PRACE looks at ClearSpeed

Print Friendly, PDF & Email

PRACE, the Partnership for Advanced Computing in Europe, sent me news via email about a PR they just issued covering some of the prototypes they have been evaluating in their continuing quest to catalogue, test, and document the known HPC universe.

PRACE is a press machine, so a release from them isn’t remarkable. What I thought was interesting was that the technology they chose to highlight features ClearSpeed quite prominently in the list of systems they’ve been looking at

  • CINES and LRZ have jointly evaluated a hybrid system architecture containing thin nodes, fat nodes and compute accelerators within a shared file system with components from SGI and ClearSpeed/PetaPath.
  • FZJ has extended the communication capabilities of their Cell-based QPACE system to estimate its suitability for a wider range of applications. This enhancement allowed running Linpack on the full system which made it no.1 on the Green500 list of energy-efficient supercomputers.
  • NCF has assessed a system composed of ClearSpeed/PetaPath accelerator boards together with the ClearSpeed programming language Cn.

Also, the software list features a lot of software aimed at managing CPU/accelerator programming of various types (including GPUs and FPGAs).

Honestly, I’d sort of stopped following ClearSpeed since they were eclipsed by NVIDIA. Good to know they are still out there plugging away. Diversity is good.