tag:blogger.com,1999:blog-1015214236289077798.post4371133645105546707..comments2024-03-24T17:13:53.855-07:00Comments on TenFourFox Development: I am the world's biggest liarClassicHasClasshttp://www.blogger.com/profile/17331846076856918359noreply@blogger.comBlogger10125tag:blogger.com,1999:blog-1015214236289077798.post-43843926844525601702011-07-16T04:21:08.214-07:002011-07-16T04:21:08.214-07:00Great !!
Hence the power of opensource software,;)...Great !!<br />Hence the power of opensource software,;)<br />We just need bright minds!Kiranhttps://www.blogger.com/profile/11121202875557117011noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-61376126089172365182011-04-21T04:18:00.608-07:002011-04-21T04:18:00.608-07:00Just in case you hadn't run into this yet: the...Just in case you hadn't run into this yet: there's example code by Apple for Altivec-accelerated DCTs at http://developer.apple.com/hardwaredrivers/ve/examples.htmlJonas Maebehttps://www.blogger.com/profile/02458193496621283799noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-42196444841720872782011-04-15T06:15:44.905-07:002011-04-15T06:15:44.905-07:00IPC for TenFourFox is a different problem than Lin...IPC for TenFourFox is a different problem than Linux -- Linux lacks the intrinsics for PPC, but can compile everything else (the patch you reference indeed has the missing intrinsics). TenFourFox is on Mac OS X, so we have the intrinsics, but there are other 10.5-specific library functions that have to be rewritten for 10.4. I've done this before, but it's never been tested.<br /><br />I finished the compiles yesterday, but video on my iBook G4/1.33 is still choppier than I would like, so I'm doing some rebuilds with adjusted buffering. It plays now on the 1.33, but skips a lot of frames. The G5 is just fine, of course.ClassicHasClasshttps://www.blogger.com/profile/17331846076856918359noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-73124887930312363002011-04-15T03:55:20.881-07:002011-04-15T03:55:20.881-07:00yeah!! Great news again, thanks a lot!!
Anyway wh...yeah!! Great news again, thanks a lot!!<br /><br />Anyway what about IPC support on PPC too?<br />here there is a first patch from an ArchlinuxPPC developer:<br />http://bugs.gentoo.org/show_bug.cgi?id=325185Nellohttps://www.blogger.com/profile/11091919423941692083noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-65382092752798724772011-04-14T14:05:35.594-07:002011-04-14T14:05:35.594-07:001.2 is in fact in Mozilla 2.0 (see media/libtheora...1.2 is in fact in Mozilla 2.0 (see media/libtheora/README). Yes, I agree that oc_frag_recon_inter2?_c are pretty straightforward vector conversions. I'll look at this when I get a free chance (possibly for 4.0.2pre), but I always accept patches, hint hint :)ClassicHasClasshttps://www.blogger.com/profile/17331846076856918359noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-1018878843947215922011-04-14T13:46:57.352-07:002011-04-14T13:46:57.352-07:00Okay; wrt VP3 (Theora) -- libtheora 1.2 (not-yet-r...Okay; wrt VP3 (Theora) -- libtheora 1.2 (not-yet-released) clocks in at ~10% faster than 1.1 on my Powerbook, so its perhaps a good step if you can move to it.<br /><br />For Altivec support for VP3, when run standalone (actually via the Xiph QT components :)), Theora (1.2 as of last summer) spends ~30% of its CPU time in oc_frag_recon_inter2 and oc_frag_recon_inter, which would be fairly trivial to vectorize; (these two checked in at #2 and #3, after the loop filter on a neat stop motion plant video).<br /><br />Also, the original VP3 code has some (fairly messy) code you can start from: http://svn.xiph.org/trunk/vp32/CoreLibs/CDXV/Vp31/Common/mac/OptFunctionsPPC.c ; no idea on how good they are.Unknownhttps://www.blogger.com/profile/00784154965730982563noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-8464843731303100372011-04-14T12:47:51.684-07:002011-04-14T12:47:51.684-07:00Venkatesh, yes, I looked at some other places that...Venkatesh, yes, I looked at some other places that VMX/AltiVec could be pref'ed on (and in fact there is one more that I'll announce with the beta, which if I can get it certified will probably be out tomorrow evening PST). The problem with the liboggplay code in the Mozilla 1.9.2 tree is that it actually doesn't accelerate anything even if AltiVec mode is requested; it's still using the vanilla converters (see oggplay_yuv2rgb.c and look for ENABLE_ALTIVEC). And of course liboggplay is gone from Mozilla 2.0. So I'm still investigating AltiVec VP3, but I'm sticking with the wins I know I can get first. Eventually I'd like to have as much of the content decoding AltiVec-accelerated as possible, but that's another story for another day.<br /><br />W/r/t building an accelerated graphics stack for TenFourFox in 10.5, I can't advise you there because I don't run 10.5 -- that's another reason why TenFourFox is 10.4, because I need it myself. In fact, I don't own a PowerPC that runs 10.5 at all. If someone manages to get this working, I will be happy to accept their changeset as long as it doesn't interfere with 10.4. I won't be able to run off such builds myself, however, so that would always remain a custom option.ClassicHasClasshttps://www.blogger.com/profile/17331846076856918359noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-59139227745231360512011-04-14T12:14:45.847-07:002011-04-14T12:14:45.847-07:00Cool! ;
If you're interested in Altivec supp...Cool! ; <br /><br />If you're interested in Altivec support for YUV->RGB conversion, the OggPlay code in Firefox 3.6 had (disabled) Altivec YUV->RGB code. Perhaps it'd be straightforward to adapt to the Chromium-based code in FF4.<br /><br />Also, could you share a bit about how to build a TenFourFox for 10.5 (:)) with an accelerated graphics stack, whatever that means? <br /><br />Thanks,<br />-- vsUnknownhttps://www.blogger.com/profile/00784154965730982563noreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-52760229119688279562011-04-14T03:37:14.984-07:002011-04-14T03:37:14.984-07:00Looking forward to testing WebM performance.
Keep ...Looking forward to testing WebM performance.<br />Keep on lying!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-1015214236289077798.post-88044510208758917152011-04-13T13:40:43.844-07:002011-04-13T13:40:43.844-07:00WooHoo! Great News. Keep up the good work!WooHoo! Great News. Keep up the good work!Unknownhttps://www.blogger.com/profile/04243784654946857340noreply@blogger.com