X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fdnxhdenc.c;h=58fd97e339ccac8e01c4e0d1ea7f1bb082b2b358;hb=7ea5dbcb83a502d8152d5c64d32f9a16e7e907c7;hp=fde98d2ba2fa125eb7b13238af4a19ac7700251a;hpb=9db747b2a300380dd65032818155067054332dae;p=ffmpeg

diff --git a/libavcodec/dnxhdenc.c b/libavcodec/dnxhdenc.c
index fde98d2ba2f..58fd97e339c 100644
--- a/libavcodec/dnxhdenc.c
+++ b/libavcodec/dnxhdenc.c
@@ -31,7 +31,6 @@
 #include "dsputil.h"
 #include "internal.h"
 #include "mpegvideo.h"
-#include "mpegvideo_common.h"
 #include "dnxhdenc.h"
 #include "internal.h"
 
@@ -39,7 +38,7 @@
 #define DNX10BIT_QMAT_SHIFT 18 // The largest value that will not lead to overflow for 10bit samples.
 
 static const AVOption options[]={
-    {"nitris_compat", "encode with Avid Nitris compatibility", offsetof(DNXHDEncContext, nitris_compat), AV_OPT_TYPE_INT, {.dbl = 0}, 0, 1, VE},
+    {"nitris_compat", "encode with Avid Nitris compatibility", offsetof(DNXHDEncContext, nitris_compat), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, VE},
 {NULL}
 };
 
@@ -52,7 +51,7 @@ static const AVClass class = {
 
 #define LAMBDA_FRAC_BITS 10
 
-static void dnxhd_8bit_get_pixels_8x4_sym(DCTELEM *restrict block, const uint8_t *pixels, int line_size)
+static void dnxhd_8bit_get_pixels_8x4_sym(DCTELEM *av_restrict block, const uint8_t *pixels, int line_size)
 {
     int i;
     for (i = 0; i < 4; i++) {
@@ -69,16 +68,24 @@ static void dnxhd_8bit_get_pixels_8x4_sym(DCTELEM *restrict block, const uint8_t
     memcpy(block + 24, block - 32, sizeof(*block) * 8);
 }
 
-static av_always_inline void dnxhd_10bit_get_pixels_8x4_sym(DCTELEM *restrict block, const uint8_t *pixels, int line_size)
+static av_always_inline void dnxhd_10bit_get_pixels_8x4_sym(DCTELEM *av_restrict block, const uint8_t *pixels, int line_size)
 {
     int i;
-
-    block += 32;
+    const uint16_t* pixels16 = (const uint16_t*)pixels;
+    line_size >>= 1;
 
     for (i = 0; i < 4; i++) {
-        memcpy(block + i     * 8, pixels + i * line_size, 8 * sizeof(*block));
-        memcpy(block - (i+1) * 8, pixels + i * line_size, 8 * sizeof(*block));
+        block[0] = pixels16[0]; block[1] = pixels16[1];
+        block[2] = pixels16[2]; block[3] = pixels16[3];
+        block[4] = pixels16[4]; block[5] = pixels16[5];
+        block[6] = pixels16[6]; block[7] = pixels16[7];
+        pixels16 += line_size;
+        block += 8;
     }
+    memcpy(block,      block -  8, sizeof(*block) * 8);
+    memcpy(block +  8, block - 16, sizeof(*block) * 8);
+    memcpy(block + 16, block - 24, sizeof(*block) * 8);
+    memcpy(block + 24, block - 32, sizeof(*block) * 8);
 }
 
 static int dnxhd_10bit_dct_quantize(MpegEncContext *ctx, DCTELEM *block,
@@ -287,9 +294,8 @@ static int dnxhd_encode_init(AVCodecContext *avctx)
        ctx->block_width_l2 = 3;
     }
 
-#if HAVE_MMX
-    ff_dnxhd_init_mmx(ctx);
-#endif
+    if (ARCH_X86)
+        ff_dnxhdenc_init_x86(ctx);
 
     ctx->m.mb_height = (avctx->height + 15) / 16;
     ctx->m.mb_width  = (avctx->width  + 15) / 16;
@@ -1008,7 +1014,7 @@ static const AVCodecDefault dnxhd_defaults[] = {
 AVCodec ff_dnxhd_encoder = {
     .name           = "dnxhd",
     .type           = AVMEDIA_TYPE_VIDEO,
-    .id             = CODEC_ID_DNXHD,
+    .id             = AV_CODEC_ID_DNXHD,
     .priv_data_size = sizeof(DNXHDEncContext),
     .init           = dnxhd_encode_init,
     .encode2        = dnxhd_encode_picture,