GPU servers and parallel hardware at RGNC

Contents




1. GPU Servers

We currently hold four GPU computing servers, named after the four highest peaks in Spain: Teide (3715m, Canary Islands), Mulhacen (3479m, Granada), Aneto (3404m, Huesca), Veleta (3396m, Granada).

Note: We are continuously working on the configuration of the servers, so more libraries are going to be installed soon...


Teide:

  • Supermicro (A+ SuperWorkstation 5014A-TT)
  • CPU: 16 cores (1-socket 16-core 32-Threads) AMD(R) Ryzen Threadripper(TM) PRO 3955WX CPU @ 3.90GHz
  • Main memory: 32 GBytes DDRR4 @ 3200 MHz
  • Disk memory: 480GB SSD for /, 2TB HDD for /data (please, store here your datasets)
  • GPUs:
    • 2 x NVIDIA RTX3090 - 10496 cores (82 SMs x 128 SPs) @ 1.775Ghz, 24 GBytes GDDR6 (provided by our R&D project MABICAP and INVASORAS)
    • CUDA 12.1
  • Operating system: Rocky Linux 9
  • Software libraries through CernVM-FS


Mulhacen:

  • Even gaming
  • CPU: 8 cores (2-socket 4-core) Intel(R) Core(TM) i7-9700K CPU @ 3.60GHz
  • Main memory: 32 GBytes DDRR4 @ 2133 MHz
  • Disk memory: 354GB SSD for /home, 1TB HDD for /data (please, store here your datasets), 100GB SSD for /
  • GPUs:
    • 1x NVIDIA RTX2080 - 2944 cores (46 SMs x 64 SPs) @ 1.85Ghz, 8 GBytes GDDR5 (provided by our R&D project MABICAP)
    • 1x NVIDIA RTX3090 - 10496 cores (82 SMs x 128 SPs) @ 1.775Ghz, 24 GBytes GDDR6 (provided by our R&D project MABICAP and INVASORAS)
    • CUDA 12.1
  • Operating system: Rocky Linux 9
  • Software libraries through CernVM-FS


Aneto: (This server is down because of hardware problems)

  • Its GPUs and hard drives were moved to Veleta.


Veleta (login node):

  • Supermicro Server 7046GT-TRF
  • CPU: 8 cores (2-socket 4-core) Intel i5 Nehalem E5504 @ 2.00GHz
  • Main memory: 12 GBytes DDR3 @ 1333Mhz
  • Disk memory: 839GB HDD for /home, 102GB SSD for /
  • GPUs:
    • 1 x NVIDIA RTX2080 - 2944 cores (46 SMs x 64 SPs) @ 1.85Ghz, 8 GBytes GDDR5 (provided by our R&D project MABICAP)
    • 1 x NVIDIA Tesla K40c - 2880 cores (15 SMXs x 192 SPs) @ 0.88Ghz, 12 GBytes GDDR3 (provided by NVIDIA under the CUDA Research Center program)
    • 1 x NVIDIA GeForce GTX 780 Ti - 2880 cores (15 SMXs x 192 SPs) @ 0.93Ghz, 3 GBytes GDDR3 (provided by our R&D projects)
    • CUDA toolkit 11.8 / CUDA 11.4 driver (470) to support our Kepler GPUs
  • Operating system: Rocky Linux 9
  • Software libraries through CernVM-FS

Linux

CentOS

NVIDIA CUDA

CernVM File System

Slurm




2. CPU server


  • Supermicro Rack Platinum (RACK2XF-ADVANCE1)
  • CPU: Intel CLX 4208 2P 8C/16T 2.1G (16 cores, 32 threads)
  • Main memory: 4 x 32 (128) GBytes DDR4-2933 2Rx4 ECC REG DIMM
  • Disk memory: 2 x SSD 480GB SATA 6G/s V4 2.5", TOSHIBA 3.5" 2TB SATA 6GB/S 7.2K RPM 128M 512E
  • Provided by our R&D project INVASORAS

Linux

Ubuntu

NVIDIA CUDA

Slurm




3. GPU for mobility hardware


Jetson TX2 Development Kit:

  • GPU: NVIDIA Pascal GPU with 256 CUDA cores
  • CPUs: 64-bit NVIDIA Denver and ARM Cortex-A57
  • Main memory: 8GB LPDDR4
  • Provided by our R&D project MABICAP




4. Funding and Acknowledgments

The CPU server and an RTX3090 were provided by INVASORAS project: FEDER/Junta de Andalucía – Consejería de Transformación Económica, Industria, Conocimiento y Universidades/ _Proyecto (P20_00486).

Teide and Mulhacen GPU servers at RGNC were provided by MABICAP project: FEDER/Ministerio de Ciencia e Innovación – Agencia Estatal de Investigación/ _Proyecto (TIN2017-89842-P).


The Aneto GPU server at RGNC was provided by the R&D project TIN2012-37434 (funded by Ministerio de Economía y Competitividad of Gobierno de España), co-financed by the European FEDER funds. The Tesla K40c GPU was a donation by NVIDIA under the CUDA Research Center program.

The Veleta GPU server at RGNC was provided by the R&D projects P08-TIC4200 (funded by Consejería de Economía, Innovación y Ciencia of Junta de Andalucía) and TIN2009-13192 (funded by Ministerio de Ciencia e Innovación of Gobierno de España), both co-financed by the European FEDER funds.

Please, consider to acknowledge our R&D projects in your papers if you are using our GPU servers and hardware for your research (also notify us about this).