]> granicus.if.org Git - libx264/commit
projects / libx264 / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 552a04e) | patch
Resolve floating point exception with frame_init_lowres mmx
authorFiona Glaser <fiona@x264.com>
Sun, 6 Jul 2008 17:15:19 +0000 (11:15 -0600)
committerFiona Glaser <fiona@x264.com>
Sun, 6 Jul 2008 17:17:33 +0000 (11:17 -0600)
commit653249521805b21564c00148f7db1e4b28e6e15c
tree54013d78b1ed72a81fa49755679ae42663ee5b56tree | snapshot
parent552a04ea3c56317046686bdc41d31e15490f6b85commit | diff
Resolve floating point exception with frame_init_lowres mmx
In some cases, the mmx version of frame_init_lowres could leave the FPU uninitialized for use in ratecontrol, resulting in floating point exceptions.
Since frame_init_lowres is such a time-consuming function, an emms was just put at the end, since it costs almost nothing compared to the total time of frame_init_lowres.
common/x86/mc-a2.asm diff | blob | history
Unnamed repository; edit this file 'description' to name the repository.