swscale: Add p016 output support and generalise yuv420p1x to p010

To make the best use of existing code, I generalised the wrapper
that currently does yuv420p10 to p010 to support any mixture of
input and output sizes between 10 and 16 bits. This had the side
effect of yielding a working code path for all yuv420p1x formats
to p01x.

1 files changed, 25 insertions, 10 deletions

diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 5ec2116bcf..766c9b4872 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -180,16 +180,28 @@ static int nv12ToPlanarWrapper(SwsContext *c, const uint8_t *src[],
     return srcSliceH;
 }
 
-static int planarToP010Wrapper(SwsContext *c, const uint8_t *src8[],
+static int planarToP01xWrapper(SwsContext *c, const uint8_t *src8[],
                                int srcStride[], int srcSliceY,
                                int srcSliceH, uint8_t *dstParam8[],
                                int dstStride[])
 {
+    const AVPixFmtDescriptor *src_format = av_pix_fmt_desc_get(c->srcFormat);
+    const AVPixFmtDescriptor *dst_format = av_pix_fmt_desc_get(c->dstFormat);
     const uint16_t **src = (const uint16_t**)src8;
     uint16_t *dstY = (uint16_t*)(dstParam8[0] + dstStride[0] * srcSliceY);
     uint16_t *dstUV = (uint16_t*)(dstParam8[1] + dstStride[1] * srcSliceY / 2);
     int x, y;
 
+    /* Calculate net shift required for values. */
+    const int shift[3] = {
+        dst_format->comp[0].depth + dst_format->comp[0].shift -
+        src_format->comp[0].depth - src_format->comp[0].shift,
+        dst_format->comp[1].depth + dst_format->comp[1].shift -
+        src_format->comp[1].depth - src_format->comp[1].shift,
+        dst_format->comp[2].depth + dst_format->comp[2].shift -
+        src_format->comp[2].depth - src_format->comp[2].shift,
+    };
+
     av_assert0(!(srcStride[0] % 2 || srcStride[1] % 2 || srcStride[2] % 2 ||
                  dstStride[0] % 2 || dstStride[1] % 2));
 
@@ -197,7 +209,7 @@ static int planarToP010Wrapper(SwsContext *c, const uint8_t *src8[],
         uint16_t *tdstY = dstY;
         const uint16_t *tsrc0 = src[0];
         for (x = c->srcW; x > 0; x--) {
-            *tdstY++ = *tsrc0++ << 6;
+            *tdstY++ = *tsrc0++ << shift[0];
         }
         src[0] += srcStride[0] / 2;
         dstY += dstStride[0] / 2;
@@ -207,8 +219,8 @@ static int planarToP010Wrapper(SwsContext *c, const uint8_t *src8[],
             const uint16_t *tsrc1 = src[1];
             const uint16_t *tsrc2 = src[2];
             for (x = c->srcW / 2; x > 0; x--) {
-                *tdstUV++ = *tsrc1++ << 6;
-                *tdstUV++ = *tsrc2++ << 6;
+                *tdstUV++ = *tsrc1++ << shift[1];
+                *tdstUV++ = *tsrc2++ << shift[2];
             }
             src[1] += srcStride[1] / 2;
             src[2] += srcStride[2] / 2;
@@ -1738,14 +1750,17 @@ void ff_get_unscaled_swscale(SwsContext *c)
         !(flags & SWS_ACCURATE_RND) && (c->dither == SWS_DITHER_BAYER || c->dither == SWS_DITHER_AUTO) && !(dstH & 1)) {
         c->swscale = ff_yuv2rgb_get_func_ptr(c);
     }
-    /* yuv420p10_to_p010 */
-    if ((srcFormat == AV_PIX_FMT_YUV420P10 || srcFormat == AV_PIX_FMT_YUVA420P10) &&
-        dstFormat == AV_PIX_FMT_P010) {
-        c->swscale = planarToP010Wrapper;
+    /* yuv420p1x_to_p01x */
+    if ((srcFormat == AV_PIX_FMT_YUV420P10 || srcFormat == AV_PIX_FMT_YUVA420P10 ||
+         srcFormat == AV_PIX_FMT_YUV420P12 ||
+         srcFormat == AV_PIX_FMT_YUV420P14 ||
+         srcFormat == AV_PIX_FMT_YUV420P16 || srcFormat == AV_PIX_FMT_YUVA420P16) &&
+        (dstFormat == AV_PIX_FMT_P010 || dstFormat == AV_PIX_FMT_P016)) {
+        c->swscale = planarToP01xWrapper;
     }
-    /* yuv420p_to_p010le */
+    /* yuv420p_to_p01xle */
     if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) &&
-        dstFormat == AV_PIX_FMT_P010LE) {
+        (dstFormat == AV_PIX_FMT_P010LE || dstFormat == AV_PIX_FMT_P016LE)) {
         c->swscale = planar8ToP01xleWrapper;
     }