Hi, I've ported liba52 0.7.4 to mplayer, integrating almost all the changes in liba52{_amd64,}_changes.diff; if someone is interested I'll send the patch in the next mail.
On Saturday, 07 January 2006 at 11:27, Emanuele Giaquinta wrote:
Hi,
I've ported liba52 0.7.4 to mplayer, integrating almost all the changes in liba52{_amd64,}_changes.diff; if someone is interested I'll send the patch in the next mail.
Please do, and tell us what didn't get integrated (since you said "almost all"). Regards, R. -- MPlayer RPMs maintainer: http://rpm.greysector.net/mplayer/ "I am Grey. I stand between the candle and the star. We are Grey. We stand between the darkness ... and the light." -- Delenn in Grey Council in Babylon 5:"Babylon Squared"
On 1/7/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
Please do, and tell us what didn't get integrated (since you said "almost all").
Apart from the changes already integrated upstream, I've not ported the ones to the non accelerated imdct in imdct.c (it has been totally rewritten). I've tested it succesfully with the accelerated resample/downmix/imdct on ppc/altivec and x86/mmx+sse. To test it create a new liba52 directory and do the following: 1) copy the following files verbatim from the liba52 directory in the mplayer tree: Makefile crc.c imdct_3dnow.h resample_altivec.c resample.c resample_c.c resample_mmx.c srfftp_3dnow.h srfftp.h 2) Apply the attached patches to libmpcodecs/ad_liba52.c and liba52/Makefile 3) Copy the following files from the a52dec-0.7.4.tar.gz tarball and apply liba52_changes.diff: a52.h a52_internal.h bit_allocate.c bitstream.c bitstream.h downmix.c imdct.c mm_accel.h parse.c tables.h It should work :)
On Sat, Jan 07, 2006 at 01:29:41PM +0100, Emanuele Giaquinta wrote:
On 1/7/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
Please do, and tell us what didn't get integrated (since you said "almost all").
Apart from the changes already integrated upstream, I've not ported the ones to the non accelerated imdct in imdct.c (it has been totally rewritten). I've tested it succesfully with the accelerated resample/downmix/imdct on ppc/altivec and x86/mmx+sse. To test it create a new liba52 directory and do the following:
I'd appreciate if somebody could look into this. We have a bug in Bugzilla about failing AC3 samples that a newer version of liba52 should hopefully be able to play. Furthermore an upgrade promises much improved performance. Benchmarks comparing old and new version would be good. Diego
On Saturday, 14 January 2006 at 19:23, Diego Biurrun wrote:
On Sat, Jan 07, 2006 at 01:29:41PM +0100, Emanuele Giaquinta wrote:
On 1/7/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
Please do, and tell us what didn't get integrated (since you said "almost all").
Apart from the changes already integrated upstream, I've not ported the ones to the non accelerated imdct in imdct.c (it has been totally rewritten). I've tested it succesfully with the accelerated resample/downmix/imdct on ppc/altivec and x86/mmx+sse. To test it create a new liba52 directory and do the following:
I'd appreciate if somebody could look into this. We have a bug in Bugzilla about failing AC3 samples that a newer version of liba52 should hopefully be able to play. Furthermore an upgrade promises much improved performance.
Benchmarks comparing old and new version would be good.
