IPB

Welcome Guest ( Log In | Register )

8 Pages V  « < 5 6 7 8 >  
Reply to this topicStart new topic
Ogg Vorbis acceleration project, Is it dead?
john33
post Jul 4 2012, 13:21
Post #151


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



QUOTE (Raimu @ Jul 3 2012, 19:55) *
@john33, any interest in also posting the cli encoder binary at Rarewares?

Done. smile.gif


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
punkrockdude
post Jul 4 2012, 13:43
Post #152





Group: Members
Posts: 244
Joined: 21-February 05
Member No.: 20022



Anyone that can give some guidance on how to compile this under Linux (Ubuntu)? Regards.
Go to the top of the page
+Quote Post
LigH
post Jul 4 2012, 14:20
Post #153





Group: Members
Posts: 157
Joined: 20-November 01
Member No.: 503



A few more statistics, transcoding 01:42:28 h of a 5.1 AC3 on a Phenom-II X4 945 using BeSweet with DPL-II downmix and fixed gain (to avoid including the normalization pass):

Generic
06:42 (686)
06:04 (P4)

Lancer
04:30 (SSE)
03:51 (SSE2)
03:50 (SSE3)

The gap between generic and extreme optimization is quite impressive. And even the gap between SSE and SSE2 is still remarkable. But after all, decoding and downmixing takes its time too, so a certain degree of saturation is expectable.


--------------------
http://forum.gleitz.info - das deutsche doom9/Gleitz-Forum
Go to the top of the page
+Quote Post
Brazil2
post Jul 4 2012, 14:22
Post #154





Group: Members
Posts: 149
Joined: 9-May 10
Member No.: 80499



QUOTE (john33 @ Jul 4 2012, 14:21) *
QUOTE (Raimu @ Jul 3 2012, 19:55) *
@john33, any interest in also posting the cli encoder binary at Rarewares?

Done. smile.gif

Thanks but unfortunately, and unlike your previous builds, it's not running anymore on older OSes pre-XP SP2 on which VC2010 runtimes can't be installed sad.gif

But this might be helpfull: http://mulder.googlecode.com/svn/trunk/Uti...rLib/README.txt
Go to the top of the page
+Quote Post
LigH
post Jul 4 2012, 14:25
Post #155





Group: Members
Posts: 157
Joined: 20-November 01
Member No.: 503



There are reasons why such old OS are deprecated. An excuse would be running them offline.


--------------------
http://forum.gleitz.info - das deutsche doom9/Gleitz-Forum
Go to the top of the page
+Quote Post
john33
post Jul 4 2012, 14:25
Post #156


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



QUOTE (Brazil2 @ Jul 4 2012, 14:22) *
Thanks but unfortunately, and unlike your previous builds, it's not running anymore on older OSes pre-XP SP2 on which VC2010 runtimes can't be installed sad.gif

But this might be helpfull: http://mulder.googlecode.com/svn/trunk/Uti...rLib/README.txt

OK, what optimisation does your CPU support?


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
LigH
post Jul 4 2012, 14:40
Post #157





Group: Members
Posts: 157
Joined: 20-November 01
Member No.: 503



It's rather a question of PE-building and linking than of CPU optimizations, john33. Not the CPU is the limit, but the OS and its set of supported Windows API functions.

This post has been edited by LigH: Jul 4 2012, 14:41


--------------------
http://forum.gleitz.info - das deutsche doom9/Gleitz-Forum
Go to the top of the page
+Quote Post
Brazil2
post Jul 4 2012, 14:43
Post #158





Group: Members
Posts: 149
Joined: 9-May 10
Member No.: 80499



QUOTE (john33 @ Jul 4 2012, 15:25) *
OK, what optimisation does your CPU support?

MMX, SSE, SSE2, SSE3, SSSE3 and I'm usually using your P4 optimized builds.
Thank you smile.gif
Go to the top of the page
+Quote Post
Steve Forte Rio
post Jul 4 2012, 16:26
Post #159





Group: Members
Posts: 443
Joined: 4-October 08
From: Ukraine
Member No.: 59301



QUOTE (john33 @ Jul 4 2012, 10:21) *
QUOTE (Raimu @ Jul 3 2012, 19:55) *
@john33, any interest in also posting the cli encoder binary at Rarewares?

Done. smile.gif


Hi, John. But what is the difference between your new compiles and this?

I don't remember where I got it, but it was more than one year ago and actually this is also OggEnc v2.87 LancerMod(SSE3) based on aoTuV b6.03 [20110424]. Could you clarify?

