udelay() broken for SMP cores?
Jamie Lokier
jamie at shareable.org
Wed Apr 21 20:14:17 EDT 2010
Russell King - ARM Linux wrote:
> > > Consider system performance where you're driving a bus using udelay()
> > > to provide 1us timings, but udelay ends up taking 10us instead every
> > > time because of the calculation for number of loops for a 1us timing.
> >
> > Hence nested loop. You don't multiply. No calculation.
>
> Ok, since you seem to have a clear idea how to convert this into a double
> nested loop, try converting it:
>
> @ 0 <= r0 <= 0x7fffff06
> ldr r2, .LC0 (loops_per_jiffy)
> ldr r2, [r2] @ max = 0x01ffffff
> mov r0, r0, lsr #14 @ max = 0x0001ffff
> mov r2, r2, lsr #10 @ max = 0x00007fff
> mul r0, r2, r0 @ max = 2^32-1
> movs r0, r0, lsr #6
> moveq pc, lr
> 1: subs r0, r0, #1
> bhi 1b
> mov pc, lr
>
> into two loops without losing the precision - note that the multiply
> is part of a 'dividing by multiply+shift' technique.
ldr r2, loops_per_jiffy
ldr r3, microseconds_per_jiffy
mov r4, r2
1: subs r4, r4, r3
bhi 1b
subs r0, r0, #1
add r4, r4, r2
bhi 1b
mov pc, lr
Goodnight :)
- Jamie
(Admission: I wasn't thinking of high precision when I glibly said two
loops; your challenge prompted me to work it out, and I was pleasantly
surprised to see it come out so neatly.)
More information about the linux-arm-kernel
mailing list