My CPU is AMD Athlon Thunderbird 1GHz, MMX2, 3DNowEx, no SSE. MPlayer compiled with -O3 -ffast-math -march=athlon (which is the default). With 5:32 long 448kbit/s AC3 5.1 sample, the new liba52 is slower: for i in `seq 1 5` ; do mplayer -channels 6 -benchmark -novideo -ao \ pcm:nowaveheader:file=/dev/null 51.ac3 ; done $ benchavg.pl <mplayer-old-AC3-5.1.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 7.294s average SYS is: 0.268s average tot is: 7.563s $ benchavg.pl <mplayer-new-AC3-5.1.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 7.740s average SYS is: 0.291s average tot is: 8.030s This is about 6% slower. With 23:31 long 192kbit/s AC3 2.0 sample, the new liba52 is slower, too: for i in `seq 1 5` ; do mplayer -channels 2 -benchmark -novideo -ao \ pcm:nowaveheader:file=/dev/null 20.ac3 ; done $ benchavg.pl <mplayer-old-AC3-2.0.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 11.451s average SYS is: 0.406s average tot is: 11.857s $ benchavg.pl <mplayer-new-AC3-2.0.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 12.429s average SYS is: 0.413s average tot is: 12.842s This is about 8% slower. Maybe someone can provide samples for which the old liba52 fails and the new one works. Regards, R. -- MPlayer RPMs maintainer: http://rpm.greysector.net/mplayer/ "I am Grey. I stand between the candle and the star. We are Grey. We stand between the darkness ... and the light." -- Delenn in Grey Council in Babylon 5:"Babylon Squared"
On Mon, Jan 16, 2006 at 01:19:38AM +0100, Dominik 'Rathann' Mierzejewski wrote:
On Saturday, 14 January 2006 at 19:23, Diego Biurrun wrote:
On Sat, Jan 07, 2006 at 01:29:41PM +0100, Emanuele Giaquinta wrote:
Apart from the changes already integrated upstream, I've not ported the ones to the non accelerated imdct in imdct.c (it has been totally rewritten). I've tested it succesfully with the accelerated resample/downmix/imdct on ppc/altivec and x86/mmx+sse. To test it create a new liba52 directory and do the following:
I'd appreciate if somebody could look into this. We have a bug in Bugzilla about failing AC3 samples that a newer version of liba52 should hopefully be able to play. Furthermore an upgrade promises much improved performance.
Benchmarks comparing old and new version would be good.
My CPU is AMD Athlon Thunderbird 1GHz, MMX2, 3DNowEx, no SSE. MPlayer compiled with -O3 -ffast-math -march=athlon (which is the default).
With 5:32 long 448kbit/s AC3 5.1 sample, the new liba52 is slower:
Hmm, this is mysterious, since the liba52 homepage promises much improved performance.. Did the 3dnow optimizations get ported from our version to the updated one? Diego
Ok, I've finally found the reason for the slower performance on x86; in liba52-0.7.4 the definition of swab32 using bswap is disabled, so it was using the generic (slower) version. The attached patch updates the internal liba52 to the new one. -- Emanuele Giaquinta
On Sunday, 26 March 2006 at 16:47, Emanuele Giaquinta wrote:
Ok, I've finally found the reason for the slower performance on x86; in liba52-0.7.4 the definition of swab32 using bswap is disabled, so it was using the generic (slower) version. The attached patch updates the internal liba52 to the new one.
Indeed, now it seems to be about 2% faster. R. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
On Mon, Mar 27, 2006 at 01:12:28AM +0200, Dominik 'Rathann' Mierzejewski wrote:
On Sunday, 26 March 2006 at 16:47, Emanuele Giaquinta wrote:
Ok, I've finally found the reason for the slower performance on x86; in liba52-0.7.4 the definition of swab32 using bswap is disabled, so it was using the generic (slower) version. The attached patch updates the internal liba52 to the new one.
Indeed, now it seems to be about 2% faster.
Faster than what we currently have in CVS? Could you post benchmarks? Diego
On Monday, 27 March 2006 at 08:03, Diego Biurrun wrote:
On Mon, Mar 27, 2006 at 01:12:28AM +0200, Dominik 'Rathann' Mierzejewski wrote:
On Sunday, 26 March 2006 at 16:47, Emanuele Giaquinta wrote:
Ok, I've finally found the reason for the slower performance on x86; in liba52-0.7.4 the definition of swab32 using bswap is disabled, so it was using the generic (slower) version. The attached patch updates the internal liba52 to the new one.
Indeed, now it seems to be about 2% faster.
Faster than what we currently have in CVS?
Yes.
Could you post benchmarks?
Yes, as soon as I re-do them. ;) I've already done some preliminary benchmarks (hence the result), but deleted the logs. R. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
Patch updated against latest svn.
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
Patch updated against latest svn.
