linux-kernel - Re: [PATCH] lib/int_sqrt.c: Optimize square root function

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 02 Feb 2015 20:47:23 -0800
From:	Davidlohr Bueso <dave@...olabs.net>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	Anshul Garg <aksgarg1989@...il.com>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	anshul.g@...sung.com
Subject: Re: [PATCH] lib/int_sqrt.c: Optimize square root function

On Mon, 2015-02-02 at 11:00 -0800, Linus Torvalds wrote:
> Hmm. I don't disagree, but would like some more feedback.
> 
> Davidlohr - you were the person to touch this function last (commit
> 30493cc9dddb: "lib/int_sqrt.c: optimize square root algorithm"), and
> you did so for performance reasons. And in fact, when you did that,
> you removed that initial loop:
> 
> -       one = 1UL << (BITS_PER_LONG - 2);
> -       while (one > op)
> -               one >>= 2;
> 
> but I'm not sure that was actually all that conscious, I think the
> real optimization was the changes inside the loop to make the final
> real loop faster and simpler.

I missed that. And yes, the real optimization should be in the loop.

> 
> Also, you had performance numbers, so presumably a test harness for it
> all. It probably depends a lot on the actual distribution of argument
> values, of course, but it would be good to accompany the patch with
> actual real numbers like lasty time.

Aha. In my case I recall I ran a usersapce program using each function
from 1 to a million, and throwing perf at it for 10 times.

> (I'm also not entirely sure what uses int_sqrt() that ends up being so
> performance-critical, so it would be good to document that too, since
> that probably also matters for the "what's the normal argument range"
> question..)

It's not a big deal afaik.

Thanks,
Davidlohr

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/