LEADER 03903nam  22006735  450 
001 9910298982703321
005 20230810213448.0
010   $a3-658-07597-X
024 7 $a10.1007/978-3-658-07597-2
035   $a(CKB)3710000000261943
035   $a(EBL)1965811
035   $a(OCoLC)905990053
035   $a(SSID)ssj0001372342
035   $a(PQKBManifestationID)11802167
035   $a(PQKBTitleCode)TC0001372342
035   $a(PQKBWorkID)11304274
035   $a(PQKB)10426243
035   $a(MiAaPQ)EBC1965811
035   $a(DE-He213)978-3-658-07597-2
035   $a(PPN)182095029
035   $a(EXLCZ)993710000000261943
100   $a20141009d2014      u|         0
101 0 $aeng
135   $aur|n|---|||||
181   $ctxt
182   $cc
183   $acr
200 10$aAlgorithmic Differentiation of Pragma-Defined Parallel Regions $eDifferentiating Computer Programs Containing OpenMP /$fby Michael Förster
205   $a1st ed. 2014.
210  1$aWiesbaden :$cSpringer Fachmedien Wiesbaden :$cImprint: Springer Vieweg,$d2014.
215   $a1 online resource (411 p.)
300   $a''Research''--Cover.
311   $a3-658-07596-1 
320   $aIncludes bibliographical references and index.
327   $aIntroduction with Examples from Numerical Optimization -- Algorithmic Differentiation by Source Transformation -- Transformation rules for Parallel Code Regions (e.g. OpenMP 3.1) -- Static Program Analysis.
330   $aNumerical programs often use parallel programming techniques such as OpenMP to compute the program's output values as efficient as possible. In addition, derivative values of these output values with respect to certain input values play a crucial role. To achieve code that computes not only the output values simultaneously but also the derivative values, this work introduces several source-to-source transformation rules. These rules are based on a technique called algorithmic differentiation. The main focus of this work lies on the important reverse mode of algorithmic differentiation. The inherent data-flow reversal of the reverse mode must be handled properly during the transformation. The first part of the work examines the transformations in a very general way since pragma-based parallel regions occur in many different kinds such as OpenMP, OpenACC, and Intel Phi. The second part describes the transformation rules of the most important OpenMP constructs. Contents Introduction with Examples from Numerical Optimization Algorithmic Differentiation by Source Transformation Transformation rules for Parallel Code Regions (e.g. OpenMP 3.1) Static Program Analysis Target Groups Lecturers and students of computer science Computer scientists, engineers, mathematicians and numerical analysts The Author Michael Förster is currently Research Associate of the Institute Software and Tools for Computational Engineering, RWTH Aachen University.
606   $aComputer science$xMathematics
606   $aArtificial intelligence
606   $aEngineering mathematics
606   $aEngineering$xData processing
606   $aMathematics of Computing
606   $aArtificial Intelligence
606   $aMathematical and Computational Engineering Applications
615  0$aComputer science$xMathematics.
615  0$aArtificial intelligence.
615  0$aEngineering mathematics.
615  0$aEngineering$xData processing.
615 14$aMathematics of Computing.
615 24$aArtificial Intelligence.
615 24$aMathematical and Computational Engineering Applications.
676   $a004
676   $a004.0151
676   $a006
676   $a519
700   $aFörster$b Michael$4aut$4http://id.loc.gov/vocabulary/relators/aut$0906921
906   $aBOOK
912   $a9910298982703321
996   $aAlgorithmic Differentiation of Pragma-Defined Parallel Regions$92028769
997   $aUNINA