summaryrefslogtreecommitdiff
path: root/libavcodec/v210enc.c
diff options
context:
space:
mode:
authorJames Darnley <james.darnley@gmail.com>2016-01-15 18:30:03 +0000
committerJames Darnley <james.darnley@gmail.com>2016-01-17 16:03:43 +0100
commit2cba1825f70c301f5513a799302f755967680651 (patch)
treec39ebf1ac76c35ab1852cd4555fa155b78d77f4d /libavcodec/v210enc.c
parent3836f404a8c0ffd7c565260434768ef4ebba85a7 (diff)
avcodec/v210: add avx2 version of the 10-bit line encoder
Around 25% faster than the ssse3 version.
Diffstat (limited to 'libavcodec/v210enc.c')
-rw-r--r--libavcodec/v210enc.c11
1 files changed, 9 insertions, 2 deletions
diff --git a/libavcodec/v210enc.c b/libavcodec/v210enc.c
index ec63864cc8..00c89dc1d8 100644
--- a/libavcodec/v210enc.c
+++ b/libavcodec/v210enc.c
@@ -135,13 +135,20 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
const uint16_t *v = (const uint16_t *)pic->data[2];
for (h = 0; h < avctx->height; h++) {
uint32_t val;
- w = (avctx->width / 6) * 6;
+ w = (avctx->width / (6 * s->sample_factor)) * 6 * s->sample_factor;
s->pack_line_10(y, u, v, dst, w);
y += w;
u += w >> 1;
v += w >> 1;
- dst += (w / 6) * 16;
+ dst += (w / (6 * s->sample_factor)) * 16 * s->sample_factor;
+
+ for (; w < avctx->width - 5; w += 6) {
+ WRITE_PIXELS(u, y, v);
+ WRITE_PIXELS(y, u, y);
+ WRITE_PIXELS(v, y, u);
+ WRITE_PIXELS(y, v, y);
+ }
if (w < avctx->width - 1) {
WRITE_PIXELS(u, y, v);