libswscale: Adds conversions from/to float gray format.

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

7 files changed, 226 insertions, 4 deletions

diff --git a/libswscale/input.c b/libswscale/input.c
index 3fd3a5d81e..4099c19c2b 100644
--- a/libswscale/input.c
+++ b/libswscale/input.c
@@ -942,6 +942,30 @@ static av_always_inline void planar_rgb16_to_uv(uint8_t *_dstU, uint8_t *_dstV,
 }
 #undef rdpx
 
+static av_always_inline void grayf32ToY16_c(uint8_t *_dst, const uint8_t *_src, const uint8_t *unused1,
+                                            const uint8_t *unused2, int width, uint32_t *unused)
+{
+    int i;
+    const float *src = (const float *)_src;
+    uint16_t *dst    = (uint16_t *)_dst;
+
+    for (i = 0; i < width; ++i){
+        dst[i] = av_clip_uint16(lrintf(65535.0f * src[i]));
+    }
+}
+
+static av_always_inline void grayf32ToY16_bswap_c(uint8_t *_dst, const uint8_t *_src, const uint8_t *unused1,
+                                                  const uint8_t *unused2, int width, uint32_t *unused)
+{
+    int i;
+    const uint32_t *src = (const uint32_t *)_src;
+    uint16_t *dst    = (uint16_t *)_dst;
+
+    for (i = 0; i < width; ++i){
+        dst[i] = av_clip_uint16(lrintf(65535.0f * av_int2float(av_bswap32(src[i]))));
+    }
+}
+
 #define rgb9plus_planar_funcs_endian(nbits, endian_name, endian)                                    \
 static void planar_rgb##nbits##endian_name##_to_y(uint8_t *dst, const uint8_t *src[4],              \
                                                   int w, int32_t *rgb2yuv)                          \
@@ -1538,6 +1562,20 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_P010BE:
         c->lumToYV12 = p010BEToY_c;
         break;
+    case AV_PIX_FMT_GRAYF32LE:
+#if HAVE_BIGENDIAN
+        c->lumToYV12 = grayf32ToY16_bswap_c;
+#else
+        c->lumToYV12 = grayf32ToY16_c;
+#endif
+        break;
+    case AV_PIX_FMT_GRAYF32BE:
+#if HAVE_BIGENDIAN
+        c->lumToYV12 = grayf32ToY16_c;
+#else
+        c->lumToYV12 = grayf32ToY16_bswap_c;
+#endif
+        break;
     }
     if (c->needAlpha) {
         if (is16BPS(srcFormat) || isNBPS(srcFormat)) {
diff --git a/libswscale/output.c b/libswscale/output.c
index 0af2fffea4..de8637aa3b 100644
--- a/libswscale/output.c
+++ b/libswscale/output.c
@@ -208,6 +208,105 @@ static void yuv2p016cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterS
     }
 }
 
