Christophe Gisquet adf4ee40e7 wma lossless: reuse scalarproduct_and_madd_int16
This is done by padding the coefficient buffer with 0s, because the order
may be only a multiple of 4, and the DSP function requires batches of 8.

However, no sample with such a case was found, so request one if it uses
that kind of order.

Approximate relative speedup depending on instruction set:
plain C: -6%
mmxext:  51%
sse2:    54%

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-06 13:51:41 +02:00
2014-06-03 10:58:19 -08:00
2014-06-03 10:58:19 -08:00
2012-05-04 18:40:36 +02:00
2014-06-05 12:20:49 +02:00
2014-06-03 10:58:19 -08:00
2014-05-06 14:14:32 +02:00
2014-05-28 03:52:50 +02:00
2014-05-28 03:52:50 +02:00
2014-06-05 20:31:59 +02:00
2014-05-23 23:30:21 +02:00
2014-05-21 15:59:22 +02:00
2014-05-28 22:38:38 +02:00
2014-05-28 22:38:28 +02:00
2014-05-28 22:38:11 +02:00
2014-03-13 08:24:11 -04:00

FFmpeg README

  1. Documentation

  1. Licensing

  • See the LICENSE file.
  1. Build and Install

  • See the INSTALL file.
Description
No description provided
Readme 173 MiB
Languages
C 92.1%
Assembly 6%
Makefile 1.2%
C++ 0.3%
Objective-C 0.2%
Other 0.1%