[PATCH v3 2/5] benchtests: Add memset zero fill benchtest

[naohirot@fujitsu.com]

Hi Lucas,

> From: Lucas A. M. Magalhaes <lamm@linux.ibm.com>
> Sent: Monday, September 13, 2021 11:05 PM
>
> Thanks for clarifying, now I got it. Please can you add a comment on the
> code explaining this patterns and the reason behind them?
> 
> With that said this patch LGTM.

Thank you for the review!
I just submitted V4 patch by adding the comment.
Please find it [1] and merge if it's OK.

Changes from V3:

> Reviewed-by: Lucas A. M. Magalhaes <lamm@linux.ibm.com>
> Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
> Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>

> +  // To analyze zero fill performance by comparing among the following 4
> +  // patterns from 256B to 64MB(RAM) through L1, L2 and L3 caches.
> +  // - zero-over-zero: c1=0, c2=0
> +  // - zero-over-one:  c1=0, c2=1
> +  // - one-over-zero:  c1=1, c2=0
> +  // - one-over-one:   c1=1, c2=1

[1] https://sourceware.org/pipermail/libc-alpha/2021-September/130946.html

Thanks.
Naohiro