Re: compiling for parallel machines

Your suspicion about software rather than hardware being the challenge in
parallel programming systems may be correct.


I am working on high level programming languages & systems for SIMD machines
(I have the Connection Machine in mind).


References:


"Partitioning and Scheduling parallel programs for multiprocessors"
Vivek Sarkar, MIT press 1989.
--based on his Ph.D thesis (1987).




"Optimizing Supercompilers for supercomputers"
Michael Wolfe, MIT press 1989.
--deals with dependence analysis etc.




IEEE Software July 1989 - is a special issue on Parallel Programming
environments and languages.


The state of the art in parallel languages is rather poor. The languages are
too low level - puts more burden on the programmer and the excessive detail
the programmer specifies prevents program optimizations; portability is out
of the question.


There has been quite a bit of work on Parallel programming environments.
Doesn't look very elegant most of the time.


Could you send me any other info you get. Hope you find this useful.


Thanks
--Deb
[From deb@quimby.dartmouth.edu (Deb Banerjee)]

Return to the comp.compilers page.
Search the comp.compilers archives again.