v210: Add avx2 version of the 8-bit line encoder

Around 35% faster than the avx version.

Signed-off-by: Henrik Gramner <henrik@gramner.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>

1 files changed, 3 insertions, 2 deletions

diff --git a/libavcodec/v210enc.c b/libavcodec/v210enc.c
index ca6ad2ee2f..ce690f1634 100644
--- a/libavcodec/v210enc.c
+++ b/libavcodec/v210enc.c
@@ -86,6 +86,7 @@ av_cold void ff_v210enc_init(V210EncContext *s)
 {
     s->pack_line_8  = v210_planar_pack_8_c;
     s->pack_line_10 = v210_planar_pack_10_c;
+    s->sample_factor = 1;
 
     if (ARCH_X86)
         ff_v210enc_init_x86(s);
@@ -172,13 +173,13 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
         const uint8_t *v = pic->data[2];
         for (h = 0; h < avctx->height; h++) {
             uint32_t val;
-            w = (avctx->width / 12) * 12;
+            w = (avctx->width / (12 * s->sample_factor)) * 12 * s->sample_factor;
             s->pack_line_8(y, u, v, dst, w);
 
             y += w;
             u += w >> 1;
             v += w >> 1;
-            dst += (w / 12) * 32;
+            dst += (w / (12 * s->sample_factor)) * 32 * s->sample_factor;
 
             for (; w < avctx->width - 5; w += 6) {
                 WRITE_PIXELS8(u, y, v);