Commit 04e41665 authored by Derek Buitenhuis's avatar Derek Buitenhuis

Merge commit 'e280fe13'

* commit 'e280fe13':
  v210: Use separate sample_factors
Merged-by: 's avatarDerek Buitenhuis <derek.buitenhuis@gmail.com>
parents 6bff2b5f e280fe13
...@@ -86,7 +86,8 @@ av_cold void ff_v210enc_init(V210EncContext *s) ...@@ -86,7 +86,8 @@ av_cold void ff_v210enc_init(V210EncContext *s)
{ {
s->pack_line_8 = v210_planar_pack_8_c; s->pack_line_8 = v210_planar_pack_8_c;
s->pack_line_10 = v210_planar_pack_10_c; s->pack_line_10 = v210_planar_pack_10_c;
s->sample_factor = 1; s->sample_factor_8 = 1;
s->sample_factor_10 = 1;
if (ARCH_X86) if (ARCH_X86)
ff_v210enc_init_x86(s); ff_v210enc_init_x86(s);
...@@ -133,15 +134,19 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt, ...@@ -133,15 +134,19 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
const uint16_t *y = (const uint16_t *)pic->data[0]; const uint16_t *y = (const uint16_t *)pic->data[0];
const uint16_t *u = (const uint16_t *)pic->data[1]; const uint16_t *u = (const uint16_t *)pic->data[1];
const uint16_t *v = (const uint16_t *)pic->data[2]; const uint16_t *v = (const uint16_t *)pic->data[2];
const int sample_size = 6 * s->sample_factor_10;
const int sample_w = avctx->width / sample_size;
for (h = 0; h < avctx->height; h++) { for (h = 0; h < avctx->height; h++) {
uint32_t val; uint32_t val;
w = (avctx->width / (6 * s->sample_factor)) * 6 * s->sample_factor; w = sample_w * sample_size;
s->pack_line_10(y, u, v, dst, w); s->pack_line_10(y, u, v, dst, w);
y += w; y += w;
u += w >> 1; u += w >> 1;
v += w >> 1; v += w >> 1;
dst += (w / (6 * s->sample_factor)) * 16 * s->sample_factor; dst += sample_w * 16 * s->sample_factor_10;
for (; w < avctx->width - 5; w += 6) { for (; w < avctx->width - 5; w += 6) {
WRITE_PIXELS(u, y, v); WRITE_PIXELS(u, y, v);
...@@ -178,15 +183,19 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt, ...@@ -178,15 +183,19 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
const uint8_t *y = pic->data[0]; const uint8_t *y = pic->data[0];
const uint8_t *u = pic->data[1]; const uint8_t *u = pic->data[1];
const uint8_t *v = pic->data[2]; const uint8_t *v = pic->data[2];
const int sample_size = 12 * s->sample_factor_8;
const int sample_w = avctx->width / sample_size;
for (h = 0; h < avctx->height; h++) { for (h = 0; h < avctx->height; h++) {
uint32_t val; uint32_t val;
w = (avctx->width / (12 * s->sample_factor)) * 12 * s->sample_factor; w = sample_w * sample_size;
s->pack_line_8(y, u, v, dst, w); s->pack_line_8(y, u, v, dst, w);
y += w; y += w;
u += w >> 1; u += w >> 1;
v += w >> 1; v += w >> 1;
dst += (w / (12 * s->sample_factor)) * 32 * s->sample_factor; dst += sample_w * 32 * s->sample_factor_8;
for (; w < avctx->width - 5; w += 6) { for (; w < avctx->width - 5; w += 6) {
WRITE_PIXELS8(u, y, v); WRITE_PIXELS8(u, y, v);
......
...@@ -28,8 +28,8 @@ typedef struct V210EncContext { ...@@ -28,8 +28,8 @@ typedef struct V210EncContext {
const uint8_t *v, uint8_t *dst, ptrdiff_t width); const uint8_t *v, uint8_t *dst, ptrdiff_t width);
void (*pack_line_10)(const uint16_t *y, const uint16_t *u, void (*pack_line_10)(const uint16_t *y, const uint16_t *u,
const uint16_t *v, uint8_t *dst, ptrdiff_t width); const uint16_t *v, uint8_t *dst, ptrdiff_t width);
int sample_factor; /* This value must be the same for both 8-and 10-bit int sample_factor_8;
functions otherwise the output will be incorrect. */ int sample_factor_10;
} V210EncContext; } V210EncContext;
void ff_v210enc_init(V210EncContext *s); void ff_v210enc_init(V210EncContext *s);
......
...@@ -45,9 +45,10 @@ av_cold void ff_v210enc_init_x86(V210EncContext *s) ...@@ -45,9 +45,10 @@ av_cold void ff_v210enc_init_x86(V210EncContext *s)
if (EXTERNAL_AVX(cpu_flags)) if (EXTERNAL_AVX(cpu_flags))
s->pack_line_8 = ff_v210_planar_pack_8_avx; s->pack_line_8 = ff_v210_planar_pack_8_avx;
if (EXTERNAL_AVX2_FAST(cpu_flags)) { if (EXTERNAL_AVX2(cpu_flags)) {
s->pack_line_8 = ff_v210_planar_pack_8_avx2; s->sample_factor_8 = 2;
s->pack_line_10 = ff_v210_planar_pack_10_avx2; s->pack_line_8 = ff_v210_planar_pack_8_avx2;
s->sample_factor = 2; s->sample_factor_10 = 2;
s->pack_line_10 = ff_v210_planar_pack_10_avx2;
} }
} }
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment