Re: [PATCH] Optimize int_sqrt for small values for faster idle

[Rasmus Villemoes]

On Mon, Feb 01 2016, Andi Kleen <ak@xxxxxxxxxxxxxxx> wrote:

> On Mon, Feb 01, 2016 at 10:25:17PM +0100, Rasmus Villemoes wrote:
>> On Thu, Jan 28 2016, Andi Kleen <andi@xxxxxxxxxxxxxx> wrote:
>> 
>> > From: Andi Kleen <ak@xxxxxxxxxxxxxxx>
>> >
>> > The menu cpuidle governor does at least two int_sqrt() each time
>> > we go into idle in get_typical_interval to compute stddev
>> >
>> > int_sqrts take 100-120 cycles each. Short idle latency is important
>> > for many workloads.
>> >
>> 
>> If you want to optimize get_typical_interval(), why not just take the
>> square root out of the equation (literally)?
>> 
>> Something like
>
> Looks good. Yes that's a better fix.
>

Thanks. (Is there a good way to tell gcc that avg*avg is actually a
32x32->64 multiplication?)

While there and doing the math, I noticed that the variance computation
may _theoretically_ overflow (if half the observations are 0, half C,
the variance before the division should be around INTERVALS*C^2/4, which
is around 2^65 for C=UINT_MAX and INTERVALS=8). I have no idea if it
actually matters, but it can be fixed by lowering the initial threshold
from UINT_MAX to sqrt(4*U64_MAX/INTERVALS) ~~ 3e9. However, this would
make it possible that all observations are larger than the initial
threshold, so we'd have to protect against a division by zero...

Rasmus