Can GPGPU Programming Be Liberated from the Data-Parallel Bottleneck?

With the growth in transistor counts in modern hardware, heterogeneous systems are becoming commonplace. Core counts are increasing such that GPU and CPU designs are reaching deep into the tens of cores. For performance reasons, different cores in a heterogeneous platform follow different design cho...

Full description

Saved in:

Bibliographic Details
Published in:	Computer (Long Beach, Calif.) Vol. 45; no. 8; pp. 42 - 52
Main Authors:	Gaster, Benedict R., Howes, Lee
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.08.2012 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Bottlenecks braided parallelism Braiding Circuits Computer graphics Computer programming Computer simulation data-parallel execution distributed arrays Flexibility GPGPU programming Graphics processing unit Hardware heterogeneous parallel primitives Indexes massively threaded computing systems Mathematical models Multithreading Parellel processing Performance evaluation persistent threading Programming
ISSN:	0018-9162, 1558-0814
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!