FatELF: universal binaries for Linux [LWN.net]

FatELF: universal binaries for Linux

Posted Nov 4, 2009 16:20 UTC (Wed) by Darkmere (subscriber, #53695)
Parent article: FatELF: universal binaries for Linux

For me, I do not think FatELF would solve the problems with regards to optimizations. Let us take the more "modern" architectures ( and disregard the need for "i686 without CMOV" ) we have things like Atom(ipia) vs. i686 where the two have vastly different behaviour wrt. performance. Right now we don't even know which way will be dominant in the future, but a fair guess would be to see that atom-like architectures become more common in the future, and I don't think the dynamic linker will be a good place for this kind of logic.

Then again, I also believe in link time optimization for gcc and the tooth fairy.

to post comments

FatELF: universal binaries for Linux

Posted Nov 5, 2009 18:16 UTC (Thu) by nix (subscriber, #2304) [Link] (3 responses)

Support for -ftooth-fairy was added to GCC a few weeks ago.

FatELF: universal binaries for Linux

Posted Nov 6, 2009 20:02 UTC (Fri) by Darkmere (subscriber, #53695) [Link] (2 responses)

Only things left are full system profile guided optimizations (Buildsystem issue I suspect) and working link time optimization (For things like firefox. -fwhole-program and similar are. interesting.)

FatELF: universal binaries for Linux

Posted Nov 6, 2009 20:36 UTC (Fri) by nix (subscriber, #2304) [Link] (1 responses)

Well, the point of -fwhopr is to make LTO optimizations practical even for
very large programs, without needing insane amounts of memory. So that's
been added too.

FatELF: universal binaries for Linux

Posted Nov 7, 2009 2:28 UTC (Sat) by Darkmere (subscriber, #53695) [Link]

Oh, seems they really did add my -ponies then!