Le ven 23/01/2004 à 18:55, Grzegorz Kulewski a écrit :> Hmm, what these instructions do? (I know nothing about ARMs; I have some > knowlege about x86 assemblers and programming).These are dsp-like instructions. For example, one of them replaces 4 instructions by doing a 32 bits x 16 bits fused multiply-add. I know they're available on xscale, but I don't know about other ARM cores.> Cant we use pure standard C++ or Java?Sure, the assembly is only for some parts where there's a potential gain in speed.> Does Speex work with fixedpoint math? (As far as I know Java > on 6600 has no builtin floatingpoint, there is emulation class somewhere > on the net, but it is probably painfully slow.) I do not know if this > processor has builtin floatingpoint math module.Speex uses fixed-point arithmetic. Otherwise, it would be about 100 times slower than real-time.> When "current" code would be able to do it in Your opinion?I have no idea. You have to test that. If the multiply-add and similar operations are supported, it might be already possible. Otherwise, there would be some optimization to do. Right now, Speex is about 5x faster than real-time on a 400 MHz xscale. Jean-Marc -- Jean-Marc Valin, M.Sc.A., ing. jr. LABORIUS (http://www.gel.usherb.ca/laborius) Université de Sherbrooke, Québec, Canada -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 190 bytes Desc: Ceci est une partie de message numériquement signée. Url : http://lists.xiph.org/pipermail/speex-dev/attachments/20040123/78de4034/signature-0001.pgp
Hmm, what these instructions do? (I know nothing about ARMs; I have some knowlege about x86 assemblers and programming). Cant we use pure standard C++ or Java? Does Speex work with fixedpoint math? (As far as I know Java on 6600 has no builtin floatingpoint, there is emulation class somewhere on the net, but it is probably painfully slow.) I do not know if this processor has builtin floatingpoint math module. When "current" code would be able to do it in Your opinion? <p>Grzegorz <p>On Fri, 23 Jan 2004, Jean-Marc Valin wrote:> > I have one question: Will Speex run in realtime (both encode / decode > > probably simulateusly) on Nokia 6600 --- basicaly ARM9 104MHz with Symbian > > 7s after porting to its C++ or Java? I am thinking mostly about the worst > > quality encoding (optionally duplex). Can this processor make it? Oh 6600 > > has something about 6mb memory if I remember good. > > I'm not sure the current code will do it (maybe?), but I think it can be > done. On question: does this ARM support instruction like smlabb, > smulbb, smulwb, ... ? > > Jean-Marc--- >8 ---- List archives: http://www.xiph.org/archives/ Ogg project homepage: http://www.xiph.org/ogg/ To unsubscribe from this list, send a message to 'speex-dev-request@xiph.org' containing only the word 'unsubscribe' in the body. No subject is needed. Unsubscribe messages sent to the list will be ignored/filtered.
> When "current" code would be able to do it in Your opinion?I just tested the non-asm version on a 140 MHz iPaq (Intel StrongARM-1110 rev 8) and it can do real-time encode+decode with about 50% CPU. This means it might actually work on your CPU. Jean-Marc Compiled with gcc 3.2 (-mcpu=strongarm1100) -- Jean-Marc Valin, M.Sc.A., ing. jr. LABORIUS (http://www.gel.usherb.ca/laborius) Université de Sherbrooke, Québec, Canada -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 190 bytes Desc: Ceci est une partie de message numériquement signée. Url : http://lists.xiph.org/pipermail/speex-dev/attachments/20040124/51b592ae/signature-0001.pgp
Thanks very much. You mean both encode and decode simulateusly (duplex)? Could you test the Java version (jspeex) on that iPaq too? (I do not have anything other than very fast PC, so I cant do this...) And, in phone, the mic can record not only the users speech but also voice from the other side (from speaker)... Does this make compression harder or the result worse? How can this impact bitrate? Can Speex eliminate this effect? Beside this, can Speex be compiled by anything other than gcc? (I do not know if gcc can create binaries for Symbian on that phone and if I remember good the SDK for Symbian on 6600 comes with some Borland C++ compiler...) thanks once more <p>Grzegorz <p><p>On Sat, 24 Jan 2004, Jean-Marc Valin wrote:> > When "current" code would be able to do it in Your opinion? > > I just tested the non-asm version on a 140 MHz iPaq (Intel > StrongARM-1110 rev 8) and it can do real-time encode+decode with about > 50% CPU. This means it might actually work on your CPU. > > Jean-Marc > > Compiled with gcc 3.2 (-mcpu=strongarm1100)--- >8 ---- List archives: http://www.xiph.org/archives/ Ogg project homepage: http://www.xiph.org/ogg/ To unsubscribe from this list, send a message to 'speex-dev-request@xiph.org' containing only the word 'unsubscribe' in the body. No subject is needed. Unsubscribe messages sent to the list will be ignored/filtered.