Automatic parallelization: Difference between revisions

Revision as of 17:37, 2 May 2021

Revision as of 01:34, 19 September 2021

Line 1:

{{multiple issues|

{{Expert subject|Computer science|date=March 2011}}

{{Refimprove|date=February 2008}}

}}

'''Automatic parallelization''', also '''auto parallelization''', or '''autoparallelization''' refers to converting sequential [[source code|code]] into [[multi-threaded]] and/or [[Automatic vectorization|vectorized]] code in order to use multiple processors simultaneously in a shared-memory [[multiprocessor]] ([[Symmetric multiprocessing|SMP]]) machine.<ref>[http://u.cs.biu.ac.il/~wiseman/para2001.pdf "{{cite journal|last=Yehezkael|first=Rafael|title=Experiments in Separating Computational Algorithm from Program Distribution and Communication|journal=Lecture Notes in Computer Science of Springer Verlag |year=2000|volume=1947|pages=268–278|doi=10.1007/3-540-70734-4_32|series=Lecture Notes in Computer Science|isbn=978-3-540-41729-3}}"]</ref> Fully automatic parallelization of sequential programs is a challenge because it requires complex [[program analysis (computer science)|program analysis]] and the best approach may depend upon parameter values that are not known at compilation time.<ref name="pcworks">{{cite book | last = Fox | first = Geoffrey |author2=Roy Williams |author3=Paul Messina | title = Parallel Computing Works! | year = 1994 | publisher = Morgan Kaufmann | pages = 575, 593 | isbn = 978-1-55860-253-3 }}</ref>