Activity Counter: New Optimization for the dynamic scheduling of SIMD Control Flow
- 1 August 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (01903918) , 184-187
- https://doi.org/10.1109/icpp.1993.36
Abstract
SIMD or vector computers and collection-oriented languages, like C*, are designed to perform the same computation on each data item or on just a subset of the data. Subsets of processors or data items implemented via an activiry bit and a stack of activity bits when subsets of subsets are supported. This method is also used in VLIW processors through if-conversion to implement paralalle1 control flow as in SIMD computers. Wt present a new method of dynamic scheduling of several SIMD control flow constructions which can be nested.Keywords
This publication has 6 references indexed in Scilit:
- Microarchitecture Support For Dynamic Scheduling Of Acyclic Task GraphsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Loop distribution with multiple exitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Loop distribution with arbitrary control flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Control structures for data-parallel SIMD languages: semantics and implementationFuture Generation Computer Systems, 1992
- POMP or how to design a massively parallel machine with small developmentsPublished by Springer Nature ,1991
- Conversion of control dependence to data dependencePublished by Association for Computing Machinery (ACM) ,1983