SNAC Large, Fall 2018


This round has already been decided by the committee and is not open for proposals.

More information about this round is available at


Resource Centre Total
Available Capacity Unit Note
Hebbe C3SE 1 245 600 x 1000 core-h/month
The Hebbe cluster is built on Intel Xeon E5-2650v3 (code-named "haswell") CPU's. The system has a total of 323 compute nodes (total of 6480 cores) with 27 TiB of RAM and 6 GPUs. More specific:
  • 260 x 64 GB of RAM (249 of these available for SNIC users)
  • 46 x 128 GB of RAM (31 of these available for SNIC users)
  • 7 x 256 GB of RAM (not available for SNIC users)
  • 3 x 512 GB of RAM (1 of these available for SNIC users)
  • 1 x 1024 GB of RAM
  • 4 x 64 GB of RAM and NVIDIA Tesla K40 GPU (2 of these available for SNIC users)
  • 2 x 256 GB of RAM and NVIDIA k4200 for remote graphics
Each node have 2 CPUs with 10 cores each. There's a 10Gigabit Ethernet network used for logins, and a dedicated management network and an Infiniband high-speed/low-latency network for parallel computations and filesystem access. The nodes are equipped with Mellanox ConnectX-3 FDR Infiniband 56Gbps HCA's.
Kebnekaise HPC2N 8 125 3 200 x 1000 core-h/month
Kebnekaise is a heterogeneous computing resource consisting of:


  1. Access to the Large Memory nodes are handled through the 'Kebnekaise Large Memory' resource.
  2. Note: It is important that requests for GPU nodes and KNL nodes are explicitly specified in the user's proposal. Also to note that the GPU nodes and the KNL nodes will be charged differently than ordinary computing nodes.
Kebnekaise Large Memory HPC2N 695 450 x 1000 core-h/month
This resource is for access to the 'Large Memory nodes' in Kebnekaise. For standard, GPU and KNL nodes see resource 'Kebnekaise'.

Kebnekaise is a heterogeneous computing resource consisting of:

Aurora Lunarc 600 500 x 1000 core-h/month
Was opened for test usage at the end of January 2016.
Tetralith NSC 24 620 14 500 x 1000 core-h/month
Tetralith,, runs a CentOS 7 version of the NSC Cluster Software Environment. This means that most things are very familiar to Triolith users. You still use Slurm (e.g sbatch, interactive, ...) to submit your jobs. ThinLinc is available on the login nodes. Applications are selected using "module". All Tetralith compute nodes have 32 CPU cores. There will be 1832 "thin" nodes with 96 GiB of primary memory (RAM) and 60 "fat" nodes with 384 GiB. Each compute node will have a local SSD disk where applications can store temporary files (approximately 200GB per node). All Tetralith nodes are interconnected with a 100 Gbps Intel Omni-Path network which is also used to connect the existing storage. The Omni-Path network works in a similar way to the FDR Infiniband network in Triolith (e.g with a fat-tree topology). The Tetralith installation will take place in two phases. The first phase consist of 644 nodes and have a capacity that exceeds the current computing capacity of Triolith. The first phase was made available to users on August 23, 2018. Triolith was turned off September 21, 2018. After this, the second phase of the Tetralith installation will begin. NSC plans to have the entire Tetralith in operation no later than December 31st (i.e for the next round of SNAC Large projects.)
Beskow PDC 20 764 11 200 x 1000 core-h/month
Tegner PDC 0 210 x 1000 core-h/month
Pre/post system for the beskow cluster. All approved Beskow allocation will get 1/60 of the beskow corehours on Tegner

Tegner is the pre/post processing cluster for Beskow
Crex 1 UPPMAX 20 000 1 000 000 GiB Storage resource attached to Rackham
Crex is the centre storage at UPPMAX, attached to the Rackham compute cluster. Proposals requesting Crex storage in SNAC LARGE must also include requests for compute resources totalling more the limits of SNAC MEDIUM (100 kch/month), at least part of which are on Rackham.

Active data storage for SNIC UPPMAX projects.
Rackham UPPMAX 1 100 1 000 x 1000 core-h/month
Rackham provides 9720 cores in the form of 486 nodes with two 10-core Intel Xeon V4 CPUs each. 4 fat nodes have 1 TB of memory, 32 fat nodes have 256 GB, and the rest have 128 GB. The interconnect is Infiniband.

Click the ▶ to show more information about the resource.