I am using memcpy on an x86 machine and finding it to be
quite slow compared to other optimised routines.
I am moving 16384 words of 32-bit floating point data and
it's taking around 49us. If I call the
Float32ToNativeInt32 routine in the PCMBlittlerLib, it
takes 13us.
If I call my own memcpy routine:
inline void mymemcpy(Float32* pDest, const Float32* pSrc,
int nSizeInWords)
{
while ( nSizeInWords-- )
*pDest++ = *pSrc++;
}
It is slightly faster (41us) when using O3 optimisation.
It's not possible to avoid the memcpy in my code, is there
a way to make it any faster?
Thanks,
Brett.
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Darwin-drivers mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
http://lists.apple.com/mailman/options/darwin-drivers/email@hidden
