Revert r31153. It failed to build on:

x86_64 / Mac OS X gcc 4.0.1
x86_64 / Linux icc (all)
x86_64 / Linux gcc 4.0.4
x86_64 / OpenBSD gcc 3.3.5
x86_64 / Linux suncc 5.10
and there are some reports of crashes.


git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@31170 b3059339-0415-0410-9bf9-f77b7e298cf2

6 files changed, 55 insertions, 57 deletions

diff --git a/libswscale/bfin/internal_bfin.S b/libswscale/bfin/internal_bfin.S
index cb8d71253c..5af46540a8 100644
--- a/libswscale/bfin/internal_bfin.S
+++ b/libswscale/bfin/internal_bfin.S
@@ -466,8 +466,8 @@ DEFUN_END(yuv2rgb24_line)
 #define ARG_srcStride   40
 
 DEFUN(uyvytoyv12, mL3,  (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                         int width, int height,
-                         int lumStride, int chromStride, int srcStride)):
+                         long width, long height,
+                         long lumStride, long chromStride, long srcStride)):
         link 0;
         [--sp] = (r7:4,p5:4);
 
@@ -539,8 +539,8 @@ DEFUN(uyvytoyv12, mL3,  (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8
 DEFUN_END(uyvytoyv12)
 
 DEFUN(yuyvtoyv12, mL3,  (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                         int width, int height,
-                         int lumStride, int chromStride, int srcStride)):
+                         long width, long height,
+                         long lumStride, long chromStride, long srcStride)):
         link 0;
         [--sp] = (r7:4,p5:4);
 
diff --git a/libswscale/bfin/swscale_bfin.c b/libswscale/bfin/swscale_bfin.c
index 6c64d143a9..ce2f1720dd 100644
--- a/libswscale/bfin/swscale_bfin.c
+++ b/libswscale/bfin/swscale_bfin.c
@@ -38,12 +38,12 @@
 #endif
 
 int ff_bfin_uyvytoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                       int width, int height,
-                       int lumStride, int chromStride, int srcStride) L1CODE;
+                       long width, long height,
+                       long lumStride, long chromStride, long srcStride) L1CODE;
 
 int ff_bfin_yuyvtoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                       int width, int height,
-                       int lumStride, int chromStride, int srcStride) L1CODE;
+                       long width, long height,
+                       long lumStride, long chromStride, long srcStride) L1CODE;
 
 static int uyvytoyv12_unscaled(SwsContext *c, uint8_t* src[], int srcStride[], int srcSliceY,
                                int srcSliceH, uint8_t* dst[], int dstStride[])
diff --git a/libswscale/colorspace-test.c b/libswscale/colorspace-test.c
index 242973d0f2..5a48065d1f 100644
--- a/libswscale/colorspace-test.c
+++ b/libswscale/colorspace-test.c
@@ -79,7 +79,7 @@ int main(int argc, char **argv)
             int src_bpp;
             int dst_bpp;
             const char *name;
-            void (*func)(const uint8_t *src, uint8_t *dst, int src_size);
+            void (*func)(const uint8_t *src, uint8_t *dst, long src_size);
         } func_info[] = {
             FUNC(2, 2, rgb15to16),
             FUNC(2, 3, rgb15to24),
diff --git a/libswscale/swscale.c b/libswscale/swscale.c
index 623d8498dd..2b02dd3dfd 100644
--- a/libswscale/swscale.c
+++ b/libswscale/swscale.c
@@ -1040,7 +1040,7 @@ static inline void rgb48ToUV_half(uint8_t *dstU, uint8_t *dstV,
 }
 
 #define BGR2Y(type, name, shr, shg, shb, maskr, maskg, maskb, RY, GY, BY, S)\
-static inline void name(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)\
+static inline void name(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)\
 {\
     int i;\
     for (i=0; i<width; i++) {\
@@ -1059,7 +1059,7 @@ BGR2Y(uint16_t, bgr15ToY, 0, 0, 0, 0x001F, 0x03E0, 0x7C00, RY<<10, GY<<5, BY
 BGR2Y(uint16_t, rgb16ToY, 0, 0, 0, 0xF800, 0x07E0, 0x001F, RY    , GY<<5, BY<<11, RGB2YUV_SHIFT+8)
 BGR2Y(uint16_t, rgb15ToY, 0, 0, 0, 0x7C00, 0x03E0, 0x001F, RY    , GY<<5, BY<<10, RGB2YUV_SHIFT+7)
 
