swscale: Add swscale input support for Y210LE

[ffmpeg] / libswscale / input.c

diff --git a/libswscale/input.c b/libswscale/input.c
index 4099c19c2bc2dbaba15230bfe2fefdd9678e1f41..8346cf4da65757df449b30328d154470cf6b3c6a 100644 (file)
--- a/libswscale/input.c
+++ b/libswscale/input.c
@@ -286,8 +286,8 @@ static av_always_inline void rgb16_32ToUV_c_template(int16_t *dstU,
                                                      int gsh, int bsh, int S,
                                                      int32_t *rgb2yuv)
 {
-    const int ru       = rgb2yuv[RU_IDX] << rsh, gu = rgb2yuv[GU_IDX] << gsh, bu = rgb2yuv[BU_IDX] << bsh,
-              rv       = rgb2yuv[RV_IDX] << rsh, gv = rgb2yuv[GV_IDX] << gsh, bv = rgb2yuv[BV_IDX] << bsh;
+    const int ru       = rgb2yuv[RU_IDX] * (1 << rsh), gu = rgb2yuv[GU_IDX] * (1 << gsh), bu = rgb2yuv[BU_IDX] * (1 << bsh),
+              rv       = rgb2yuv[RV_IDX] * (1 << rsh), gv = rgb2yuv[GV_IDX] * (1 << gsh), bv = rgb2yuv[BV_IDX] * (1 << bsh);
     const unsigned rnd = (256u<<((S)-1)) + (1<<(S-7));
     int i;
 
@@ -314,8 +314,8 @@ static av_always_inline void rgb16_32ToUV_half_c_template(int16_t *dstU,
                                                           int gsh, int bsh, int S,
                                                           int32_t *rgb2yuv)
 {
-    const int ru       = rgb2yuv[RU_IDX] << rsh, gu = rgb2yuv[GU_IDX] << gsh, bu = rgb2yuv[BU_IDX] << bsh,
-              rv       = rgb2yuv[RV_IDX] << rsh, gv = rgb2yuv[GV_IDX] << gsh, bv = rgb2yuv[BV_IDX] << bsh,
+    const int ru       = rgb2yuv[RU_IDX] * (1 << rsh), gu = rgb2yuv[GU_IDX] * (1 << gsh), bu = rgb2yuv[BU_IDX] * (1 << bsh),
+              rv       = rgb2yuv[RV_IDX] * (1 << rsh), gv = rgb2yuv[GV_IDX] * (1 << gsh), bv = rgb2yuv[BV_IDX] * (1 << bsh),
               maskgx   = ~(maskr | maskb);
     const unsigned rnd = (256U<<(S)) + (1<<(S-6));
     int i;
@@ -552,6 +552,24 @@ static void yvy2ToUV_c(uint8_t *dstU, uint8_t *dstV, const uint8_t *unused0, con
     av_assert1(src1 == src2);
 }
 
+static void y210le_UV_c(uint8_t *dstU, uint8_t *dstV, const uint8_t *unused0, const uint8_t *src,
+                        const uint8_t *unused1, int width, uint32_t *unused2)
+{
+    int i;
+    for (i = 0; i < width; i++) {
+        AV_WN16(dstU + i * 2, AV_RL16(src + i * 8 + 2) >> 6);
+        AV_WN16(dstV + i * 2, AV_RL16(src + i * 8 + 6) >> 6);
+    }
+}
+
+static void y210le_Y_c(uint8_t *dst, const uint8_t *src, const uint8_t *unused0,
+                       const uint8_t *unused1, int width, uint32_t *unused2)
+{
+    int i;
+    for (i = 0; i < width; i++)
+        AV_WN16(dst + i * 2, AV_RL16(src + i * 4) >> 6);
+}
+
 static void bswap16Y_c(uint8_t *_dst, const uint8_t *_src, const uint8_t *unused1, const uint8_t *unused2, int width,
                        uint32_t *unused)
 {
@@ -1020,9 +1038,11 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
         c->chrToYV12 = uyvyToUV_c;
         break;
     case AV_PIX_FMT_NV12:
+    case AV_PIX_FMT_NV24:
         c->chrToYV12 = nv12ToUV_c;
         break;
     case AV_PIX_FMT_NV21:
+    case AV_PIX_FMT_NV42:
         c->chrToYV12 = nv21ToUV_c;
         break;
     case AV_PIX_FMT_RGB8:
@@ -1097,6 +1117,8 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUVA420P10LE:
     case AV_PIX_FMT_YUVA422P10LE:
     case AV_PIX_FMT_YUVA444P10LE:
+    case AV_PIX_FMT_YUVA422P12LE:
+    case AV_PIX_FMT_YUVA444P12LE:
     case AV_PIX_FMT_YUVA420P16LE:
     case AV_PIX_FMT_YUVA422P16LE:
     case AV_PIX_FMT_YUVA444P16LE:
@@ -1127,6 +1149,8 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUVA420P10BE:
     case AV_PIX_FMT_YUVA422P10BE:
     case AV_PIX_FMT_YUVA444P10BE:
+    case AV_PIX_FMT_YUVA422P12BE:
+    case AV_PIX_FMT_YUVA444P12BE:
     case AV_PIX_FMT_YUVA420P16BE:
     case AV_PIX_FMT_YUVA422P16BE:
     case AV_PIX_FMT_YUVA444P16BE:
@@ -1148,6 +1172,9 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_P016BE:
         c->chrToYV12 = p016BEToUV_c;
         break;
+    case AV_PIX_FMT_Y210LE:
+        c->chrToYV12 = y210le_UV_c;
+        break;
     }
     if (c->chrSrcHSubSample) {
         switch (srcFormat) {
@@ -1401,6 +1428,8 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUVA420P10LE:
     case AV_PIX_FMT_YUVA422P10LE:
     case AV_PIX_FMT_YUVA444P10LE:
+    case AV_PIX_FMT_YUVA422P12LE:
+    case AV_PIX_FMT_YUVA444P12LE:
     case AV_PIX_FMT_YUVA420P16LE:
     case AV_PIX_FMT_YUVA422P16LE:
     case AV_PIX_FMT_YUVA444P16LE:
@@ -1441,6 +1470,8 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUVA420P10BE:
     case AV_PIX_FMT_YUVA422P10BE:
     case AV_PIX_FMT_YUVA444P10BE:
+    case AV_PIX_FMT_YUVA422P12BE:
+    case AV_PIX_FMT_YUVA444P12BE:
     case AV_PIX_FMT_YUVA420P16BE:
     case AV_PIX_FMT_YUVA422P16BE:
     case AV_PIX_FMT_YUVA444P16BE:
@@ -1576,6 +1607,9 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
         c->lumToYV12 = grayf32ToY16_bswap_c;
 #endif
         break;
+    case AV_PIX_FMT_Y210LE:
+        c->lumToYV12 = y210le_Y_c;
+        break;
     }
     if (c->needAlpha) {
         if (is16BPS(srcFormat) || isNBPS(srcFormat)) {