Test results on AMD64. MPlayer compiled with -m64 -O3 -march=k8. $ for i in `seq 1 5` ; do mplayer -quiet -channels 2 -benchmark -novideo -ao \ pcm:nowaveheader:file=/dev/null:fast Slayers_Next_2.en.ac3 ; done $ benchavg.pl <mplayer-old-AC3-2.0.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 7.143s average SYS is: 0.066s average tot is: 7.209s $ benchavg.pl <mplayer-new-AC3-2.0.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 7.140s average SYS is: 0.065s average tot is: 7.205s $ for i in `seq 1 5` ; do mplayer -quiet -channels 6 -benchmark -novideo -ao \ pcm:nowaveheader:file=/dev/null:fast Bjorn_Lynne-Secret_World-surround.ac3 ; \ done $ benchavg.pl <mplayer-old-AC3-5.1.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 4.551s average SYS is: 0.052s average tot is: 4.603s $ benchavg.pl <mplayer-new-AC3-5.1.log 5 results processed average VC is: 0.000s average VO is: 0.000s average AO is: 4.545s average SYS is: 0.050s average tot is: 4.595s Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up. Regards, R. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
Hi, On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits. G -- "Success consists of going from failure to failure without loss of enthusiasm." -- Winston Churchill
On Wednesday, 14 June 2006 at 23:29, Guillaume POIRIER wrote:
Hi,
On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits.
I can't find any cosmetics there. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
Hi, On 6/15/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 23:29, Guillaume POIRIER wrote:
Hi,
On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits.
I can't find any cosmetics there.
The ones I saw were just the copyright year changes. I hope I'm too mistaken since maybe these were in the local diff... Guillaume -- "Success consists of going from failure to failure without loss of enthusiasm." -- Winston Churchill
On Thursday, 15 June 2006 at 07:23, Guillaume POIRIER wrote:
Hi,
On 6/15/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 23:29, Guillaume POIRIER wrote:
Hi,
On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits.
I can't find any cosmetics there.
The ones I saw were just the copyright year changes. I hope I'm too mistaken since maybe these were in the local diff...
I don't consider those cosmetics. Regards, R. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
On Thursday, 15 June 2006 at 12:02, Dominik 'Rathann' Mierzejewski wrote:
On Thursday, 15 June 2006 at 07:23, Guillaume POIRIER wrote:
Hi,
On 6/15/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 23:29, Guillaume POIRIER wrote:
Hi,
On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits.
I can't find any cosmetics there.
The ones I saw were just the copyright year changes. I hope I'm too mistaken since maybe these were in the local diff...
I don't consider those cosmetics.
Bleh, looks like there were some cosmetics after all. Attached are two patches: functional-only and cosmetic-only (to be applied over the first one). -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
On Friday, 16 June 2006 at 00:31, Dominik 'Rathann' Mierzejewski wrote:
On Thursday, 15 June 2006 at 12:02, Dominik 'Rathann' Mierzejewski wrote:
On Thursday, 15 June 2006 at 07:23, Guillaume POIRIER wrote:
Hi,
On 6/15/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 23:29, Guillaume POIRIER wrote:
Hi,
On 6/14/06, Dominik 'Rathann' Mierzejewski <dominik@rangers.eu.org> wrote:
On Wednesday, 14 June 2006 at 15:35, Emanuele Giaquinta wrote:
[..]
Looks like the updated liba52 is slightly faster. I'm committing it tomorrow unless somebody speaks up.
Please do so, but as this patch contains some cosmetics, please split them up in separate commits.
I can't find any cosmetics there.
The ones I saw were just the copyright year changes. I hope I'm too mistaken since maybe these were in the local diff...
I don't consider those cosmetics.
Bleh, looks like there were some cosmetics after all. Attached are two patches: functional-only and cosmetic-only (to be applied over the first one).
Committed. -- MPlayer developer and RPMs maintainer: http://rpm.greysector.net/mplayer/ There should be a science of discontent. People need hard times and oppression to develop psychic muscles. -- from "Collected Sayings of Muad'Dib" by the Princess Irulan
participants (4)
-
Diego Biurrun -
Dominik 'Rathann' Mierzejewski -
Emanuele Giaquinta -
Guillaume POIRIER