+static av_always_inline void
+yuv2plane1_float_c_template(const int32_t *src, float *dest, int dstW)
+{
+    static const int big_endian = HAVE_BIGENDIAN;
+    static const int shift = 3;
+    static const float float_mult = 1.0f / 65535.0f;
+    int i, val;
+    uint16_t val_uint;
+
+    for (i = 0; i < dstW; ++i){
+        val = src[i] + (1 << (shift - 1));
+        output_pixel(&val_uint, val, 0, uint);
+        dest[i] = float_mult * (float)val_uint;
+    }
+}
+
+static av_always_inline void
+yuv2plane1_float_bswap_c_template(const int32_t *src, uint32_t *dest, int dstW)
+{
+    static const int big_endian = HAVE_BIGENDIAN;
+    static const int shift = 3;
+    static const float float_mult = 1.0f / 65535.0f;
+    int i, val;
+    uint16_t val_uint;
+
+    for (i = 0; i < dstW; ++i){
+        val = src[i] + (1 << (shift - 1));
+        output_pixel(&val_uint, val, 0, uint);
+        dest[i] = av_bswap32(av_float2int(float_mult * (float)val_uint));
+    }
+}
+
+static av_always_inline void
+yuv2planeX_float_c_template(const int16_t *filter, int filterSize, const int32_t **src,
+                            float *dest, int dstW)
+{
+    static const int big_endian = HAVE_BIGENDIAN;
+    static const int shift = 15;
+    static const float float_mult = 1.0f / 65535.0f;
+    int i, j, val;
+    uint16_t val_uint;
+
+    for (i = 0; i < dstW; ++i){
+        val = (1 << (shift - 1)) - 0x40000000;
+        for (j = 0; j < filterSize; ++j){
+            val += src[j][i] * (unsigned)filter[j];
+        }
+        output_pixel(&val_uint, val, 0x8000, int);
+        dest[i] = float_mult * (float)val_uint;
+    }
+}
+
+static av_always_inline void
+yuv2planeX_float_bswap_c_template(const int16_t *filter, int filterSize, const int32_t **src,
+                            uint32_t *dest, int dstW)
+{
+    static const int big_endian = HAVE_BIGENDIAN;
+    static const int shift = 15;
+    static const float float_mult = 1.0f / 65535.0f;
+    int i, j, val;
+    uint16_t val_uint;
+
+    for (i = 0; i < dstW; ++i){
+        val = (1 << (shift - 1)) - 0x40000000;
+        for (j = 0; j < filterSize; ++j){
+            val += src[j][i] * (unsigned)filter[j];
+        }
+        output_pixel(&val_uint, val, 0x8000, int);
+        dest[i] = av_bswap32(av_float2int(float_mult * (float)val_uint));
+    }
+}
+
+#define yuv2plane1_float(template, dest_type, BE_LE) \
+static void yuv2plane1_float ## BE_LE ## _c(const int16_t *src, uint8_t *dest, int dstW, \
+                                            const uint8_t *dither, int offset) \
+{ \
+    template((const int32_t *)src, (dest_type *)dest, dstW); \
+}
+
+#define yuv2planeX_float(template, dest_type, BE_LE) \
+static void yuv2planeX_float ## BE_LE ## _c(const int16_t *filter, int filterSize, \
+                                            const int16_t **src, uint8_t *dest, int dstW, \
+                                            const uint8_t *dither, int offset) \
+{ \
+    template(filter, filterSize, (const int32_t **)src, (dest_type *)dest, dstW); \
+}
+
+#if HAVE_BIGENDIAN
+yuv2plane1_float(yuv2plane1_float_c_template,       float,    BE)
+yuv2plane1_float(yuv2plane1_float_bswap_c_template, uint32_t, LE)
+yuv2planeX_float(yuv2planeX_float_c_template,       float,    BE)
+yuv2planeX_float(yuv2planeX_float_bswap_c_template, uint32_t, LE)
+#else
+yuv2plane1_float(yuv2plane1_float_c_template,       float,    LE)
+yuv2plane1_float(yuv2plane1_float_bswap_c_template, uint32_t, BE)
+yuv2planeX_float(yuv2planeX_float_c_template,       float,    LE)
+yuv2planeX_float(yuv2planeX_float_bswap_c_template, uint32_t, BE)
+#endif
+
 #undef output_pixel
 
 #define output_pixel(pos, val) \
@@ -2303,6 +2402,12 @@ av_cold void ff_sws_init_output_funcs(SwsContext *c,
             *yuv2plane1 = isBE(dstFormat) ? yuv2plane1_14BE_c  : yuv2plane1_14LE_c;
         } else
             av_assert0(0);
+    } else if (dstFormat == AV_PIX_FMT_GRAYF32BE) {
+        *yuv2planeX = yuv2planeX_floatBE_c;
+        *yuv2plane1 = yuv2plane1_floatBE_c;
+    } else if (dstFormat == AV_PIX_FMT_GRAYF32LE) {
+        *yuv2planeX = yuv2planeX_floatLE_c;
+        *yuv2plane1 = yuv2plane1_floatLE_c;
     } else {
         *yuv2plane1 = yuv2plane1_8_c;
         *yuv2planeX = yuv2planeX_8_c;
diff --git a/libswscale/ppc/swscale_altivec.c b/libswscale/ppc/swscale_altivec.c
index 9438a63ff2..2fb2337769 100644
--- a/libswscale/ppc/swscale_altivec.c
+++ b/libswscale/ppc/swscale_altivec.c
@@ -339,6 +339,7 @@ av_cold void ff_sws_init_swscale_ppc(SwsContext *c)
     }
     if (!is16BPS(dstFormat) && !isNBPS(dstFormat) &&
         dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
+        dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE &&
         !c->needAlpha) {
         c->yuv2planeX = yuv2planeX_altivec;
     }
diff --git a/libswscale/swscale_internal.h b/libswscale/swscale_internal.h
index 1703856ab2..4fa59386a6 100644
--- a/libswscale/swscale_internal.h
+++ b/libswscale/swscale_internal.h
@@ -336,6 +336,8 @@ typedef struct SwsContext {
     uint32_t pal_yuv[256];
     uint32_t pal_rgb[256];
 
