Hi all Thought I'd broadcast this more widely in the hope of catching more Crunh-weary folks ;)
---------- Forwarded message ---------- From: Martin Guy <[email protected]> Date: Dec 18, 2008 2:39 PM Subject: Re: in at the deep end To: [email protected] Ok, I have working Maverick patches for gcc-4.3.2. Main differences from the Futaris 4.1.2 and 4.2.0 ones: - no negative impact on speed of regular ARM code - addition of -mieee flag for full IEEE precision at about half of full speed - generated floating point code is about 10% faster See martinwguy.co.uk/martin/crunch for patches, native compiler tarballs and description. While I've compiled and run testsuite of various real programs, the infamous "paranoia" IEEE conformance torture test when testing double precision, fails in bizarre ways (see above web page). This seems to be due to further undocumented subtle timing bugs in the silicon, which only "paranoia" is unlucky enough to tickle. Enjoy; feedback welcome M -- To UNSUBSCRIBE, email to [email protected] with a subject of "unsubscribe". Trouble? Contact [email protected]
