Re: [MP3 ENCODER] Speeding up window_subband

[Naoki Shibata]

Takehiro> but..... but it is not faster than the old brute force calculation
Takehiro> algorithm, and obviously slow (about 20% for filtering itself, 5% for
Takehiro> overall encoding process) on my celeron 464 linux box.

  The code obviously needs optimization. Since I couldn't understand
 how current window_subband works, I chose not to optimize the code.
 Since almost all MP3 decoders use DCT version of the algorithm in
 subband synthesis, it should become faster than naive one, perhaps. :)

--
Naoki Shibata   e-mail: [EMAIL PROTECTED]

--
MP3 ENCODER mailing list ( http://geek.rcc.se/mp3encoder/ )