[FFmpeg-devel] [PATCH] ARM: NEON optimised float_to_int16

Ian Caulfield ian.caulfield
Thu Dec 18 11:56:42 CET 2008

2008/12/18 M?ns Rullg?rd <mans at mansr.com>:
> The 4-register load uses 2 issue cycles, only one of which can
> dual-issue.  2-register load uses only one cycle and can dual-issue
> with either the preceding or following instruction.  Splitting the
> loads is often faster in situations like this with good opportunities
> for dual-issue.  I didn't benchmark this particular case though.

Fair enough - I'm not very familiar with the details of scheduling for Cortex-A8


More information about the ffmpeg-devel mailing list