+    float uint2float_lut[256];
+
     /**
      * @name Scaled horizontal lines ring buffer.
      * The horizontal scaler keeps just enough scaled lines in a ring buffer
@@ -764,6 +766,13 @@ static av_always_inline int isAnyRGB(enum AVPixelFormat pix_fmt)
             pix_fmt == AV_PIX_FMT_MONOBLACK || pix_fmt == AV_PIX_FMT_MONOWHITE;
 }
 
+static av_always_inline int isFloat(enum AVPixelFormat pix_fmt)
+{
+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(pix_fmt);
+    av_assert0(desc);
+    return desc->flags & AV_PIX_FMT_FLAG_FLOAT;
+}
+
 static av_always_inline int isALPHA(enum AVPixelFormat pix_fmt)
 {
     const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(pix_fmt);
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 6480070cbf..973fa4875f 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -1467,6 +1467,46 @@ static int yvu9ToYv12Wrapper(SwsContext *c, const uint8_t *src[],
     return srcSliceH;
 }
 
+static int uint_y_to_float_y_wrapper(SwsContext *c, const uint8_t *src[],
+                                     int srcStride[], int srcSliceY,
+                                     int srcSliceH, uint8_t *dst[], int dstStride[])
+{
+    int y, x;
+    ptrdiff_t dstStrideFloat = dstStride[0] >> 2;
+    const uint8_t *srcPtr = src[0];
+    float *dstPtr = (float *)(dst[0] + dstStride[0] * srcSliceY);
+
+    for (y = 0; y < srcSliceH; ++y){
+        for (x = 0; x < c->srcW; ++x){
+            dstPtr[x] = c->uint2float_lut[srcPtr[x]];
+        }
+        srcPtr += srcStride[0];
+        dstPtr += dstStrideFloat;
+    }
+
+    return srcSliceH;
+}
+
+static int float_y_to_uint_y_wrapper(SwsContext *c, const uint8_t* src[],
+                                     int srcStride[], int srcSliceY,
+                                     int srcSliceH, uint8_t* dst[], int dstStride[])
+{
+    int y, x;
+    ptrdiff_t srcStrideFloat = srcStride[0] >> 2;
+    const float *srcPtr = (const float *)src[0];
+    uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
+
+    for (y = 0; y < srcSliceH; ++y){
+        for (x = 0; x < c->srcW; ++x){
+            dstPtr[x] = av_clip_uint8(lrintf(255.0f * srcPtr[x]));
+        }
+        srcPtr += srcStrideFloat;
+        dstPtr += dstStride[0];
+    }
+
+    return srcSliceH;
+}
+
 /* unscaled copy like stuff (assumes nearly identical formats) */
 static int packedCopyWrapper(SwsContext *c, const uint8_t *src[],
                              int srcStride[], int srcSliceY, int srcSliceH,
@@ -1899,6 +1939,16 @@ void ff_get_unscaled_swscale(SwsContext *c)
             c->swscale = yuv422pToUyvyWrapper;
     }
 
+    /* uint Y to float Y */
+    if (srcFormat == AV_PIX_FMT_GRAY8 && dstFormat == AV_PIX_FMT_GRAYF32){
+        c->swscale = uint_y_to_float_y_wrapper;
+    }
+
+    /* float Y to uint Y */
+    if (srcFormat == AV_PIX_FMT_GRAYF32 && dstFormat == AV_PIX_FMT_GRAY8){
+        c->swscale = float_y_to_uint_y_wrapper;
+    }
+
     /* LQ converters if -sws 0 or -sws 4*/
     if (c->flags&(SWS_FAST_BILINEAR|SWS_POINT)) {
         /* yv12_to_yuy2 */
@@ -1925,13 +1975,13 @@ void ff_get_unscaled_swscale(SwsContext *c)
     if ( srcFormat == dstFormat ||
         (srcFormat == AV_PIX_FMT_YUVA420P && dstFormat == AV_PIX_FMT_YUV420P) ||
         (srcFormat == AV_PIX_FMT_YUV420P && dstFormat == AV_PIX_FMT_YUVA420P) ||
-        (isPlanarYUV(srcFormat) && isPlanarGray(dstFormat)) ||
+        (isFloat(srcFormat) == isFloat(dstFormat)) && ((isPlanarYUV(srcFormat) && isPlanarGray(dstFormat)) ||
         (isPlanarYUV(dstFormat) && isPlanarGray(srcFormat)) ||
         (isPlanarGray(dstFormat) && isPlanarGray(srcFormat)) ||
         (isPlanarYUV(srcFormat) && isPlanarYUV(dstFormat) &&
          c->chrDstHSubSample == c->chrSrcHSubSample &&
          c->chrDstVSubSample == c->chrSrcVSubSample &&
-         !isSemiPlanarYUV(srcFormat) && !isSemiPlanarYUV(dstFormat)))
+         !isSemiPlanarYUV(srcFormat) && !isSemiPlanarYUV(dstFormat))))
     {
         if (isPacked(c->srcFormat))
             c->swscale = packedCopyWrapper;
diff --git a/libswscale/utils.c b/libswscale/utils.c
index 61b47182f8..5e56371180 100644
--- a/libswscale/utils.c
+++ b/libswscale/utils.c
@@ -258,6 +258,8 @@ static const FormatEntry format_entries[AV_PIX_FMT_NB] = {
     [AV_PIX_FMT_P010BE]      = { 1, 1 },
     [AV_PIX_FMT_P016LE]      = { 1, 1 },
     [AV_PIX_FMT_P016BE]      = { 1, 1 },
+    [AV_PIX_FMT_GRAYF32LE]   = { 1, 1 },
+    [AV_PIX_FMT_GRAYF32BE]   = { 1, 1 },
 };
 
