[vorbis-dev] vorbis on playstation 2
bbarclay at jsyncmanager.org
Wed Feb 5 17:20:16 PST 2003
On Wed, 5 Feb 2003 19:53:24 -0500 (EST), Nicolas Pitre wrote:
>It would be interesting if you could do the same analysis with Tremor.
>I've made many cache improvements in Tremor's mdct_backward some time ago.
>Cache usage clearly improved on an ARM processor compared to the earlier
>version of the same function, but I don't know how it compares to the
Well, it looks like I'll be re-running the profiling tools on
the PS2 again this weekend, to generate some digital results (as
opposed to the printed results I have sitting here), so I'll grab the
Tremor sources and build and profile them as well.
Of course, this will only be valid for the PS2, and only with a
straight non-platform-optimized recompile of the code. The PS2 should
be able to do much better (by an order of magnitude or so) with use of
the currently unused parallel VPUs, but that requires some inline VPU
assembly that hasn't been written yet (and I'm not sure if Tremor will
benifit from this as much as Vorbis would, as the VPUs are designed to
transform floating point data).
When I have some result files, I'll post them up here so people
can analyze them.
>From the OS/2 WARP v4.5 Desktop of Brad BARCLAY.
E-Mail: yaztromo at acm.org Web: http://www.jsyncmanager.org
<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 to 'vorbis-dev-request at xiph.org'
containing only the word 'unsubscribe' in the body. No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.
More information about the Vorbis-dev