swscale: make yuv2interleavedX more asm-friendly

Extracting information from SwsContext in assembly is difficult, and
rearranging SwsContext just for asm access didn't look good. These
functions only need a couple of fields from it anyway, so just make
them parameters in their own right.

Signed-off-by: Nelson Gomez <nelson.gomez@microsoft.com>

libswscale/output.c

@@ -180,7 +180,7 @@ yuv2planeX_16_c_template(const int16_t *filter, int filterSize,
     }
 }
 
-static void yuv2p016cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+static void yuv2p016cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither, const int16_t *chrFilter, int chrFilterSize,
                          const int16_t **chrUSrc, const int16_t **chrVSrc,
                          uint8_t *dest8, int chrDstW)
 {
@@ -188,7 +188,7 @@ static void yuv2p016cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterS
     const int32_t **uSrc = (const int32_t **)chrUSrc;
     const int32_t **vSrc = (const int32_t **)chrVSrc;
     int shift = 15;
-    int big_endian = c->dstFormat == AV_PIX_FMT_P016BE;
+    int big_endian = dstFormat == AV_PIX_FMT_P016BE;
     int i, j;
 
     for (i = 0; i < chrDstW; i++) {
@@ -402,12 +402,10 @@ static void yuv2plane1_8_c(const int16_t *src, uint8_t *dest, int dstW,
     }
 }
 
-static void yuv2nv12cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+static void yuv2nv12cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither, const int16_t *chrFilter, int chrFilterSize,
                         const int16_t **chrUSrc, const int16_t **chrVSrc,
                         uint8_t *dest, int chrDstW)
 {
-    enum AVPixelFormat dstFormat = c->dstFormat;
-    const uint8_t *chrDither = c->chrDither8;
     int i;
 
     if (dstFormat == AV_PIX_FMT_NV12 ||
@@ -477,13 +475,13 @@ static void yuv2p010lX_c(const int16_t *filter, int filterSize,
     }
 }
 
-static void yuv2p010cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+static void yuv2p010cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither, const int16_t *chrFilter, int chrFilterSize,
                          const int16_t **chrUSrc, const int16_t **chrVSrc,
                          uint8_t *dest8, int chrDstW)
 {
     uint16_t *dest = (uint16_t*)dest8;
     int shift = 17;
-    int big_endian = c->dstFormat == AV_PIX_FMT_P010BE;
+    int big_endian = dstFormat == AV_PIX_FMT_P010BE;
     int i, j;
 
     for (i = 0; i < chrDstW; i++) {

libswscale/swscale_internal.h

@@ -119,7 +119,8 @@ typedef void (*yuv2planarX_fn)(const int16_t *filter, int filterSize,
  * Write one line of horizontally scaled chroma to interleaved output
  * with multi-point vertical scaling between input pixels.
  *
- * @param c             SWS scaling context
+ * @param dstFormat     destination pixel format
+ * @param chrDither     ordered dither array of type uint8_t and size 8
  * @param chrFilter     vertical chroma scaling coefficients, 12 bits [0,4096]
  * @param chrUSrc       scaled chroma (U) source data, 15 bits for 8-10-bit
  *                      output, 19 bits for 16-bit output (in int32_t)
@@ -130,7 +131,7 @@ typedef void (*yuv2planarX_fn)(const int16_t *filter, int filterSize,
  *                      output, this is in uint16_t
  * @param dstW          width of chroma planes
  */
-typedef void (*yuv2interleavedX_fn)(struct SwsContext *c,
+typedef void (*yuv2interleavedX_fn)(enum AVPixelFormat dstFormat, const uint8_t *chrDither,
                                     const int16_t *chrFilter,
                                     int chrFilterSize,
                                     const int16_t **chrUSrc,

libswscale/vscale.c

@@ -92,7 +92,7 @@ static int chr_planar_vscale(SwsContext *c, SwsFilterDescriptor *desc, int slice
         uint16_t *filter = inst->filter[0] + (inst->isMMX ? 0 : chrSliceY * inst->filter_size);
 
         if (c->yuv2nv12cX) {
-            inst->pfn.yuv2interleavedX(c, filter, inst->filter_size, (const int16_t**)src1, (const int16_t**)src2, dst1[0], dstW);
+            inst->pfn.yuv2interleavedX(c->dstFormat, c->chrDither8, filter, inst->filter_size, (const int16_t**)src1, (const int16_t**)src2, dst1[0], dstW);
         } else if (inst->filter_size == 1) {
             inst->pfn.yuv2planar1((const int16_t*)src1[0], dst1[0], dstW, c->chrDither8, 0);
             inst->pfn.yuv2planar1((const int16_t*)src2[0], dst2[0], dstW, c->chrDither8, 3);