-static inline void abgrToA(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void abgrToA(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
     int i;
     for (i=0; i<width; i++) {
@@ -1068,7 +1068,7 @@ static inline void abgrToA(uint8_t *dst, const uint8_t *src, int width, uint32_t
 }
 
 #define BGR2UV(type, name, shr, shg, shb, maska, maskr, maskg, maskb, RU, GU, BU, RV, GV, BV, S)\
-static inline void name(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, const uint8_t *dummy, int width, uint32_t *unused)\
+static inline void name(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, const uint8_t *dummy, long width, uint32_t *unused)\
 {\
     int i;\
     for (i=0; i<width; i++) {\
@@ -1080,7 +1080,7 @@ static inline void name(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, const
         dstV[i]= ((RV)*r + (GV)*g + (BV)*b + (257<<((S)-1)))>>(S);\
     }\
 }\
-static inline void name ## _half(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, const uint8_t *dummy, int width, uint32_t *unused)\
+static inline void name ## _half(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, const uint8_t *dummy, long width, uint32_t *unused)\
 {\
     int i;\
     for (i=0; i<width; i++) {\
@@ -1105,7 +1105,7 @@ BGR2UV(uint16_t, bgr15ToUV, 0, 0, 0,          0,   0x001F, 0x03E0,   0x7C00, RU<
 BGR2UV(uint16_t, rgb16ToUV, 0, 0, 0,          0,   0xF800, 0x07E0,   0x001F, RU    , GU<<5, BU<<11, RV    , GV<<5, BV<<11, RGB2YUV_SHIFT+8)
 BGR2UV(uint16_t, rgb15ToUV, 0, 0, 0,          0,   0x7C00, 0x03E0,   0x001F, RU    , GU<<5, BU<<10, RV    , GV<<5, BV<<10, RGB2YUV_SHIFT+7)
 
-static inline void palToY(uint8_t *dst, const uint8_t *src, int width, uint32_t *pal)
+static inline void palToY(uint8_t *dst, const uint8_t *src, long width, uint32_t *pal)
 {
     int i;
     for (i=0; i<width; i++) {
@@ -1117,7 +1117,7 @@ static inline void palToY(uint8_t *dst, const uint8_t *src, int width, uint32_t
 
 static inline void palToUV(uint8_t *dstU, uint8_t *dstV,
                            const uint8_t *src1, const uint8_t *src2,
-                           int width, uint32_t *pal)
+                           long width, uint32_t *pal)
 {
     int i;
     assert(src1 == src2);
@@ -1129,7 +1129,7 @@ static inline void palToUV(uint8_t *dstU, uint8_t *dstV,
     }
 }
 
-static inline void monowhite2Y(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void monowhite2Y(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
     int i, j;
     for (i=0; i<width/8; i++) {
@@ -1139,7 +1139,7 @@ static inline void monowhite2Y(uint8_t *dst, const uint8_t *src, int width, uint
     }
 }
 
-static inline void monoblack2Y(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void monoblack2Y(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
     int i, j;
     for (i=0; i<width/8; i++) {
diff --git a/libswscale/swscale_internal.h b/libswscale/swscale_internal.h
index c6fbdedaf9..5be17d4abb 100644
--- a/libswscale/swscale_internal.h
+++ b/libswscale/swscale_internal.h
@@ -260,14 +260,14 @@ typedef struct SwsContext {
                         const int16_t *lumSrc, const int16_t *chrSrc, const int16_t *alpSrc,
                         uint8_t *dest,
                         uint8_t *uDest, uint8_t *vDest, uint8_t *aDest,
-                        int dstW, int chrDstW);
+                        long dstW, long chrDstW);
     void (*yuv2yuvX   )(struct SwsContext *c,
                         const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
                         const int16_t *chrFilter, const int16_t **chrSrc, int chrFilterSize,
                         const int16_t **alpSrc,
                         uint8_t *dest,
                         uint8_t *uDest, uint8_t *vDest, uint8_t *aDest,
-                        int dstW, int chrDstW);
+                        long dstW, long chrDstW);
     void (*yuv2packed1)(struct SwsContext *c,
                         const uint16_t *buf0,
                         const uint16_t *uvbuf0, const uint16_t *uvbuf1,
@@ -284,26 +284,26 @@ typedef struct SwsContext {
                         const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
                         const int16_t *chrFilter, const int16_t **chrSrc, int chrFilterSize,
                         const int16_t **alpSrc, uint8_t *dest,
-                        int dstW, int dstY);
+                        long dstW, long dstY);
 
