tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Silly question - a further one : TLB flush

On Sun, Sep 07, 2008 at 02:31:16PM +0200, Vincent wrote:
> Manuel,
> >This I'm not sure. I guess the CPU is using 64bit data path internally,
> >even in 32bit mode, so the number of entries in the TLB is probably
> >the same in 32 and 64bit modes. Using 2 different TLB formats would
> >make things more complext for no real gain.
> Well, what gain can be expected out of a doubling of the TLB size (all 
> other parameters being left unchanged)?

Simplicity in the design of the chip (and so in silicium surface)
You have to have a 64bit tlb anyway for support of the 64bit mode;
so in 32bit mode it's much simpler, from a electronic design POW, to
just set the 32 upper bits to 0 on data path entry of the TBL than
to have internals of the TLB work in a different way (basically requiring
every TLB registers to be dual-mode, as well as the lookup and eviction
logics). This would be a quite high cost on the silicium, maybe near of
doubing the on-die size of the TLB. This would also be a cost in timing, as
you're adding extra gates in the critical path.

Manuel Bouyer <>
     NetBSD: 26 ans d'experience feront toujours la difference

Home | Main Index | Thread Index | Old Index