Tag Archives: GPU

PGI Community Edition [free]

PGI Community Edition

PGI Community Edition includes a no-cost license to a recent release of the PGI Fortran, C and C++ compilers and tools for multicore CPUs and NVIDIA Tesla GPUs, including all OpenACC, OpenMP and CUDA Fortran features. The PGI Community Edition enables development of performance-portable HPC applications with uniform source code across the most widely used parallel processors and systems.

http://www.pgroup.com/products/community.htm 

 

module load pgi/2017

Compilers:

pgc
pgcc
pgc++
pgf77
pgf90
pgf95
etc...

OpenMPI for PGI compilers

module load pgi/mpi/1.10.2/2017

OR

module load pgi/mpi/2.1.2/2017

Then mpi versions of PGI compilers will be available as

mpicc, mpic++, mpif90, mpif77...

 

GPU stuff

k80

(“World fastest GPU accelerator” as per 2014 — http://images.nvidia.com/content/tesla/pdf/nvidia-tesla-k80-overview.pdf )

10 New Zeus HPC Broadwell-CPU based nodes have 10 x 2 Nvidia Tesla K80 GPU accelerators on board (2 per node). Theoretical performance of each K80 GPU in double precision is 2.91 TFlops (8.7 TFlop in single precision) , which gives theoretical GPU power of these nodes in order of 58 TFlop in double precision calculations.

18 Older Sandybridge CPU-based compute nodes of Zeus have 36 Nvidia Tesla K20 GPU accelerators (2 per node), each of K20 has max. theoretical performance of 1.2 TFlops (double precision), which gives overall max GPU compute power of 43 TFlop. Obviously this is just an indication of the amount of max. possible compute power at ideal scaling (realistically you can’t just add these numbers together).

In comparison HPL benchmark performed on CPUs of all new 56 Broadwell nodes (1792 CPU-cores) gave 34 Tflop and 1152 CPUs of older 8-Core Nehalem based nodes gave 9.5 TFlops. and 18 x 12-core Sandybridge CPUs produced about 3.6 TFlops. See details here: http://zeus.coventry.ac.uk/wordpress/?s=HPL

——

Alex

 

css.php