     void (*lumToYV12)(uint8_t *dst, const uint8_t *src,
-                      int width, uint32_t *pal); ///< Unscaled conversion of luma plane to YV12 for horizontal scaler.
+                      long width, uint32_t *pal); ///< Unscaled conversion of luma plane to YV12 for horizontal scaler.
     void (*alpToYV12)(uint8_t *dst, const uint8_t *src,
-                      int width, uint32_t *pal); ///< Unscaled conversion of alpha plane to YV12 for horizontal scaler.
+                      long width, uint32_t *pal); ///< Unscaled conversion of alpha plane to YV12 for horizontal scaler.
     void (*chrToYV12)(uint8_t *dstU, uint8_t *dstV,
                       const uint8_t *src1, const uint8_t *src2,
-                      int width, uint32_t *pal); ///< Unscaled conversion of chroma planes to YV12 for horizontal scaler.
+                      long width, uint32_t *pal); ///< Unscaled conversion of chroma planes to YV12 for horizontal scaler.
     void (*hyscale_fast)(struct SwsContext *c,
-                         int16_t *dst, int dstWidth,
+                         int16_t *dst, long dstWidth,
                          const uint8_t *src, int srcW, int xInc);
     void (*hcscale_fast)(struct SwsContext *c,
-                         int16_t *dst, int dstWidth,
+                         int16_t *dst, long dstWidth,
                          const uint8_t *src1, const uint8_t *src2,
                          int srcW, int xInc);
 
     void (*hScale)(int16_t *dst, int dstW, const uint8_t *src, int srcW,
                    int xInc, const int16_t *filter, const int16_t *filterPos,
-                   int filterSize);
+                   long filterSize);
 
     void (*lumConvertRange)(uint16_t *dst, int width); ///< Color range conversion function for luma plane if needed.
     void (*chrConvertRange)(uint16_t *dst, int width); ///< Color range conversion function for chroma planes if needed.
diff --git a/libswscale/swscale_template.c b/libswscale/swscale_template.c
index 0e832f4e10..0d259ed1a0 100644
--- a/libswscale/swscale_template.c
+++ b/libswscale/swscale_template.c
@@ -896,7 +896,7 @@
 
 static inline void RENAME(yuv2yuvX)(SwsContext *c, const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
                                     const int16_t *chrFilter, const int16_t **chrSrc, int chrFilterSize, const int16_t **alpSrc,
-                                    uint8_t *dest, uint8_t *uDest, uint8_t *vDest, uint8_t *aDest, int dstW, int chrDstW)
+                                    uint8_t *dest, uint8_t *uDest, uint8_t *vDest, uint8_t *aDest, long dstW, long chrDstW)
 {
 #if COMPILE_TEMPLATE_MMX
     if(!(c->flags & SWS_BITEXACT)) {
@@ -945,7 +945,7 @@ static inline void RENAME(yuv2nv12X)(SwsContext *c, const int16_t *lumFilter, co
 }
 
