to allow a request to go to memory and back in one instruction time?Moreover suppose u have a large source program consisting of m files to compile.tha compilation is to take place on a system with n processors,where n>>m.the best u can hope for is an m-fold speedup over a single processor.What factors might cause the speedup to be less than this maximum?releated to distributed computing?
2007-01-25
23:23:07
·
2 answers
·
asked by
Anonymous
in
Computers & Internet
➔ Hardware
➔ Other - Hardware