|No such thing as a small change|
I fed your JustShift solution (a cute bit of lateral thinking :), into my benchmark and on my hardware it is a tad slower than shift&and:
I was a bit surprised by that as both shift & and are designated as single clock operations on my cpu. I guess the difference is in the perl operations that overlay them.
I follow your drift regarding the effect that assignment and stack handling can have on a benchmark of this nature; but the values are re-used several times through the rest of the body of the inner loop, so the assignment is a constant factor that I've chosen to exclude.
With the rise and rise of 'Social' network sites: 'Computers are making people easier to use everyday'
Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.
"Science is about questioning the status quo. Questioning authority".
In the absence of evidence, opinion is indistinguishable from prejudice.