Table 1 Hardware configuration of the different platforms used. Cluster information is given on a per node basis.

From: Metadata practices for simulation workflows

System

CPU

GPU

Laptop

Intel Core i7-12800H vPro, 14 cores (6 P-cores + 8 E-cores), P-core 4.8GHz / E-core 3.7GHz

NVIDIA RTX 3070 Ti Mobile2, 1410 MHz, 8 GB GDDR6, 5888 CUDA cores

JUSUF cluster

2 × AMD EPYC 7742, 2 × 64 cores, 2.25 GHz

NVIDIA V1001, 1530 MHz, 16 GB HBM2e, 5120 CUDA cores

JURECA-DC cluster

2 × AMD EPYC 7742, 2 × 64 cores, 2.25 GHz

NVIDIA A1002, 1410 MHz, 40 GB HBM2e, 6912 CUDA cores

Workstation

Intel Core i9-10940X, 14 cores, 3.30 GHz

NVIDIA RTX 40903, 2520 MHz, 24 GB GDDR6X, 16384 CUDA cores

  1. 1Volta architecture: https://developer.nvidia.com/blog/inside-volta, last access: 25 June 2024.
  2. 2Ampere architecture: https://developer.nvidia.com/blog/nvidia-ampere-architecture-in-depth, last access: 25 June 2024.
  3. 3Ada Lovelace architecture: https://www.nvidia.com/en-us/technologies/ada-architecture/, last access: 25 June 2024.
Back to article page