This post has been edited by Steve Forte Rio: Jul 4 2012, 16:28
Go to the top of the page
+Quote Post
john33
post Jul 4 2012, 16:49
Post #160


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



QUOTE (Brazil2 @ Jul 4 2012, 14:43) *
QUOTE (john33 @ Jul 4 2012, 15:25) *
OK, what optimisation does your CPU support?

MMX, SSE, SSE2, SSE3, SSSE3 and I'm usually using your P4 optimized builds.
Thank you smile.gif

Try this: http://www.rarewares.org/files/ogg/oggenc2...cerSSE2_OLD.zip
and perhaps you could let me know if it's OK? smile.gif


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
john33
post Jul 4 2012, 16:52
Post #161


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



QUOTE (Steve Forte Rio @ Jul 4 2012, 16:26) *
QUOTE (john33 @ Jul 4 2012, 10:21) *
QUOTE (Raimu @ Jul 3 2012, 19:55) *
@john33, any interest in also posting the cli encoder binary at Rarewares?

Done. smile.gif


Hi, John. But what is the difference between your new compiles and this?

I don't remember where I got it, but it was more than one year ago and actually this is also OggEnc v2.87 LancerMod(SSE3) based on aoTuV b6.03 [20110424]. Could you clarify?

I couldn't say with any certainty, but probably the only difference from looking at the size of the executables is that I don't think they were compiled with the libsamplerate resampler.


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
Brazil2
post Jul 4 2012, 17:05
Post #162





Group: Members
Posts: 149
Joined: 9-May 10
Member No.: 80499



QUOTE (john33 @ Jul 4 2012, 17:49) *
Try this: http://www.rarewares.org/files/ogg/oggenc2...cerSSE2_OLD.zip
and perhaps you could let me know if it's OK? smile.gif

Brilliant! Works like a charm, thanks a lot smile.gif
CODE
G:\Test\>oggenc2 -h
OggEnc v2.87 (LancerMod(SSE2) based on aoTuV b6.03 [20110424])
(c) 2000-2005 Michael Smith <msmith@xiph.org>
& portions by John Edwards <john.edwards33@ntlworld.com>
Go to the top of the page
+Quote Post
lvqcl
post Jul 4 2012, 17:14
Post #163





Group: Developer
Posts: 3363
Joined: 2-December 07
Member No.: 49183



My versions of oggenc2.exe doesn't include SRC and FLAC libraries and I commented out all relevant options and calls.

@john33: in your compiles these options are disabled too lalala.gif I think it's not what you want, and 3 source files with re-enabled options are attached to the post.
Go to the top of the page
+Quote Post
Raimu
post Jul 4 2012, 18:08
Post #164





Group: Members
Posts: 9
Joined: 2-July 12
Member No.: 101128



QUOTE
Hi, John. But what is the difference between your new compiles and this?
I don't remember where I got it, but it was more than one year ago and actually this is also OggEnc v2.87 LancerMod(SSE3) based on aoTuV b6.03 [20110424]. Could you clarify?

Some tests (out of interest) on my PC reveal that john33's current binaries are slightly but noticably faster than these in your link, in the very least.

This post has been edited by Raimu: Jul 4 2012, 18:09
Go to the top of the page
+Quote Post
john33
post Jul 4 2012, 18:58
Post #165


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



QUOTE (lvqcl @ Jul 4 2012, 17:14) *
My versions of oggenc2.exe doesn't include SRC and FLAC libraries and I commented out all relevant options and calls.

@john33: in your compiles these options are disabled too lalala.gif I think it's not what you want, and 3 source files with re-enabled options are attached to the post.

Thanks, but the versions at Rarewares have these enabled. smile.gif

EDIT: I just realised that the options were disabled in the oggenc2 code! blush.gif I had enabled the inclusion of the libs in the compiles and hadn't checked the code!

This post has been edited by john33: Jul 4 2012, 19:05


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
john33
post Jul 4 2012, 19:27
Post #166


xcLame and OggDropXPd Developer


Group: Developer
Posts: 3760
Joined: 30-September 01
From: Bracknell, UK
Member No.: 111



All of the above oggenc2 compiles have been updated at Rarewares. Sorry for the confusion! blink.gif


--------------------
John
----------------------------------------------------------------
My compiles and utilities are at http://www.rarewares.org/
Go to the top of the page
+Quote Post
xconstellationx
post Jul 7 2012, 10:46
Post #167





Group: Members
Posts: 29
Joined: 7-July 12
Member No.: 101227



QUOTE (john33 @ Jul 4 2012, 20:27) *
All of the above oggenc2 compiles have been updated at Rarewares. Sorry for the confusion! blink.gif


Great work, thanks a lot.

