similar to: Ogg Vorbis and MMX/3dnow

Hi, I´m new on this list so I really don´t know that kind of questions have been asked, but here I go. Is the current ogg plug-ins using any mmx or 3dnow! instructions? Is there any performance to gain? I know that most of the mp3-decoders uses mmx/3dnow! to decode mp3streams so in theory it would be applyable to ogg to...? Just a thought... Regards, Andreas Karlsson hermes@home.se

Hi, <p>> I have a question for you. If I want to write a vorbis client from scratch, > should it attempt to read the input file from start to finish, or should it > attempt to start at the end first > in order to use statistical analysis to optimize the conversion process? I have > been playing > around with oggenc and ogg123 and enjoying the way my music sounds, but I

I finally got all of the 3DNow! instruction intrinsics and builtins into LLVM and Clang, however, while testing them, I've noticed that they produce incorrect results. For example: typedef float V2f __attribute__((vector_size(8))); int main() { V2f dest, a = {1.0, 3.0}, b = {10.0, 3.5}; dest = __builtin_ia32_pfadd(a, b); printf("(%f, %f)\n", dest[0], dest[1]); } Should

On Apr 14, 2011, at 12:47 PM, Eli Friedman wrote: >> I looked at the program using a debugger, and the pfadd instruction is >> executed correctly and the MMX register contains the correct values. >> The code that prepares the stack for the printf call seems to be >> messing it up. > > I would call that "user error"; basically, using MMX instructions >

I'm trying to improve Opus on an AMD Geode CPU, which has limited SSE support (called 3DNow!), but MMX. Without optimizations I can only encode 16 bit audio @16KHz with complexity up to 2-3 without underruns. I tried compiling with SSE2/4 optimizations, but all I got was a crash with SIGILL, so I looked into optimized code and found that a good starting point was the dot product, so I

I got a new Athlon recently, and to my surprise, FLAC started segfaulting, even when recompiled. The problem goes away if I build with --disable-asm-optimizations. Has anyone else had problems of this sort? Here are the specs on the processor: processor : 0 vendor_id : AuthenticAMD cpu family : 6 model : 4 model name : AMD Athlon(tm) Processor stepping :

On Thu, Apr 14, 2011 at 5:37 PM, Chris Lattner <clattner at apple.com> wrote: > > On Apr 14, 2011, at 12:47 PM, Eli Friedman wrote: > >>> I looked at the program using a debugger, and the pfadd instruction is >>> executed correctly and the MMX register contains the correct values. >>> The code that prepares the stack for the printf call seems to be

On Thu, Apr 14, 2011 at 12:16 PM, Michael Spencer <bigcheesegs at gmail.com> wrote: > I finally got all of the 3DNow! instruction intrinsics and builtins > into LLVM and Clang, however, while testing them, I've noticed that > they produce incorrect results. > > For example: > > typedef float V2f __attribute__((vector_size(8))); > > int main() { >  V2f dest,

Hey all, I''m thinking about moving my 2.0.7 install over to 3.0.0 for eventual use in a production environment. Two questions: 1) Do people think 3.0.0 is ready for production - or is it just a testing/unstable playpen? 2) What do I have to change - just the xen-2.0.7.gz for do I have to recompile the dom0/domU kernels too? Cheers, Matthew Walster

Hi Jean Marc, I think there is just a confusion over terminology going on here- I agree that support for 3dnow base version may not necessarily be relevant; However, even though 3dNow extended is a bastardized version of SSE, it still supports the same instructions, and that is what is important- I don't think we intend to add any AMD specfic code. The real issue is cross CPU SSE support,

Dave St John wrote: >Correct since im not sending any content type headers for browsers, as the >links are intended to be inserted into playlist files .pls > >example mp3 >[playlist] >NumberOfEntries=1 >File1=http://mediacast1.com/members/listen_icecast2_mp3.php?submc1id=999&sub >mc1srvkey=278931a39ae8a23377e2d9445d8c9432f3e48a1d >Title1=latex radio >Length1=-1

Smörk wrote: > I think I have the same problem. I didn't managed to complie the > "example" streamer, but if I open a url with a browser the connections > hangs too. IIRC the old icecast send a 404 if there is no stream > available. icecast 2 does nothing if I point to > http://localhost:8000/wrongmountpoint, doesn't matter if I use winamp > or a normal web

Hi all, While I was busy sorting out my music collection, I discovered that file(1) had no Ogg/Vorbis (or Ogg/* for that matter) support yet. Is there anyone working on support for this or am I using an outdated version of file(1) ? file(1) has extensive MP3 support. Compare the following : $ file */*.ogg | grep 01 Busta Rhymes - Genesis/01 Intro.ogg: data De La Soul -

I have been using a laptop computer of Pentium III 1.13 Ghz. I heard that AMD's Athlon has excellent floating point capacity. So I bought a Athlon 2200+ laptop yesterday. I expected that new Athlon 2200+ will be twice as fast as the P III 1.13 GB. I ran a R simulation program and the new computer is only 30% faster, in fact slightly slower than a Celeron 1.50 GB laptop. I am very disappointed

I have done fresh builds of xmms-1.2.5, libogg-1.0rc2, and libvorbis-1.0rc2 on a sparc-solaris-2.8 platform, using gcc-2.95.3. I had to use the GNU binutils to get the libvorbis libraries to link correctly. Everything built clean and without protest. When I install it all and try an ogg-vorbis file, I get noise. I'm wondering if this is a big-endian problem somewhere. I'd appreciate

An article I saw on the french news site http://www.linuxfr.org says that the BBC is testing streaming with Vorbis on his web servers. Apparently, it works very well with XMMS. Vorbis is growing in popularity and it's a good thing! <p>--- >8 ---- List archives: http://www.xiph.org/archives/ Ogg project homepage: http://www.xiph.org/ogg/ To unsubscribe from this list, send a message

Dear Developers, I am currently involved in the co-ordination of archiving a whole heap of tapes containing audio (4000+ sermons for www.newcreation.org.au) to digital format. At present, all the tapes have been converted into mp3 @ CBR 40kbs, 44100 Hz... And this appears to play in most portable players capable of playing mp3's. (ogg vorbis isn't that widely supported, and many portable

Dave St John wrote: >fyi so you can see what im talking about >mp3 demo username demo pass demo123 >http://mediacast1.com/members/listen_icecast2_mp3.php?submc1id=999&submc1srvkey=278931a39ae8a23377e2d9445d8c9432f3e48a1d > >ogg demo that wont work >same username and password as above

So we ran the code on a Windows XP based Atholon XP system and the xmm registers work just fine so it appears that Windows 2000 and below does not support them. We agree on not supporting the non-FP version, however the run time flags need to be settable with a non FP SSE mode so that exceptions are avoided. I thus propose a set of defines like this instead of the ones in our initial patch:

qemu recently added support for 3dnow instructions. Because of that, 3dnow will be featured among cpuid bits. But this will break kvm in cpus that don't have those instructions (which includes my laptop). So we fixup our cpuid before exposing it to the guest. Signed-off-by: Glauber Costa <gcosta at redhat.com> --- arch/x86/kvm/x86.c | 22 ++++++++++++++++++----