|
From: Ian P. <ian...@in...> - 2004-04-06 22:41:01
|
On 07 Apr 2004, at 00:35, Andreas Raab wrote: > Lastly, I don't really see where this would > really help any integer operations - most of them can simply drop the > low > bits and would have to do this regardless of whether there's a one or > a zero > in it (no clear advantage here). If you can do double-word products and then correct for the 4-bit "drift", it saves you a cycle or two. Otherwise I agree. Ian |