This is the mail archive of the
mailing list for the glibc project.
Re: [PATCH 02/10] Add the low level infrastructure for pthreadslock elision with TSX
On Sun, 2013-01-13 at 21:46 +0100, Andi Kleen wrote:
> > I'm going to be suggesting we should expose a generic API and
> > environment variables.
> I think an program API is a bad idea. I don't want programs with these
> tunables hard coded. I don't consider them an ABI and reserve
> the right to change them at any time. Tunables are for experiments,
> not for hardcoding forever.
So, does that mean that the tunables that you suggest for HLE are *only*
meant for experiments, and are not necessary for in-production