Author: Robert Hyatt
Date: 08:10:41 08/07/03
Go up one level in this thread
On August 07, 2003 at 08:13:09, Vincent Diepeveen wrote: >Hello, > >exactly this i had noticed too. not the solution though. perhaps some of you >might get helped by it for your software in case you use intel c++: What does that have to do with "bugs"? >----------- >Name: redpriest (redpriest@alum.wpi.edu) 8/5/03 > >...but it isn't really. Sometimes it produces correct results. It just needs you >to look at the results and ensure they are correct, disable if necessary. >There is definite proof of what *can* happen. I built a ScienceMark binary and >the results were seemingly impressive.... until I checked the results. They were >completely incorrect. > >A possible issue here is that the Intel compiler has the /Op option OFF by >default. With this off, fp results are much faster but they lose precision and >generate weird errors further down the line. This happened to me. With /Op on, >the compiler was no faster than say, the MSVC 6.0 SP5 compiler with /Op on. > >/Op appears to be the *default* setting for the Microsoft compiler. /Op off >appears to be the *default* setting for the Intel C compiler. > >Also, some of those fp functions are ANSI C-compatible are broken when inlining >is enabled... > >It's not cheating but it's very misleading. ALWAYS, ALWAYS check the results >before getting too excited... > >David Kanter (dkanter@realworldtech.com) on 8/4/03 wrote: >--------------------------- >>There is no such proof there. We have person X saying that Intel's compiler deliberately >>uses imprecise representations. >> >>I do not see any examples; I would want to see multiple ones. Perhaps a program >>compiled with ICC that does such manipulations displaying the result at the end of each step. >> >>I have yet to see anything "proving" that Intel's compilers cheat. I have however >>heard several people say that it is not the best for some sorts of code. >> >>David >> >> >>Suki (323@yahoo.com) on 8/4/03 wrote: >>--------------------------- >>>Proof in this thread >>> >>>http://www.aceshardware.com/forum?read=105028264 >>
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.