Optimize pure C unscaled yuv2rgb.

Aligning the tables reduces the amount of code generated on
e.g. ARM as the offset constant then has few enough set bits
so it can be encoded inside a single instruction instead of 2.
Ideally all should be declared aligned, but the DECLARE_ALIGNED
macros does not work with pointer tables, thus also reordered
the tables.

Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>

libswscale/swscale_internal.h

@@ -362,9 +362,11 @@ typedef struct SwsContext {
     int dstY;                     ///< Last destination vertical line output from last slice.
     int flags;                    ///< Flags passed by the user to select scaler algorithm, optimizations, subsampling, etc...
     void *yuvTable;             // pointer to the yuv->rgb table start so it can be freed()
+    // alignment ensures the offset can be added in a single
+    // instruction on e.g. ARM
+    DECLARE_ALIGNED(16, int, table_gV)[256 + 2*YUVRGB_TABLE_HEADROOM];
     uint8_t *table_rV[256 + 2*YUVRGB_TABLE_HEADROOM];
     uint8_t *table_gU[256 + 2*YUVRGB_TABLE_HEADROOM];
-    int table_gV[256 + 2*YUVRGB_TABLE_HEADROOM];
     uint8_t *table_bU[256 + 2*YUVRGB_TABLE_HEADROOM];
     DECLARE_ALIGNED(16, int32_t, input_rgb2yuv_table)[16+40*4]; // This table can contain both C and SIMD formatted values, teh C vales are always at the XY_IDX points
 #define RY_IDX 0