Genius#
Note
Genius is a KU Leuven/UHasselt Tier-2 cluster which is still in operation, but most of its hardware has already been decommissioned. This page is only for possible future reference.
Hardware details#
thin nodes
86 Skylake nodes
2 Xeon Gold 6140 CPUs@2.3 GHz (Skylake), 18 cores each
(1 NUMA domain and 1 L3 cache per CPU)192 GiB RAM (memory bandwidth and latency measurements)
200 GB SSD local disk
partition
batch|batch_longandinteractive
144 Cascadelake nodes
2 Xeon Gold 6240 CPUs@2.6 GHz (Cascadelake), 18 cores each
(1 NUMA domain and 1 L3 cache per CPU)192 GiB RAM (memory bandwidth and latency measurements)
default memory per core is 5000 MiB
200 GB SSD local disk
partition
batch|batch_long
4 Naples AMD nodes
2 EPYC 7501 CPUs@2.0 GHz, 32 cores each
(4 NUMA domains and 8 L3 caches per CPU)256 GiB RAM
200 GB SSD local disk
partition
amd
10 big memory nodes
2 Xeon Gold 6140 CPUs@2.3 GHz (Skylake), 18 cores each
(1 NUMA domain and 1 L3 cache per CPU)768 GiB RAM
default memory per core is 21000 MiB
200 GB SSD local disk
partition
bigmem|bigmem_long
1 huge memory node
Superdome8 Xeon Gold 6132 CPUs@2.6 GHz (Skylake), 14 cores each
6 TiB RAM
default memory per core is 53500 MiB
partition
superdome|superdome_long
6 GPU nodes, 24 GPU devices
6 P100 nodes
2 Xeon Gold 6140 CPUs@2.3 GHz (Skylake), 18 cores each
(1 NUMA domain and 1 L3 cache per CPU)192 GiB RAM
default memory per core is 5000 MiB
4 NVIDIA P100 SXM2@1.3 GHz, 16 GiB GDDR, connected with NVLink
200 GB SSD local disk
partition
gpu_p100|gpu_p100_long
The nodes were connected using an Infiniband EDR network (bandwidth 25 Gb/s). The islands are indicated on the diagram below.