[FFmpeg-devel,3/6] avcodec/pngdec: Optimize has_trns code

Submitted by Michael Niedermayer on Aug. 17, 2019, 11:28 p.m.

Details

Message ID 20190817232841.14709-3-michael@niedermayer.cc
State New
Headers show

Commit Message

Michael Niedermayer Aug. 17, 2019, 11:28 p.m.
30M cycles -> 5M cycles

Testcase: fate-rgbapng-4816
Testcase: 16097/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_APNG_fuzzer-5664690889293824

Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg
---
 libavcodec/pngdec.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

Comments

Reimar Döffinger Aug. 18, 2019, 6:49 a.m.
On 18.08.2019, at 01:28, Michael Niedermayer <michael@niedermayer.cc> wrote:

> 30M cycles -> 5M cycles

I see nothing wrong with it, but:
You could save reviewers a lot of time if you gave them a hint of what the change
contains instead of them having to reverse-engineer.
In this case for example something like
"add inner loop specialisations for 2 bpp and 4 bpp"

> 
> @@ -1363,19 +1364,38 @@ exit_loop:
>         unsigned x, y;
> 
>         av_assert0(s->bit_depth > 1);
> -

Cosmetic?
Michael Niedermayer Aug. 18, 2019, 8:31 a.m.
On Sun, Aug 18, 2019 at 08:49:06AM +0200, Reimar Döffinger wrote:
> On 18.08.2019, at 01:28, Michael Niedermayer <michael@niedermayer.cc> wrote:
> 
> > 30M cycles -> 5M cycles
> 
> I see nothing wrong with it, but:
> You could save reviewers a lot of time if you gave them a hint of what the change
> contains instead of them having to reverse-engineer.
> In this case for example something like
> "add inner loop specialisations for 2 bpp and 4 bpp"

added


> 
> > 
> > @@ -1363,19 +1364,38 @@ exit_loop:
> >         unsigned x, y;
> > 
> >         av_assert0(s->bit_depth > 1);
> > -
> 
> Cosmetic?

removed and reposted 

thx

[...]

Patch hide | download patch | download mbox

diff --git a/libavcodec/pngdec.c b/libavcodec/pngdec.c
index cad5796545..4ca4f7bdc1 100644
--- a/libavcodec/pngdec.c
+++ b/libavcodec/pngdec.c
@@ -24,6 +24,7 @@ 
 #include "libavutil/avassert.h"
 #include "libavutil/bprint.h"
 #include "libavutil/imgutils.h"
+#include "libavutil/intreadwrite.h"
 #include "libavutil/stereo3d.h"
 #include "libavutil/mastering_display_metadata.h"
 
@@ -1363,19 +1364,38 @@  exit_loop:
         unsigned x, y;
 
         av_assert0(s->bit_depth > 1);
-
         for (y = 0; y < s->height; ++y) {
             uint8_t *row = &s->image_buf[s->image_linesize * y];
 
-            /* since we're updating in-place, we have to go from right to left */
-            for (x = s->width; x > 0; --x) {
-                uint8_t *pixel = &row[s->bpp * (x - 1)];
-                memmove(pixel, &row[raw_bpp * (x - 1)], raw_bpp);
+            if (s->bpp == 2 && byte_depth == 1) {
+                uint8_t *pixel = &row[2 * s->width - 1];
+                uint8_t *rowp  = &row[1 * s->width - 1];
+                int tcolor = s->transparent_color_be[0];
+                for (x = s->width; x > 0; --x) {
+                    *pixel-- = *rowp == tcolor ? 0 : 0xff;
+                    *pixel-- = *rowp--;
+                }
+            } else if (s->bpp == 4 && byte_depth == 1) {
+                uint8_t *pixel = &row[4 * s->width - 1];
+                uint8_t *rowp  = &row[3 * s->width - 1];
+                int tcolor = AV_RL24(s->transparent_color_be);
+                for (x = s->width; x > 0; --x) {
+                    *pixel-- = AV_RL24(rowp-2) == tcolor ? 0 : 0xff;
+                    *pixel-- = *rowp--;
+                    *pixel-- = *rowp--;
+                    *pixel-- = *rowp--;
+                }
+            } else {
+                /* since we're updating in-place, we have to go from right to left */
+                for (x = s->width; x > 0; --x) {
+                    uint8_t *pixel = &row[s->bpp * (x - 1)];
+                    memmove(pixel, &row[raw_bpp * (x - 1)], raw_bpp);
 
-                if (!memcmp(pixel, s->transparent_color_be, raw_bpp)) {
-                    memset(&pixel[raw_bpp], 0, byte_depth);
-                } else {
-                    memset(&pixel[raw_bpp], 0xff, byte_depth);
+                    if (!memcmp(pixel, s->transparent_color_be, raw_bpp)) {
+                        memset(&pixel[raw_bpp], 0, byte_depth);
+                    } else {
+                        memset(&pixel[raw_bpp], 0xff, byte_depth);
+                    }
                 }
             }
         }