Advanced

OpenPOWER GPU-enabled architecture performance enhancement using the Engineering and Scientific Subroutine Library (ESSL) drop-in acceleration

Posted by bob on
IBM developerWorks : Linux		Mail this story
Print this story

This article illustrates the methodology to offload the part of computations to GPU without refactoring the applications. The Crossroads/NERSC-9 Memory Bandwidth benchmark is used to showcase the offload of dense matrix multiplication (DGEMM) computations on GPU by linking (compile time) the newer version of CUDA-enabled ESSL (IBM Scientific Library). The use of CUDA-enabled ESSL gives approximately six times performance gain over CPU-only code.

Full Story

  Nav
» Read more about: Groups: IBM, Linux; Story Type: News Story

» Get new stories by e-mail: nightly or as they are published

« Return to the newswire homepage

  Related stories
» More like this

This topic does not have any threads posted yet!

You cannot post until you login.