libavcodec.hg: revision graph

graph

less more | rev 1567: (0) -1000 -300 -100 -15 +15 +100 +300 +1000 +3000 +10000 tip

* introducing dct248 into the DSP context. libavcodec
Fri, 24 Oct 2003 18:28:01 +0000, by romansh
1l libavcodec
Thu, 23 Oct 2003 23:24:38 +0000, by alex
minor mmx2 optimization if the dct libavcodec
Thu, 23 Oct 2003 13:22:20 +0000, by michael
inline -> always_inline (842 -> 690 cpu cycles for dct_quantize() difference for the dct itself should be even bigger) libavcodec
Thu, 23 Oct 2003 12:59:21 +0000, by michael
4.9-RC FreeBSD doesnt like lrint() so change to lrintf(), not that bsd supports that but we emulate it ... libavcodec
Thu, 23 Oct 2003 12:41:54 +0000, by michael
optionally merge postscale into quantization table for the float aan dct libavcodec
Thu, 23 Oct 2003 09:11:56 +0000, by michael
10l libavcodec
Thu, 23 Oct 2003 08:31:26 +0000, by michael
10l libavcodec
Wed, 22 Oct 2003 22:12:25 +0000, by alex
100l libavcodec
Wed, 22 Oct 2003 22:10:22 +0000, by alex
oops forgot libavcodec
Wed, 22 Oct 2003 19:15:55 +0000, by michael
floating point AAN DCT libavcodec
Wed, 22 Oct 2003 18:26:38 +0000, by michael
112 bytes smaller MpegEncContext libavcodec
Wed, 22 Oct 2003 15:36:46 +0000, by michael
move blocks away MpegEncContext (7.4 -> 5.8k) libavcodec
Wed, 22 Oct 2003 12:01:21 +0000, by michael
move mmx quantizer matrixes out of MpegEncContext (23k -> 7k) (no meassureable slowdown) libavcodec
Wed, 22 Oct 2003 11:23:39 +0000, by michael
move q_*_matrix out of MpegEncContext (40k ->23k) dct_quantize() is even slightly faster now, dont ask my why ... libavcodec
Wed, 22 Oct 2003 10:59:39 +0000, by michael

less more | rev 1567: (0) -1000 -300 -100 -15 +15 +100 +300 +1000 +3000 +10000 tip

Mercurial > libavcodec.hg

graph