JUWELS

JUWELS is located at Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich, Germany.

 

JUWELS is the successor system of JUQUEEN. JUWELS will be a modular supercomputer, like JURECA. The cluster module is in operation since mid July 2018, and it will be complemented by a booster module.

How to get access to JUWELS

JUWELS Cluster Module

  • 122,448 CPU cores
  • 10.4 (CPU) + 1.6 (GPU) Petaflop per second peak performance
2271 standard compute nodes – Dual Intel Xeon Platinum 8168
  • 2x 24 cores, 2.7 GHz
  • 12x 8 GB, 2666 MHz
  • EDR-Infiniband (Connect-X4)
  • diskless
240 large memory compute nodes – Dual Intel Xeon Platinum 8168
  • 2x 24 cores, 2.7 GHz
  • 12x 16 GB, 2666 MHz
  • EDR-Infiniband (Connect-X4)
  • diskless
48 accelerated compute nodes – Dual Intel Xeon Gold 6148
  • 2x 20 cores, 2.4 GHz
  • 12x 16 GB, 2666MHz
  • Dual EDR-Infiniband (Connect-X4)
  • diskless
  • 4x Nvidia V100 GPU
4 visualisation nodes – Dual Intel Xeon Gold 6148
  • 2x 20 cores, 2,4 GHz
  • 12x 64 GB, 2666 MHz
  • EDR-Infiniband (Connect-X5)
  • 100 GigE
  • 2x 1TB HDD (Raid 1)
  • 1x Nvidia Pascal P100
12 login nodes – Dual Intel Xeon Gold 6148
  • 2x 20 cores, 2.4 GHz
  • 12x 64 GB, 2666MHz
  • EDR-Infiniband (Connect-X5)
  • 100 GigE
  • 2x 1TB HDD (Raid 1)
Job scheduler SLURM
More information http://www.fz-juelich.de/ias/jsc/juwels
Contact HBP-HPC-Platform@fz-juelich.de