 static inline void RENAME(yuv2yuv1)(SwsContext *c, const int16_t *lumSrc, const int16_t *chrSrc, const int16_t *alpSrc,
-                                    uint8_t *dest, uint8_t *uDest, uint8_t *vDest, uint8_t *aDest, int dstW, int chrDstW)
+                                    uint8_t *dest, uint8_t *uDest, uint8_t *vDest, uint8_t *aDest, long dstW, long chrDstW)
 {
     int i;
 #if COMPILE_TEMPLATE_MMX
@@ -1021,7 +1021,7 @@ static inline void RENAME(yuv2yuv1)(SwsContext *c, const int16_t *lumSrc, const
  */
 static inline void RENAME(yuv2packedX)(SwsContext *c, const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
                                        const int16_t *chrFilter, const int16_t **chrSrc, int chrFilterSize,
-                                       const int16_t **alpSrc, uint8_t *dest, int dstW, int dstY)
+                                       const int16_t **alpSrc, uint8_t *dest, long dstW, long dstY)
 {
 #if COMPILE_TEMPLATE_MMX
     x86_reg dummy=0;
@@ -1593,7 +1593,7 @@ static inline void RENAME(yuv2packed1)(SwsContext *c, const uint16_t *buf0, cons
 
 //FIXME yuy2* can read up to 7 samples too much
 
-static inline void RENAME(yuy2ToY)(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void RENAME(yuy2ToY)(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1618,7 +1618,7 @@ static inline void RENAME(yuy2ToY)(uint8_t *dst, const uint8_t *src, int width,
 #endif
 }
 
-static inline void RENAME(yuy2ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(yuy2ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1652,7 +1652,7 @@ static inline void RENAME(yuy2ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t
     assert(src1 == src2);
 }
 
-static inline void RENAME(LEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(LEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1686,7 +1686,7 @@ static inline void RENAME(LEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *s
 
 /* This is almost identical to the previous, end exists only because
  * yuy2ToY/UV)(dst, src+1, ...) would have 100% unaligned accesses. */
-static inline void RENAME(uyvyToY)(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void RENAME(uyvyToY)(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1710,7 +1710,7 @@ static inline void RENAME(uyvyToY)(uint8_t *dst, const uint8_t *src, int width,
 #endif
 }
 
-static inline void RENAME(uyvyToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(uyvyToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1744,7 +1744,7 @@ static inline void RENAME(uyvyToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t
     assert(src1 == src2);
 }
 
-static inline void RENAME(BEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(BEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1778,7 +1778,7 @@ static inline void RENAME(BEToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *s
 }
 
 static inline void RENAME(nvXXtoUV)(uint8_t *dst1, uint8_t *dst2,
-                                    const uint8_t *src, int width)
+                                    const uint8_t *src, long width)
 {
 #if COMPILE_TEMPLATE_MMX
     __asm__ volatile(
@@ -1813,20 +1813,20 @@ static inline void RENAME(nvXXtoUV)(uint8_t *dst1, uint8_t *dst2,
 
 static inline void RENAME(nv12ToUV)(uint8_t *dstU, uint8_t *dstV,
                                     const uint8_t *src1, const uint8_t *src2,
-                                    int width, uint32_t *unused)
+                                    long width, uint32_t *unused)
 {
     RENAME(nvXXtoUV)(dstU, dstV, src1, width);
 }
 
 static inline void RENAME(nv21ToUV)(uint8_t *dstU, uint8_t *dstV,
                                     const uint8_t *src1, const uint8_t *src2,
-                                    int width, uint32_t *unused)
+                                    long width, uint32_t *unused)
 {
     RENAME(nvXXtoUV)(dstV, dstU, src1, width);
 }
 
 #if COMPILE_TEMPLATE_MMX
-static inline void RENAME(bgr24ToY_mmx)(uint8_t *dst, const uint8_t *src, int width, enum PixelFormat srcFormat)
+static inline void RENAME(bgr24ToY_mmx)(uint8_t *dst, const uint8_t *src, long width, enum PixelFormat srcFormat)
 {
 
     if(srcFormat == PIX_FMT_BGR24) {
@@ -1879,7 +1879,7 @@ static inline void RENAME(bgr24ToY_mmx)(uint8_t *dst, const uint8_t *src, int wi
     );
 }
 
-static inline void RENAME(bgr24ToUV_mmx)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, int width, enum PixelFormat srcFormat)
+static inline void RENAME(bgr24ToUV_mmx)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src, long width, enum PixelFormat srcFormat)
 {
     __asm__ volatile(
         "movq                    24+%4, %%mm6       \n\t"
@@ -1938,7 +1938,7 @@ static inline void RENAME(bgr24ToUV_mmx)(uint8_t *dstU, uint8_t *dstV, const uin
 }
 #endif
 