 int sws_isSupportedInput(enum AVPixelFormat pix_fmt)
@@ -1173,6 +1175,7 @@ av_cold int sws_init_context(SwsContext *c, SwsFilter *srcFilter,
     const AVPixFmtDescriptor *desc_dst;
     int ret = 0;
     enum AVPixelFormat tmpFmt;
+    static const float float_mult = 1.0f / 255.0f;
 
     cpu_flags = av_get_cpu_flags();
     flags     = c->flags;
@@ -1537,6 +1540,19 @@ av_cold int sws_init_context(SwsContext *c, SwsFilter *srcFilter,
         }
     }
 
+    if (unscaled && c->srcBpc == 8 && dstFormat == AV_PIX_FMT_GRAYF32){
+        for (i = 0; i < 256; ++i){
+            c->uint2float_lut[i] = (float)i * float_mult;
+        }
+    }
+
+    // float will be converted to uint16_t
+    if ((srcFormat == AV_PIX_FMT_GRAYF32BE || srcFormat == AV_PIX_FMT_GRAYF32LE) &&
+        (!unscaled || unscaled && dstFormat != srcFormat && (srcFormat != AV_PIX_FMT_GRAYF32 ||
+        dstFormat != AV_PIX_FMT_GRAY8))){
+        c->srcBpc = 16;
+    }
+
     if (CONFIG_SWSCALE_ALPHA && isALPHA(srcFormat) && !isALPHA(dstFormat)) {
         enum AVPixelFormat tmpFormat = alphaless_fmt(srcFormat);
 
@@ -1793,7 +1809,9 @@ av_cold int sws_init_context(SwsContext *c, SwsFilter *srcFilter,
 
     /* unscaled special cases */
     if (unscaled && !usesHFilter && !usesVFilter &&
-        (c->srcRange == c->dstRange || isAnyRGB(dstFormat))) {
+        (c->srcRange == c->dstRange || isAnyRGB(dstFormat) ||
+         srcFormat == AV_PIX_FMT_GRAYF32 && dstFormat == AV_PIX_FMT_GRAY8 ||
+         srcFormat == AV_PIX_FMT_GRAY8 && dstFormat == AV_PIX_FMT_GRAYF32)) {
         ff_get_unscaled_swscale(c);
 
         if (c->swscale) {
diff --git a/libswscale/x86/swscale_template.c b/libswscale/x86/swscale_template.c
index b8bdcd4d03..7c30470679 100644
--- a/libswscale/x86/swscale_template.c
+++ b/libswscale/x86/swscale_template.c
@@ -1500,7 +1500,8 @@ static av_cold void RENAME(sws_init_swscale)(SwsContext *c)
 
     c->use_mmx_vfilter= 0;
     if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && dstFormat != AV_PIX_FMT_NV12
-        && dstFormat != AV_PIX_FMT_NV21 && !(c->flags & SWS_BITEXACT)) {
+        && dstFormat != AV_PIX_FMT_NV21 && dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE
+        && !(c->flags & SWS_BITEXACT)) {
             if (c->flags & SWS_ACCURATE_RND) {
                 if (!(c->flags & SWS_FULL_CHR_H_INT)) {
                     switch (c->dstFormat) {