summaryrefslogtreecommitdiff
path: root/libavcodec/v210enc.c
diff options
context:
space:
mode:
authorJames Darnley <james.darnley@gmail.com>2016-01-15 20:35:06 +0100
committerLuca Barbato <lu_zero@gentoo.org>2016-02-01 13:40:07 +0100
commit15ec7aa4170ed05ad1b17000ef1e3940d0a0c5e7 (patch)
treed6f2196721a51809d931883aa7039096991a112c /libavcodec/v210enc.c
parentd29237e5578a187c5a8d91338cd70ce0fd6f6003 (diff)
v210: Add avx2 version of the 10-bit line encoder
Around 25% faster than the ssse3 version. Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
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 ce690f1634..da0b23f074 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);