Re:Linear vs. Binary Search
by JoeAltmaier on Wednesday November 12, 2014 @02:13PM
(#8597511)
Something to do with the ratio between instruction cache size and cost of a jump to the pipeline?
Re:Linear vs. Binary Search
by TrainedMonkey on Wednesday November 12, 2014 @03:10PM
(#8597831)
I suspect memory bus width and latency also plays a role.
Back around 1980 when I first looked into this the generally accepted cutoff was 25 rather than 64. I don't think people were unrolling loops in the tests back then so it's hard to tell whether loop unrolling or changes in CPU architecture is the greater factor in moving the cutoff point from 25 to 64.