--- ffmpeg-0.4.9-p20051216-shared/libavcodec/i386/dsputil_mmx.c.orig	2006-01-14 13:13:04.000000000 +0100
+++ ffmpeg-0.4.9-p20051216-shared/libavcodec/i386/dsputil_mmx.c	2006-01-14 13:06:59.000000000 +0100
@@ -619,10 +619,22 @@
 
 static inline void transpose4x4(uint8_t *dst, uint8_t *src, int dst_stride, int src_stride){
     asm volatile( //FIXME could save 1 instruction if done as 8x4 ...
-        "movd  %4, %%mm0		\n\t"
-        "movd  %5, %%mm1		\n\t"
-        "movd  %6, %%mm2		\n\t"
-        "movd  %7, %%mm3		\n\t"
+        "movd  %0, %%mm0		\n\t"
+        "movd  %1, %%mm1		\n\t"
+        "movd  %2, %%mm2		\n\t"
+        
+        :
+        :  "m" (*(uint32_t*)(src + 0*src_stride)),
+           "m" (*(uint32_t*)(src + 1*src_stride)),
+           "m" (*(uint32_t*)(src + 2*src_stride))
+    );
+    asm volatile( //FIXME could save 1 instruction if done as 8x4 ...
+        "movd  %0, %%mm3		\n\t"
+        
+        :
+        :  "m" (*(uint32_t*)(src + 3*src_stride))
+    );
+    asm volatile( //FIXME could save 1 instruction if done as 8x4 ...
         "punpcklbw %%mm1, %%mm0		\n\t"
         "punpcklbw %%mm3, %%mm2		\n\t"
         "movq %%mm0, %%mm1		\n\t"
@@ -639,10 +651,6 @@
           "=m" (*(uint32_t*)(dst + 1*dst_stride)),
           "=m" (*(uint32_t*)(dst + 2*dst_stride)),
           "=m" (*(uint32_t*)(dst + 3*dst_stride))
-        :  "m" (*(uint32_t*)(src + 0*src_stride)),
-           "m" (*(uint32_t*)(src + 1*src_stride)),
-           "m" (*(uint32_t*)(src + 2*src_stride)),
-           "m" (*(uint32_t*)(src + 3*src_stride))
     );
 }