diff --git a/src/video/SDL_blit_copy.c b/src/video/SDL_blit_copy.c
index fbe4d8f54..65b46a615 100644
--- a/src/video/SDL_blit_copy.c
+++ b/src/video/SDL_blit_copy.c
@@ -56,35 +56,27 @@ SDL_memcpySSE(Uint8 * dst, const Uint8 * src, int len)
 #ifdef _MSC_VER
 #pragma warning(disable:4799)
 #endif
-/* This assumes 8-byte aligned src and dst */
 static __inline__ void
 SDL_memcpyMMX(Uint8 * dst, const Uint8 * src, int len)
 {
     int i;
 
-    __m64 values[8];
-    for (i = len / 64; i--;) {
-#ifdef __SSE__
-        _mm_prefetch(src, _MM_HINT_NTA);
-#endif
-        values[0] = *(__m64 *) (src + 0);
-        values[1] = *(__m64 *) (src + 8);
-        values[2] = *(__m64 *) (src + 16);
-        values[3] = *(__m64 *) (src + 24);
-        values[4] = *(__m64 *) (src + 32);
-        values[5] = *(__m64 *) (src + 40);
-        values[6] = *(__m64 *) (src + 48);
-        values[7] = *(__m64 *) (src + 56);
-        _mm_stream_pi((__m64 *) (dst + 0), values[0]);
-        _mm_stream_pi((__m64 *) (dst + 8), values[1]);
-        _mm_stream_pi((__m64 *) (dst + 16), values[2]);
-        _mm_stream_pi((__m64 *) (dst + 24), values[3]);
-        _mm_stream_pi((__m64 *) (dst + 32), values[4]);
-        _mm_stream_pi((__m64 *) (dst + 40), values[5]);
-        _mm_stream_pi((__m64 *) (dst + 48), values[6]);
-        _mm_stream_pi((__m64 *) (dst + 56), values[7]);
-        src += 64;
-        dst += 64;
+	__m64* d64 = (__m64*)dst;
+	__m64* s64 = (__m64*)src;
+	
+	for(i= len / 64; i--;) {
+	
+		d64[0] = s64[0];
+		d64[1] = s64[1];
+		d64[2] = s64[2];
+		d64[3] = s64[3];
+		d64[4] = s64[4];
+		d64[5] = s64[5];
+		d64[6] = s64[6];
+		d64[7] = s64[7];
+	
+		d64 += 8;
+		s64 += 8;
     }
 
     if (len & 63)
@@ -136,9 +128,7 @@ SDL_BlitCopy(SDL_BlitInfo * info)
 #endif
 
 #ifdef __MMX__
-    if (SDL_HasMMX() &&
-        !((uintptr_t) src & 7) && !(srcskip & 7) &&
-        !((uintptr_t) dst & 7) && !(dstskip & 7)) {
+    if (SDL_HasMMX()) {
         while (h--) {
             SDL_memcpyMMX(dst, src, w);
             src += srcskip;