“Think about your social media connections: there may be millions of people represented in a matrix, but your row-the people who influence you-are few. “The world is really sparse at large sizes,” said Heroux. The term “sparse” means that a matrix under consideration has mostly zero values. Today’s applications often use sparse data structures, and computations are leaner.” “The LINPACK program performs compute-rich algorithms on dense data structures to identify the theoretical maximum speed of a supercomputer. “The LINPACK program used to represent a broad spectrum of the core computations that needed to be performed, but things have changed,” said Sandia researcher Mike Heroux, who created and developed the HPCG program.
#Linpack benchmark superocmputers full
The program’s full name-High Performance Conjugate Gradients, or HPCG-doesn’t come trippingly to the tongue, but word is seeping out that this relatively new benchmarking program is becoming as valuable as its venerable partner-the High Performance LINPACK program-which some say has become less than satisfactory in measuring many of today’s computational challenges.
#Linpack benchmark superocmputers software
(Credit: Sandia National Laboratories)Ī Sandia National Laboratories software program now installed as an additional test for the widely observed TOP500 supercomputer challenge has become increasingly prominent. The rearranged order and drastic reduction in estimated speed for the HPCG benchmarks are the result of a different method of testing modern supercomputer programs.
TOP500 LINPACK and HPCG charts of the fastest supercomputers of 2017.
0 kommentar(er)
