Re: [PATCH 1/1] vsprintf: optimize decimal conversion (again)

[Denys Vlasenko <vda.linux@googlemail.com>]

On Monday 26 March 2012 22:18, Geert Uytterhoeven wrote:
> On Mon, Mar 26, 2012 at 22:13, Andrew Morton <akpm@linux-foundation.org> wrote:
> > On Mon, 26 Mar 2012 21:56:38 +0200
> > Denys Vlasenko <vda.linux@googlemail.com> wrote:
> >
> >> >> +#if BITS_PER_LONG != 32 || (~(0ULL)>>1) != ((1ULL<<63)-1)
> >> >
> >> > What's this for?
> >>
> >> The second check should be just BITS_PER_LONG_LONG != 64,
> >> but we don't have BITS_PER_LONG_LONG.
> >
> > So let's add BITS_PER_LONG_LONG rather than hacking around its absence!
> 
> I don't think Linux runs on anything with BITS_PER_LONG_LONG != 64...
> 
> BTW, what about CPUs with slow 32x32 multiplication and/or slow 64-bit
> division?

Without 32x32->64 multiply, the best we can generate is 4 decimal digits:
we produce next digit by approximating x/10 with (x * 0xcccd) >> 19,
and the first x where it gives wrong result is 81920 if multiply result
is truncated to 32 bits.
With it, we can generate 9 digits using (x * 0x1999999a) >> 32.

Regrading "slow 64-bit division" - after this patch, 32-bit machines
wouldn't use it at all. Only 64-bit machines will perform 64-bit
division, one per 9 decimal digits (thus, at most three divisions
per one long_long->string conversion).

In fact, with small change to #ifdefs, all machines with long long <= 64
bits can use division-less routine. It might be a good thing to try...

Any people with ARM hardware in hand interesting in running the test
program I sent in first email?

-- 
vda