Re: Computed goto optimization of vanilla Lua
[
Date Prev][
Date Next][
Thread Prev][
Thread Next]
[
Date Index]
[
Thread Index]
- Subject: Re: Computed goto optimization of vanilla Lua
- From: Roberto Ierusalimschy <roberto@...>
- Date: Fri, 5 Feb 2016 14:39:22 -0200
> Some numbers of a "real world" test case:
>
> [...]
>
> Conclusion, "one computed goto -O3 -fno-gcse -fno-crossjumping" may
> represent a real improvement.
Many thanks. But I don't think it is fair to change 'one' and '-O3', as
they are indpendent of what we are looking here (jump tables). In a
comparison between "one -O3" and "one -O3 -fno-gcse -fno-crossjumping
-DJUMPTAB", I got seedpus in the order of 3%.
(BTW, -fno-crossjumping alone seems to be enough to avoid collapsing
all indirect jumps into one.)
-- Roberto