We found that just simply using Intel's compiler provides an average of 30% gain on our utilities programmed in C. We even recompiled Sqlite and got the same enhancements. I maintain that recompiling J with the Intel compiler should at least be tried. Roger won't touch any idiom if he can't at least double the performance. I would be curious to see how much "overall" performamce gain can be had with tuned idioms compared with 30% across the board. I suspect that if we were to have J recompiled with the Intel compiler, the developpers of J would then discover many other possibilities offered in that compiler that could be then applied to idioms.
Skip Cave wrote: > ... > > Intel has expended significant efforts designing tools to help take advantage > of their multi-core processors. See: http://tinyurl.com/cwd7ud > It would be interesting to see what effect Intel's latest concurrent compiler > would have on J's interpreter. However, I expect that making a significant > portion of J's primitives "concurrent-aware" will require considerably more > than just a simple compiler change. I like Roger's rule that if a change to > the interpreter can't improve the processing speed or memory usage > significantly, it shouldn't be done. That should be the criteria for all > concurrent modifications to J's interpreter. ... ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