Although the version by lvqcl is still faster on my machine. I use oggenc2 32bit sse3 from here and foobar converts a flac around 49x while your compile is at 42x.
Go to the top of the page
+Quote Post
LigH
post Jul 7 2012, 10:52
Post #168





Group: Members
Posts: 157
Joined: 20-November 01
Member No.: 503



Your machine. Aha.

We all know your machine.

Oh, no, this is your first post, so how could we?

Hint: http://hwinfo.com/

This post has been edited by LigH: Jul 7 2012, 10:53


--------------------
http://forum.gleitz.info - das deutsche doom9/Gleitz-Forum
Go to the top of the page
+Quote Post
xconstellationx
post Jul 7 2012, 11:01
Post #169





Group: Members
Posts: 29
Joined: 7-July 12
Member No.: 101227



It's a core2duo laptop with a P8600+ 4gb ram on win7.
Go to the top of the page
+Quote Post
lvqcl
post Jul 7 2012, 14:03
Post #170





Group: Developer
Posts: 3363
Joined: 2-December 07
Member No.: 49183



QUOTE (xconstellationx @ Jul 7 2012, 13:46) *
Although the version by lvqcl is still faster on my machine. I use oggenc2 32bit sse3 from here and foobar converts a flac around 49x while your compile is at 42x.


Try LancerSSE2_OLD build. It is faster than other versions (except x64).
Go to the top of the page
+Quote Post
xconstellationx
post Jul 7 2012, 16:24
Post #171





Group: Members
Posts: 29
Joined: 7-July 12
Member No.: 101227



With johns lancer sse2 old i get the same speed like using your sse3 version. wink.gif
Go to the top of the page
+Quote Post
xconstellationx
post Jul 8 2012, 10:53
Post #172





Group: Members
Posts: 29
Joined: 7-July 12
Member No.: 101227



Out of curiosity i tested all 32bit oggenc2 compiles again and here are the results:


John33:

sse 35.69x
sse2 38.40x
sse3 38.60x

sse2old 47.19x


lvqcl:

sse 38.80x
sse2 47.94x
sse3 47.73x


I'm not familiar with compiling, so i wonder why there is such a huge step in speed from sse to sse2 while sse2 and sse3 are on the same level?
Go to the top of the page
+Quote Post
LigH
post Jul 8 2012, 11:55
Post #173





Group: Members
Posts: 157
Joined: 20-November 01
Member No.: 503



This effect doesn't belong to the "Compiling" as such (the C compiler only translates the source routines which are not very CPU optimized; the in-depth CPU instruction set optimization is more efficiently done via manual Assembler code).

The efficiency boost between different instruction sets depends on the algorithm to be optimized and the differences between the instruction sets. So specifically for the Vorbis encoding, SSE2 seems to introduce very useful new instructions (relative to SSE only), but the new instructions in SSE3 (relatively to SSE2 only) are only marginal for the Vorbis algorithms.


--------------------
http://forum.gleitz.info - das deutsche doom9/Gleitz-Forum
Go to the top of the page
+Quote Post
xconstellationx
post Jul 8 2012, 13:20
Post #174





Group: Members
Posts: 29
Joined: 7-July 12
Member No.: 101227



QUOTE (LigH @ Jul 8 2012, 12:55) *
The efficiency boost between different instruction sets depends on the algorithm to be optimized and the differences between the instruction sets. So specifically for the Vorbis encoding, SSE2 seems to introduce very useful new instructions (relative to SSE only), but the new instructions in SSE3 (relatively to SSE2 only) are only marginal for the Vorbis algorithms.

Thanks for clarifying.

Is it the reason there is no sse4 compile, because it introduces too little useful instructions compared to sse3 as well?
Go to the top of the page
+Quote Post
Raimu
post Jul 8 2012, 15:59
Post #175





Group: Members
Posts: 9
Joined: 2-July 12
Member No.: 101128



QUOTE
Is it the reason there is no sse4 compile, because it introduces too little useful instructions compared to sse3 as well?


I was under the impression the reason is more along the lines of SSE4* being an umbrella term for a clustermess of very different instruction sets some of which only work on newish Intel CPUs and others only on newish AMD CPUs and all of which only can be effectively optimized for on pretty new and specific compilers.
Go to the top of the page
+Quote Post

8 Pages V  « < 5 6 7 8 >
Reply to this topicStart new topic
1 User(s) are reading this topic (1 Guests and 0 Anonymous Users)
0 Members:

 



RSS Lo-Fi Version Time is now: 31st August 2014 - 06:22