sdram transfer

Ken,

(I am working with Fred, but on the software side ...)

For 32bit transfers, we just use a hand-made loop with 32bit pointers (see below).

With 8bit pointers (=8bit xfer), we get the same throughput as with memcpy(), so it seems there is no optimisation in memcpy().

Bruno.

---------------

static void

myMemcpyLong(const char *src, char *dest, int taille)

{

/* This code will fail when buffers or size are not properly aligned,

* so it is not a plug-to-plug replacement for memcpy().

* (anyway 'src' and 'dest' parameters are swapped ...) */

register const long *mySrc = src;

register long *myDest = dest;

while (taille > 0) {

*myDest++ = *mySrc++;

taille -= sizeof(*mySrc);

}

} /* myMemcpyLong */