This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Compilers for Instruction-Level Parallelism
December 1997 (vol. 30 no. 12)
pp. 63-69

Instruction-level parallelism allows a sequence of instructions derived from a sequential program to be parallelized for execution on multiple pipelined functional units. If industry acceptance is a measure of importance, ILP has blossomed. It now profoundly influences the design of almost all leading-edge microprocessors and their compilers.

ILP's key advantage is that it exploits parallelism without requiring the programmer to rewrite existing applications. This is attractive because today's applications are still programmed sequentially, and many will never be rewritten.

Exploiting ILP across a diverse set of performance-critical applications will require renewed emphasis on the role of the compiler. To advance, ILP compilers will require an enormous research effort, much like the one that drove vector compilers to today's relatively mature status. Thus far, however, ILP has yet to receive a similar investment, even though it presents what may be even more complex technical challenges. A number of ILP compilers exist both in academia and in industry, yet the development of ILP is far from complete.

Citation:
Michael Schlansker, Thomas M. Conte, James Dehnert, Kemal Ebcioglu, Jesse Z. Fang, Carol L. Thompson, "Compilers for Instruction-Level Parallelism," Computer, vol. 30, no. 12, pp. 63-69, Dec. 1997, doi:10.1109/2.642817
Usage of this product signifies your acceptance of the Terms of Use.