Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex

Normally I'd try a small lookup table (1-byte index to 1-byte value) in this case.  But if the bitscan instruction were even close in performance, it'd be preferable, due to its more-reliable caching behavior; it should be possible to capture this at code-configuration time (aligned so as to produce an optimal result for each test case; see below).

The specific code for large-versus-small testing would be useful; did I overlook it?

Note that instruction alignment with respect to words is not the only potential instruction-alignment issue.  In the past, when optimizing code to an extreme, I've run into cache-line issues where a small change that should've produced a small improvement resulted in a largish performance loss, without further work.  Lookup tables can have an analogous issue; this could, in a simplistic test, explain an anomalous large-better-than-small result, if part of the large lookup table remains cached.  (Do any modern CPUs attempt to address this??)  This is difficult to tune in a multiplatform code base, so the numbers in a particular benchmark do not tell the whole tale; you'd need to make a judgment call, and perhaps to allow a code-configuration override.

David Hudson