Re: [PATCH] Benchtests: Improve large memcpy/memset benchmarks

[Wilco Dijkstra <Wilco.Dijkstra@arm.com>]

Hi Noah,


>> -  align &= 63;
>
> Can you replace with `align &= getpagesize () - 1`?

Yes that would make more sense indeed.

>> -  if ((align + len) * sizeof (CHAR) > page_size)
>> -    return;
>
> Is there a reason to remove the out of bounds check?

Well it can't ever go out of bounds. The allocated buffer size is
2 * page_size (ie. 4 times real page size or 2 times MIN_PAGE_SIZE
due to the incorrect logic in init_sizes).

And if it could go out of bounds it should be an assert so we don't
silently benchmark a bounds check!

>>    align2 &= 4095;
>
> Might as well fix these up, can you replace 4095 with `getpagesize () - 1`?

Sure.

>> +  size_t i, iters = (MIN_PAGE_SIZE * 64) / n;
>
> this takes [.5, 10] seconds?

Yes, it's only 1 GB written per test. It takes ~8.5 seconds on an old slow
Cortex-A72.

Cheers,
Wilco