Author: Robert Hyatt
Date: 09:12:42 09/30/02
Go up one level in this thread
On September 30, 2002 at 04:17:26, Vincent Diepeveen wrote: >On September 29, 2002 at 23:31:36, Robert Hyatt wrote: > >Comon you haven't even installed gcc 3.1, >last time we chatted (some months ago), i already >months before that told you about gcc 3.1 and you >still were in the 2.95 times... No. Once again, that is _your_ misunderstanding or whatever. I clearly said "I have tried _all_ versions of GCC that have been released to date. And so far, the old 2.95.2 version _still_ produces the fastest code for Crafty. In fact, recent versions of the compiler crash crafty totally when I try to use any reasonable optimizations." You _assume_ too much, when all you have to do is ask. We've even got recent gcc versions on our sparcs and _they_ also break crafty... However, I haven't been using gcc 2.95 since intel's compiler is significantly faster in code produced. Although I do compare from time to time to catch any significant jumps from the gcc folks. Right now they have badly broken the long long stuff... > >>On September 29, 2002 at 11:31:35, Vincent Diepeveen wrote: >> >>>On September 28, 2002 at 11:12:29, Tom Likens wrote: >>> >>>For DIEP the gcc 3.1 compiler and further produce way >>>faster code based upon enabling profiling. the 3.1+ >>>gcc versions profit more from it than intel does. >>> >>>At a P3 even the gcc compiler is not measurable faster much, >>>but the real difference happens on the k7. It seems to me >>>that the intel guys of course didn't improve their compiler >>>for the AMD processor. Instead it's only optimized for P4. >>>Not even for P3 they achieve the best possible results, >>>as GCC proves. >> >>I don't know what this means. I have several dozen programs (Crafty >>is only one) that we have run using intel's compiler and gcc, and in >>_every_ case, Intel's compiler is faster. On P2's, on P3's and on >>P4's... Of course I wouldn't use intel's compiler for an AMD chip, >>why would they want to optimize for a competitor's chip??? >> >> >> >>> >>>I am under the impression that gcc simply is so fast for >>>me simply because of better profiling capabilities. >>> >>>It increases speed by over 20%. >>> >>>>On September 27, 2002 at 23:37:43, Robert Hyatt wrote: >>>> >>>>[snip!] >>>> >>>>>>>>So reality is that the above result in reality is even more positive for >>>>>>>>AMD than it looks like. We simply cannot trust these intel c++ compiles. >>>>>>> >>>>>>>Sure you can. I have tested the 6.0 release of their compiler exhaustively, >>>>>>>comparing various optimizations with a known good executable from gcc 2.95.2, >>>>>>>and the intel compiler is producing perfect code from a comparison of the >>>>>>>two... >>>> >>>>Actually, in my tests it's producing *significantly* faster code (especially, if >>>>you use the profile-enabled optimizations). >>>> >>>>regards, >>>>--tom
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.