[FFmpeg-devel] [PATCH 1/3] avutil/imgutils: Optimize writing 4 bytes in memset_bytes()

Michael Niedermayer michael at niedermayer.cc
Wed Dec 26 21:45:06 EET 2018


On Tue, Dec 25, 2018 at 10:12:13PM -0300, James Almer wrote:
> On 12/25/2018 7:15 PM, Michael Niedermayer wrote:
> > Fixes: Timeout
> > Fixes: 11502/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_WCMV_fuzzer-5664893810769920
> > Before: Executed clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_WCMV_fuzzer-5664893810769920 in 11294 ms
> > After : Executed clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_WCMV_fuzzer-5664893810769920 in 4249 ms
> > 
> > Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg
> > Signed-off-by: Michael Niedermayer <michael at niedermayer.cc>
> > ---
> >  libavutil/imgutils.c | 6 ++++++
> >  1 file changed, 6 insertions(+)
> > 
> > diff --git a/libavutil/imgutils.c b/libavutil/imgutils.c
> > index 4938a7ef67..cc38f1e878 100644
> > --- a/libavutil/imgutils.c
> > +++ b/libavutil/imgutils.c
> > @@ -529,6 +529,12 @@ static void memset_bytes(uint8_t *dst, size_t dst_size, uint8_t *clear,
> >          }
> >      } else if (clear_size == 4) {
> >          uint32_t val = AV_RN32(clear);
> > +        uint64_t val8 = val * 0x100000001ULL;
> > +        for (; dst_size >= 32; dst_size -= 32) {
> > +            AV_WN64(dst   , val8); AV_WN64(dst+ 8, val8);
> > +            AV_WN64(dst+16, val8); AV_WN64(dst+24, val8);
> > +            dst += 32;
> > +        }
> 
> This should be wrapped with a HAVE_FAST_64BIT preprocessor check.

will do so


> 
> Also, is it much slower if you also write one per loop like everywhere
> else in the function? I'd prefer if things are consistent.

as in the patch:
 3955 ms  3954 ms  3954 ms
 
with one write per iteration:
 5705 ms  5635 ms  5629 ms

 
> Similarly, you could add four and eight bytes loops to the clear_size ==
> 2 case above.

yes i can if you want me to?, but i have no testcase for that so it would be untested

thx


[...]

-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

Dictatorship naturally arises out of democracy, and the most aggravated
form of tyranny and slavery out of the most extreme liberty. -- Plato
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 181 bytes
Desc: not available
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20181226/f037f3aa/attachment.sig>


More information about the ffmpeg-devel mailing list