Replies to post #51600 on Advanced Micro Devices Inc (AMD)

[mmoy]

Well, that's what the code currently does. I'm trying to find
something faster. If nothing else, I could just unroll the loop
into chunks of 8 as well.

I'm going to try the aligned longword approach as that seems
to be far more efficient based on some testing that I did
earlier.

[chipdesigner]

The simplest way is rarely the fastest, though.