataOne and Rowan University sign engineering co-op program agreement for DataOne's Vineland AI factoryClustersLook inside Cal Poly's $3 million AI Factory (Video)DealsOpenAI Taps AMD Chips for 457 MW of AI Capacity in Six-Year TensorWave DealClustersCal Poly launches an AI data center on campus. Take a look insideInferenceArista takes aim at the next AI network battleground: distributed inferenceDealsOpenAI Signs 457 MW AI Data Center Deal as AMD Expands Its Challenge to NvidiaDealsCorvex agrees USD 103 million take-or-pay deal to perform AI inference with Mid-Atlantic GPUsSovereignNeysa scales AI infrastructure in India with AMD Instinct MI350X GPUs on TytanSovereignNeysa Deploys AMD GPU Cluster in Mumbai for AI Training and InferenceInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersDataOne and Rowan University sign engineering co-op program agreement for DataOne's Vineland AI factoryClustersLook inside Cal Poly's $3 million AI Factory (Video)DealsOpenAI Taps AMD Chips for 457 MW of AI Capacity in Six-Year TensorWave DealClustersCal Poly launches an AI data center on campus. Take a look insideInferenceArista takes aim at the next AI network battleground: distributed inferenceDealsOpenAI Signs 457 MW AI Data Center Deal as AMD Expands Its Challenge to Nvidia
EveryNeocloud
Swiss National Supercomputing Centre

Swiss National Supercomputing Centre

Switzerland's national high-performance computing centre, run by ETH Zurich in Lugano.

The Swiss National Supercomputing Centre (CSCS) is Switzerland's national high-performance computing centre, founded in Manno in 1991 and based in Lugano-Cornaredo since March 2012. It runs supercomputers as a national user lab for Swiss research and operates dedicated systems for weather forecasting and other national tasks.

Share on WhatsApp

  • Founded in Manno in 1991; moved to Lugano-Cornaredo in March 2012
  • Machine hall of 2,000 m2 with up to 27 MW of power
  • Cooling water drawn from Lake Lugano at 45 m depth, pumped 2.8 km
  • PUE below 1.25
  • Runs MeteoSwiss weather prediction since 2001

What it is

The Swiss National Supercomputing Centre, known as CSCS, is the national high-performance computing centre of Switzerland. It is an autonomous unit of ETH Zurich and works closely with the University of Lugano. Its main role is a National User Lab: Swiss researchers and their assistants can apply for free access to the centre's supercomputers through a competitive scientific review. CSCS also runs dedicated machines for research projects and national duties, including numerical weather prediction. It acts as the country's competence centre for high-performance computing and as a technology platform for computational science. Around 120 staff work there, and the annual budget is 24.3 million CHF.

How it came about

CSCS was set up in Manno, in canton Ticino, in 1991. It stayed there until March 2012, when it moved into a purpose-built site at Lugano-Cornaredo. Procurement ran in two phases. From 1991 to 2011 the centre chose proven technology so users could get to work easily, and that period was built around NEC's SX vector processors. The IBM SP4, installed in 2002, was its first production machine with a massively parallel design. Buying the first Cray XT3 in Europe, in 2005, opened a second phase in which CSCS prefers early technology, often before it is a general product.

The compute

CSCS runs a pool of national supercomputers used for both heavy calculation and the analysis of complex data. Machine names are usually taken from peaks in the Swiss Alps. The centre's history spans NEC SX vector systems, the IBM SP4 from 2002, and the Cray XT3 from 2005. For cooling, water is drawn from Lake Lugano at a depth of 45 metres and pumped 2.8 kilometres to the building, which keeps the cooling load low and gives a PUE below 1.25. PUE is the ratio of a data centre's total power draw to the power reaching the computers. CSCS also scouts new technology and publishes its findings as white papers.

Where the GPUs are

The Lugano-Cornaredo building, occupied from March 2012, has a pillar-free machine hall of 2,000 square metres and can draw up to 27 MW of electricity. Cooling water comes from Lake Lugano, taken 45 metres down and moved 2.8 kilometres to the centre. The earlier home of the centre was Manno, in canton Ticino. CSCS works closely with the University of Lugano, and in 2009 the two launched HP2C, a platform to ready Swiss research codes for future machine designs.

Swiss National Supercomputing
A drawing made by EveryNeocloud from what this page says. It is a diagram, not a picture of the real provider.

Customers and deals

Access to the national machines is open to researchers in and outside Switzerland through the user lab. Since 2001 CSCS has carried out the numerical weather prediction work of MeteoSwiss, the Swiss meteorological service. In January 2008 an operational high-resolution weather forecasting suite, the first of its kind in Europe, went into production on a massively parallel machine there. CSCS also runs the Swiss tier-2 cluster for the computing grid of the CERN LHC accelerator, and holds large data sets for SystemsX and ETH Zurich's C2SM.

Money and ownership

The centre's budget is 24.3 million CHF. It is an autonomous unit of ETH Zurich, the Swiss Federal Institute of Technology in Zurich, and employs about 120 people.

Its place in AI

CSCS is Switzerland's national competence centre for high-performance computing and a platform for computational science in the country. Its systems support work from pure calculation to large-scale data analysis. In September 2025 researchers from EPFL, ETH Zurich and CSCS released Apertus, a fully open-source, multilingual large language model.

Questions and criticism

The Lugano-Cornaredo site can draw up to 27 MW of electricity, and the centre draws its cooling water from Lake Lugano. Its design keeps cooling energy low, with a PUE under 1.25.

Questions people ask about Swiss National Supercomputing Centre

What is CSCS?

It is the Swiss National Supercomputing Centre, the country's national high-performance computing centre. An autonomous unit of ETH Zurich, it runs supercomputers for Swiss research and for national tasks such as weather forecasting. It has been based in Lugano-Cornaredo since March 2012.

Who can use its computers?

Swiss researchers and their assistants can apply for free access through a competitive scientific evaluation process, under the National User Lab scheme. The wider user lab is open to researchers in and outside Switzerland, who use the national high-performance computing infrastructure for calculation and data analysis.

What else does it run besides the user lab machines?

CSCS operates dedicated resources for strategic projects and national duties. Since 2001 it has done the numerical weather prediction for MeteoSwiss, and it runs the Swiss tier-2 cluster for the CERN LHC computing grid. It also stores large data sets for SystemsX and C2SM at ETH Zurich.

How is the building cooled?

Water is taken from Lake Lugano at a depth of 45 metres and pumped 2.8 kilometres to the centre. This keeps the energy spent on cooling low, and the site reports a PUE under 1.25. The machine hall covers 2,000 square metres without pillars and can draw up to 27 MW.

Good reading and sources

Where this page comes from

The facts on this page come from the Wikipedia article "Swiss National Supercomputing Centre", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryNeocloud rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.

It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the provider of the day, new pages on EveryNeocloud, and the conferences and anniversaries of the week ahead.