[FFmpeg-devel] [PATCH] mdec: use correctly permutated quant matrix for dequantization.

[Ronald S. Bultje]

This allows using non-simple (e.g. simplemmx) IDCT implementations.
The result is not bitexact (which is why the fate test continues to
use -idct simple), but the PSNR between C/MMX goes from ~35 to ~90.
---
 libavcodec/mdec.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/libavcodec/mdec.c b/libavcodec/mdec.c
index 97bfebb..59658b3 100644
--- a/libavcodec/mdec.c
+++ b/libavcodec/mdec.c
@@ -49,6 +49,7 @@ typedef struct MDECContext {
     int mb_height;
     int mb_x, mb_y;
     DECLARE_ALIGNED(16, int16_t, block)[6][64];
+    DECLARE_ALIGNED(16, uint16_t, quant_matrix)[64];
     uint8_t *bitstream_buffer;
     unsigned int bitstream_buffer_size;
     int block_last_index[6];
@@ -61,7 +62,7 @@ static inline int mdec_decode_block_intra(MDECContext *a, int16_t *block, int n)
     int component;
     RLTable *rl = &ff_rl_mpeg1;
     uint8_t * const scantable = a->scantable.permutated;
-    const uint16_t *quant_matrix = ff_mpeg1_default_intra_matrix;
+    const uint16_t *quant_matrix = a->quant_matrix;
     const int qscale = a->qscale;
 
     /* DC coefficient */
@@ -212,9 +213,7 @@ static int decode_frame(AVCodecContext *avctx,
 static av_cold int decode_init(AVCodecContext *avctx)
 {
     MDECContext * const a = avctx->priv_data;
-
-    if (avctx->idct_algo == FF_IDCT_AUTO)
-        avctx->idct_algo = FF_IDCT_SIMPLE;
+    int i;
 
     a->mb_width  = (avctx->coded_width  + 15) / 16;
     a->mb_height = (avctx->coded_height + 15) / 16;
@@ -231,6 +230,13 @@ static av_cold int decode_init(AVCodecContext *avctx)
     avctx->pix_fmt  = AV_PIX_FMT_YUVJ420P;
     avctx->color_range = AVCOL_RANGE_JPEG;
 
+    /* init q matrix */
+    for (i = 0; i < 64; i++) {
+        int j = a->idsp.idct_permutation[i];
+
+        a->quant_matrix[j] = ff_mpeg1_default_intra_matrix[i];
+    }
+
     return 0;
 }
 
-- 
2.8.1