[FFmpeg-devel] [PATCH 4/4] avcodec/pngdec: use memcpy instead of byte loops for P frames.

[Benoit Fouet]

Rely on the way memcpy is optimized for one's system instead of looping
on a byte buffer for buffer copies to handle P frames.
---
 libavcodec/pngdec.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/libavcodec/pngdec.c b/libavcodec/pngdec.c
index 7e7b285..8b004bd 100644
--- a/libavcodec/pngdec.c
+++ b/libavcodec/pngdec.c
@@ -844,15 +844,14 @@ static int decode_fctl_chunk(AVCodecContext *avctx, PNGDecContext *s,
 
 static void handle_p_frame_png(PNGDecContext *s, AVFrame *p)
 {
-    int i, j;
+    int j;
     uint8_t *pd      = p->data[0];
     uint8_t *pd_last = s->last_picture.f->data[0];
     int ls = FFMIN(av_image_get_linesize(p->format, s->width, 0), s->width * s->bpp);
 
     ff_thread_await_progress(&s->last_picture, INT_MAX, 0);
     for (j = 0; j < s->height; j++) {
-        for (i = 0; i < ls; i++)
-            pd[i] += pd_last[i];
+        memcpy(pd, pd_last, ls);
         pd      += s->image_linesize;
         pd_last += s->image_linesize;
     }
@@ -884,8 +883,7 @@ static int handle_p_frame_apng(AVCodecContext *avctx, PNGDecContext *s,
         ff_thread_await_progress(&s->previous_picture, INT_MAX, 0);
 
     for (j = 0; j < s->y_offset; j++) {
-        for (i = 0; i < ls; i++)
-            pd[i] = pd_last[i];
+        memcpy(pd, pd_last, ls);
         pd      += s->image_linesize;
         pd_last += s->image_linesize;
     }
@@ -907,8 +905,9 @@ static int handle_p_frame_apng(AVCodecContext *avctx, PNGDecContext *s,
         }
 
         for (j = s->y_offset; j < s->y_offset + s->cur_h; j++) {
-            for (i = 0; i < s->x_offset * s->bpp; i++)
-                pd[i] = pd_last[i];
+            i = s->x_offset * s->bpp;
+            if (i)
+                memcpy(pd, pd_last, i);
             for (; i < (s->x_offset + s->cur_w) * s->bpp; i += s->bpp) {
                 uint8_t alpha = pd[i+ai];
 
@@ -930,26 +929,27 @@ static int handle_p_frame_apng(AVCodecContext *avctx, PNGDecContext *s,
                     break;
                 }
             }
-            for (; i < ls; i++)
-                pd[i] = pd_last[i];
+            if (ls - i)
+                memcpy(pd+i, pd_last+i, ls - i);
             pd      += s->image_linesize;
             pd_last += s->image_linesize;
             pd_last_region += s->image_linesize;
         }
     } else {
         for (j = s->y_offset; j < s->y_offset + s->cur_h; j++) {
-            for (i = 0; i < s->x_offset * s->bpp; i++)
-                pd[i] = pd_last[i];
-            for (i = (s->x_offset + s->cur_w) * s->bpp; i < ls; i++)
-                pd[i] = pd_last[i];
+            int end_offset = (s->x_offset + s->cur_w) * s->bpp;
+            int end_len    = ls - end_offset;
+            if (s->x_offset)
+                memcpy(pd, pd_last, s->x_offset * s->bpp);
+            if (end_len)
+                memcpy(pd+end_offset, pd_last+end_offset, end_len);
             pd      += s->image_linesize;
             pd_last += s->image_linesize;
         }
     }
 
     for (j = s->y_offset + s->cur_h; j < s->height; j++) {
-        for (i = 0; i < ls; i++)
-            pd[i] = pd_last[i];
+        memcpy(pd, pd_last, ls);
         pd      += s->image_linesize;
         pd_last += s->image_linesize;
     }
-- 
2.2.0