The difficulty with optimising for cache effects is that you're effectively
introducing sequential dependencies between elements of the array you're
processing.
To say this another way: If you can evaluate the array elements in any order
then you can evaluate them in parallel. Adding
Hi,
2010/7/13 Gregory Crosswhite gcr...@phys.washington.edu:
Just out of curiosity, what work is being done in the data parallel
haskell / repa projects regarding cache locality?
Hi,
I'm not knowledgeable at all about this, but for a technical
introduction to DPH, I found the following
Hey everyone,
Just out of curiosity, what work is being done in the data parallel
haskell / repa projects regarding cache locality? The reason I am
asking is because, as I understand it, the biggest bottleneck on today's
processors are cache misses, and the reason why optimized
platform-specific
