[FFmpeg-cvslog] r24213 - trunk/libavcodec/dca.c
Mon Jul 12 23:17:30 CEST 2010
Wasn't registered before, sorry for replying to another mail than the
2010/7/12 M?ns Rullg?rd <mans at mansr.com>:
>>>> Won't this patch make it use double-precision floating point math when
>>>> not needed?
For the record, the only change on x86, where x87 FPU code is used
anyway, is a flds instruction (load of float) changed to a fldl (load
of double), which is pretty harmless speedwise.
And if the code really matters, simd is pretty simple on such code.
>>> Time for f-versions of those constants?
There are a number of places where some code defines its own value,
and I'm not sure float vs double is checked either.
More information about the ffmpeg-cvslog