On 9 April 2013 09:21, li guang <lig.f...@cn.fujitsu.com> wrote: > 在 2013-04-09二的 10:11 +0200,Paolo Bonzini写道: >> Il 09/04/2013 10:05, 陳韋任 (Wei-Ren Chen) ha scritto: >> > Hi liguang, >> > >> > Just to be curious, how much performance improvement this patch can get? >> >> I think zero. It is indeed making the code a tiny bit more readable in >> the 2nd/3rd/5th/6th hunks. > > I think maybe a little greater than 0, > for it optimizes a variable 'lj' increment.
(1) The compiler is easily smart enough to know that both ways of writing the code are equivalent, and to generate whatever code is better (2) This is in a comparatively rare code path anyway, because it only happens when we take an unexpected exception [eg fault on a guest load/store] (3) All optimisation should start with profiling, otherwise you have no idea whether you're even looking at the right places to improve. -- PMM