-static inline void RENAME(bgr24ToY)(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void RENAME(bgr24ToY)(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     RENAME(bgr24ToY_mmx)(dst, src, width, PIX_FMT_BGR24);
@@ -1954,7 +1954,7 @@ static inline void RENAME(bgr24ToY)(uint8_t *dst, const uint8_t *src, int width,
 #endif /* COMPILE_TEMPLATE_MMX */
 }
 
-static inline void RENAME(bgr24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(bgr24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     RENAME(bgr24ToUV_mmx)(dstU, dstV, src1, width, PIX_FMT_BGR24);
@@ -1972,7 +1972,7 @@ static inline void RENAME(bgr24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t
     assert(src1 == src2);
 }
 
-static inline void RENAME(bgr24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(bgr24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
     int i;
     for (i=0; i<width; i++) {
@@ -1986,7 +1986,7 @@ static inline void RENAME(bgr24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const ui
     assert(src1 == src2);
 }
 
-static inline void RENAME(rgb24ToY)(uint8_t *dst, const uint8_t *src, int width, uint32_t *unused)
+static inline void RENAME(rgb24ToY)(uint8_t *dst, const uint8_t *src, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     RENAME(bgr24ToY_mmx)(dst, src, width, PIX_FMT_RGB24);
@@ -2002,7 +2002,7 @@ static inline void RENAME(rgb24ToY)(uint8_t *dst, const uint8_t *src, int width,
 #endif
 }
 
-static inline void RENAME(rgb24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(rgb24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
 #if COMPILE_TEMPLATE_MMX
     assert(src1==src2);
@@ -2021,7 +2021,7 @@ static inline void RENAME(rgb24ToUV)(uint8_t *dstU, uint8_t *dstV, const uint8_t
 #endif
 }
 
-static inline void RENAME(rgb24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, int width, uint32_t *unused)
+static inline void RENAME(rgb24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const uint8_t *src1, const uint8_t *src2, long width, uint32_t *unused)
 {
     int i;
     assert(src1==src2);
@@ -2038,7 +2038,7 @@ static inline void RENAME(rgb24ToUV_half)(uint8_t *dstU, uint8_t *dstV, const ui
 
 // bilinear / bicubic scaling
 static inline void RENAME(hScale)(int16_t *dst, int dstW, const uint8_t *src, int srcW, int xInc,
-                                  const int16_t *filter, const int16_t *filterPos, int filterSize)
+                                  const int16_t *filter, const int16_t *filterPos, long filterSize)
 {
 #if COMPILE_TEMPLATE_MMX
     assert(filterSize % 4 == 0 && filterSize>0);
@@ -2252,7 +2252,7 @@ static void RENAME(lumRangeFromJpeg)(uint16_t *dst, int width)
     "shrl       $9, %%esi    \n\t"                                              \
 
 static inline void RENAME(hyscale_fast)(SwsContext *c, int16_t *dst,
-                                        int dstWidth, const uint8_t *src, int srcW,
+                                        long dstWidth, const uint8_t *src, int srcW,
                                         int xInc)
 {
 #if ARCH_X86
@@ -2326,7 +2326,6 @@ static inline void RENAME(hyscale_fast)(SwsContext *c, int16_t *dst,
         for (i=dstWidth-1; (i*xInc)>>16 >=srcW-1; i--) dst[i] = src[srcW-1]*128;
     } else {
 #endif /* COMPILE_TEMPLATE_MMX2 */
-    x86_reg dstWidth_reg = dstWidth;
     x86_reg xInc_shr16 = xInc >> 16;
     uint16_t xInc_mask = xInc & 0xffff;
     //NO MMX just normal asm ...
@@ -2356,7 +2355,7 @@ static inline void RENAME(hyscale_fast)(SwsContext *c, int16_t *dst,
         " jb        1b                       \n\t"
 
