- Infos im HLRS Wiki sind nicht rechtsverbindlich und ohne Gewähr -
- Information contained in the HLRS Wiki is not legally binding and HLRS is not responsible for any damages that might result from its use -

HPE Hawk

From HLRS Platforms
Revision as of 19:01, 24 October 2019 by Hpcbjdic (talk | contribs)
Jump to navigationJump to search

Hawk is the next generation HPC system at HLRS. It will replace the existing HazelHen system. The installation is planed to take place in Q4 2019. For more detailed information see the Hawk installation schedule.

This Page is under construction!

IMPORTANT: In case you do system calls from within your code (e.g. executing stuff in a shell), please do not run it with HPE MPI (aka MPT) on Naples nodes!!!

Best Practises for Software Installation

Best practices for software installation on Hawk is described on a separate (internal) wiki page Software Installation on Hawk.

Access

Login-Node: hawk-tds-login1.hww.hlrs.de

Note: Access to the Hawk TDS is possible now on request. In case you have early access, we ask you to provide us with your experience regarding usage and performance (approximately have a page) once a month.


Batch System

Batch System PBSPro (Hawk)


Compiler

Compiler (Hawk)


MPI

In order to use the MPI implementation provided by HPE, please load the Message Passing Toolkit (MPT) module mpt (not ABI-compatible to other MPI implementations) or hmpt (ABI-compatible to MPICH-derivatives). For detailed information see the HPE Message Passing Interface (MPI) User Guide. Furthermore, please us the compiler wrappers mpif77 / mpif90 / mpif08 / mpicc / mpicxx.


Libraries

The following libraries are available via the module numlib/aocl/2.0. They are optimized to utilize AMD EPYC processors in an optimal way.

  • BLIS (AMD-BLAS)
  • BLIS-mt (AMD-BLAS multi-threaded version)
  • FFTW
  • FLAME (AMD-LAPACK)
  • libm
  • rng (random number generator)


Tutorial slides

Tutorial Slides from HLRS Results & Review Workshop 2019