hevc/sao: use aligned copies

For band filter, source and destination are aligned (except for 16x16 ctbs),
and otherwise, they are most often aligned. Overall, the total width is also
too small for amortizing memcpy.

Timings (using an intrinsic version of edge filters):
          B/32     B/64     E/32     E/64
Before:  32045    93952    38925    126896
After:   26772    83803    33942    117182

1 files changed, 18 insertions, 8 deletions

diff --git a/libavcodec/hevc_filter.c b/libavcodec/hevc_filter.c
index 9354c14300..7a0ec6d4be 100644
--- a/libavcodec/hevc_filter.c
+++ b/libavcodec/hevc_filter.c
@@ -139,15 +139,25 @@ static int get_qPy(HEVCContext *s, int xC, int yC)
     return s->qp_y_tab[x + y * s->sps->min_cb_width];
 }
 
-static void copy_CTB(uint8_t *dst, uint8_t *src,
-                     int width, int height, int stride_dst, int stride_src)
+static void copy_CTB(uint8_t *dst, uint8_t *src, int width, int height,
+                     intptr_t stride_dst, intptr_t stride_src)
 {
-    int i;
-
-    for (i = 0; i < height; i++) {
-        memcpy(dst, src, width);
-        dst += stride_dst;
-        src += stride_src;
+int i, j;
+
+    if (((intptr_t)dst | (intptr_t)src | stride_dst | stride_src) & 15) {
+        for (i = 0; i < height; i++) {
+            for (j = 0; j < width; j+=8)
+                AV_COPY64(dst+j, src+j);
+            dst += stride_dst;
+            src += stride_src;
+        }
+    } else {
+        for (i = 0; i < height; i++) {
+            for (j = 0; j < width; j+=16)
+                AV_COPY128(dst+j, src+j);
+            dst += stride_dst;
+            src += stride_src;
+        }
     }
 }