Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: crafty faster on AMD however

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.