Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190913072237.GA12381@zn.tnic> <CAHk-=wismo3SQvvKXg8j0W-eC+5Q-ctcYfr1QV3K-i90w5caBA@mail.gmail.com>
 <9dc9f1e6-5d19-167c-793d-2f4a5ebee097@rasmusvillemoes.dk> <20190913104232.GA4190@zn.tnic>
 <20190913163645.GC4190@zn.tnic> <3fc31917-9452-3a10-d11d-056bf2d8b97d@rasmusvillemoes.dk>
In-Reply-To: <3fc31917-9452-3a10-d11d-056bf2d8b97d@rasmusvillemoes.dk>
From:   Linus Torvalds <torvalds@linux-foundation.org>
Date:   Mon, 16 Sep 2019 10:25:25 -0700
Message-ID: <CAHk-=wjdpJ+VapXfoZE8JRUfvMb8JrVTZe0=TDFYZ-ke+uqBOA@mail.gmail.com>
Subject: Re: [RFC] Improve memset
To:     Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc:     Borislav Petkov <bp@alien8.de>,
        Rasmus Villemoes <mail@rasmusvillemoes.dk>,
        x86-ml <x86@kernel.org>, Andy Lutomirski <luto@kernel.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        lkml <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Sep 16, 2019 at 2:18 AM Rasmus Villemoes
<linux@rasmusvillemoes.dk> wrote:
>
> Eh, this benchmark doesn't seem to provide any hints on where to set the
> cut-off for a compile-time constant n, i.e. the 32 in

Yes, you'd need to use proper fixed-size memset's with
__builtin_memset() to test that case. Probably easy enough with some
preprocessor macros to expand to a lot of cases.

But even then it will not show some of the advantages of inlining the
memset (quite often you have a "memset structure to zero, then
initialize a couple of fields" pattern, and gcc does much better for
that when it just inlines the memset to stores - to the point of just
removing all the memset entirely and just storing a couple of zeroes
between the fields you initialized).

So the "inline constant sizes" case has advantages over and beyond the
obvious ones. I suspect that a reasonable cut-off point is somethinig
like "8*sizeof(long)". But look at things like "struct kstat" uses
etc, the limit might actually be even higher than that.

Also note that while "rep stosb" is _reasonably_ good with current
CPU's (ie roughly gen 8+), it's not so great a few generations ago
(gen 6ish), and it can be absolutely horrid on older cores and/or
atom. The limit for when it is a win ends up depending on whether I$
footprint is an issue too, of course, but some of the bigger wins tend
to happen when you have sizes >= 128.

You can basically always beat "rep movs/stos" with hand-tuned AVX2/512
code for specific cases if you don't look at I$ footprint and the cost
of the AVX setup (and the cost of frequency changes, which often go
hand-in-hand with the AVX use). So "rep movs/stos" is seldom
_optimal_, but it tends to be "quite good" for modern CPU's with
variable sizes that are in the 100+ byte range.

             Linus