avfilter/vf_scale_cuda: Add support for YUV444P16

This format is interesting because it's what you get for decoded
10/12bit HEVC 4:4:4.

libavfilter/version.h

@@ -31,7 +31,7 @@
 
 #define LIBAVFILTER_VERSION_MAJOR   7
 #define LIBAVFILTER_VERSION_MINOR  53
-#define LIBAVFILTER_VERSION_MICRO 100
+#define LIBAVFILTER_VERSION_MICRO 101
 
 #define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \
                                                LIBAVFILTER_VERSION_MINOR, \

libavfilter/vf_scale_cuda.c

@@ -43,7 +43,8 @@ static const enum AVPixelFormat supported_formats[] = {
     AV_PIX_FMT_NV12,
     AV_PIX_FMT_YUV444P,
     AV_PIX_FMT_P010,
-    AV_PIX_FMT_P016
+    AV_PIX_FMT_P016,
+    AV_PIX_FMT_YUV444P16,
 };
 
 #define DIV_UP(a, b) ( ((a) + (b) - 1) / (b) )
@@ -411,6 +412,20 @@ static int scalecuda_resize(AVFilterContext *ctx,
                            out->data[0]+out->linesize[0]*out->height*2, out->width, out->height, out->linesize[0],
                            1);
         break;
+    case AV_PIX_FMT_YUV444P16:
+        call_resize_kernel(ctx, s->cu_func_ushort, 1,
+                           in->data[0], in->width, in->height, in->linesize[0] / 2,
+                           out->data[0], out->width, out->height, out->linesize[0] / 2,
+                           2);
+        call_resize_kernel(ctx, s->cu_func_ushort, 1,
+                           in->data[1], in->width, in->height, in->linesize[1] / 2,
+                           out->data[1], out->width, out->height, out->linesize[1] / 2,
+                           2);
+        call_resize_kernel(ctx, s->cu_func_ushort, 1,
+                           in->data[2], in->width, in->height, in->linesize[2] / 2,
+                           out->data[2], out->width, out->height, out->linesize[2] / 2,
+                           2);
+        break;
     case AV_PIX_FMT_NV12:
         call_resize_kernel(ctx, s->cu_func_uchar, 1,
                            in->data[0], in->width, in->height, in->linesize[0],