Abstract
Automatic vectorization of loops by investigation of data access dependences is known from literature. But the algorithms almost only describe the vectorization of fully vectorizable loops. A loop is judged to be nonvectorizable, if some data access dependences form a cycle. However, practical programs often contain loops with cyclic data access dependences where not all variables are included in the cyclic dependence. If cyclic dependences can be isolated, variables not encountered in the cyclic dependence are vectorizable. Thus, in vectorizing compilers not only full loop vectorization but also partial vectorization should be done. Here, the code generation for partially vectorizable loops is described for the vectorizing Pascal-XT compiler. The effect is compared to the vectorizing Fortran compilers of CDC, Cray and Fujitsu.
Preview
Unable to display preview. Download preview PDF.
References
Vector Processor System. Siemens System 7.800 — System Description. Order no. U1889-J-Z62-2-7600 (1985).
Pascal-XT(BS2000/SINIX), Brief Description. Siemens. Order no. U2491-J-Z52-1-7600 (1985).
L. Lamport: The Parallel Execution of DO Loops. Communications of the ACM 17, 2 (1974), 83–93.
K.-C. Li: A Note on the Vector C Language. ACM SIGPLAN Notices 21 1(1986), 49–57.
H. Ehlich: PASCALV — Der PASCAL Compiler für den Vektorrechner CYBER205. Bochumer Schriften zur Parallelen Datenverarbeitung 5. RZ Ruhr Universität Bochum (1984).
S. Kamiya, F. Isobe, H. Takashima, M. Takiuchi: Practical Vectorization Techniques for the “FACOM VP”. Information Processing 83, R. Mason (ed.), Elsevier Science Publishers B. V. (North-Holland).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1986 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hammer, C., Raebel, G. (1986). Code generation for partially vectorizable loops in the vectorizing Pascal-XT compiler. In: Händler, W., Haupt, D., Jeltsch, R., Juling, W., Lange, O. (eds) CONPAR 86. CONPAR 1986. Lecture Notes in Computer Science, vol 237. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-16811-7_183
Download citation
DOI: https://doi.org/10.1007/3-540-16811-7_183
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-16811-9
Online ISBN: 978-3-540-44856-3
eBook Packages: Springer Book Archive