 
-        :: "r" (src), "m" (dst), "m" (dstWidth_reg), "m" (xInc_shr16), "m" (xInc_mask)
+        :: "r" (src), "m" (dst), "m" (dstWidth), "m" (xInc_shr16), "m" (xInc_mask)
         : "%"REG_a, "%"REG_d, "%ecx", "%"REG_D, "%esi"
     );
 #if COMPILE_TEMPLATE_MMX2
@@ -2375,13 +2374,13 @@ static inline void RENAME(hyscale_fast)(SwsContext *c, int16_t *dst,
 }
 
       // *** horizontal scale Y line to temp buffer
-static inline void RENAME(hyscale)(SwsContext *c, uint16_t *dst, int dstWidth, const uint8_t *src, int srcW, int xInc,
+static inline void RENAME(hyscale)(SwsContext *c, uint16_t *dst, long dstWidth, const uint8_t *src, int srcW, int xInc,
                                    const int16_t *hLumFilter,
                                    const int16_t *hLumFilterPos, int hLumFilterSize,
                                    uint8_t *formatConvBuffer,
                                    uint32_t *pal, int isAlpha)
 {
-    void (*toYV12)(uint8_t *, const uint8_t *, int, uint32_t *) = isAlpha ? c->alpToYV12 : c->lumToYV12;
+    void (*toYV12)(uint8_t *, const uint8_t *, long, uint32_t *) = isAlpha ? c->alpToYV12 : c->lumToYV12;
     void (*convertRange)(uint16_t *, int) = isAlpha ? NULL : c->lumConvertRange;
 
     src += isAlpha ? c->alpSrcOffset : c->lumSrcOffset;
@@ -2402,7 +2401,7 @@ static inline void RENAME(hyscale)(SwsContext *c, uint16_t *dst, int dstWidth, c
 }
 
 static inline void RENAME(hcscale_fast)(SwsContext *c, int16_t *dst,
-                                        int dstWidth, const uint8_t *src1,
+                                        long dstWidth, const uint8_t *src1,
                                         const uint8_t *src2, int srcW, int xInc)
 {
 #if ARCH_X86
@@ -2467,7 +2466,6 @@ static inline void RENAME(hcscale_fast)(SwsContext *c, int16_t *dst,
         }
     } else {
 #endif /* COMPILE_TEMPLATE_MMX2 */
-        x86_reg dstWidth_reg = dstWidth;
         x86_reg xInc_shr16 = (x86_reg) (xInc >> 16);
         uint16_t xInc_mask = xInc & 0xffff;
         __asm__ volatile(
@@ -2496,9 +2494,9 @@ static inline void RENAME(hcscale_fast)(SwsContext *c, int16_t *dst,
 /* GCC 3.3 makes MPlayer crash on IA-32 machines when using "g" operand here,
 which is needed to support GCC 4.0. */
 #if ARCH_X86_64 && AV_GCC_VERSION_AT_LEAST(3,4)
-            :: "m" (src1), "m" (dst), "g" (dstWidth_reg), "m" (xInc_shr16), "m" (xInc_mask),
+            :: "m" (src1), "m" (dst), "g" (dstWidth), "m" (xInc_shr16), "m" (xInc_mask),
 #else
-            :: "m" (src1), "m" (dst), "m" (dstWidth_reg), "m" (xInc_shr16), "m" (xInc_mask),
+            :: "m" (src1), "m" (dst), "m" (dstWidth), "m" (xInc_shr16), "m" (xInc_mask),
 #endif
             "r" (src2)
             : "%"REG_a, "%"REG_d, "%ecx", "%"REG_D, "%esi"
@@ -2523,7 +2521,7 @@ which is needed to support GCC 4.0. */
 #endif /* ARCH_X86 */
 }
 
-inline static void RENAME(hcscale)(SwsContext *c, uint16_t *dst, int dstWidth, const uint8_t *src1, const uint8_t *src2,
+inline static void RENAME(hcscale)(SwsContext *c, uint16_t *dst, long dstWidth, const uint8_t *src1, const uint8_t *src2,
                                    int srcW, int xInc, const int16_t *hChrFilter,
                                    const int16_t *hChrFilterPos, int hChrFilterSize,
                                    uint8_t *formatConvBuffer,