DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :cc:content-type:content-transfer-encoding;
        b=k6qchOOtBjitHVkDEPiBUBZv74AmXli6Aus4CPQ86hT45yvP7SCVwKtqnTvjUUgbv4
         3rcy7iSo/KqtfuAqLCQI0mQiaXmDLyzIVJKhYNw98LqbQuMlJFIjJ1EkxWrKyKA2CKcI
         SnKAhG5I+IVi4AOm7TzRASpU4/Chx+mRRRkzM=
MIME-Version: 1.0
In-Reply-To: <4D0A1C40.7060502@panasas.com>
References: <12853.1292353313@jrobl>
	<AANLkTinjkcciZhJM5FmUkh_YCJ6bc9aTq8zV=SACDb1O@mail.gmail.com>
	<4D08BF5D.1060509@panasas.com>
	<20101215.100055.226772943.davem@davemloft.net>
	<4D09E185.2040600@panasas.com>
	<AANLkTin3v0BLYAuuqTgEzKgSOpVg4GJaJCEds=2ePrBH@mail.gmail.com>
	<4D0A1C40.7060502@panasas.com>
Date: Fri, 17 Dec 2010 01:15:44 +1100
Message-ID: <AANLkTiksAkqrMtVDgxhm5s+jqMaKoUhbTaWsXfKJ9QOy@mail.gmail.com>
Subject: Re: Big git diff speedup by avoiding x86 "fast string" memcmp
From: Nick Piggin <npiggin@gmail.com>
To: Boaz Harrosh <bharrosh@panasas.com>
Cc: David Miller <davem@davemloft.net>, hooanon05@yahoo.co.jp,
        npiggin@kernel.dk, torvalds@linux-foundation.org,
        linux-arch@vger.kernel.org, x86@kernel.org,
        linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8BIT
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1654
Lines: 50

On Fri, Dec 17, 2010 at 1:03 AM, Boaz Harrosh <bharrosh@panasas.com> wrote:
> On 12/16/2010 03:13 PM, Nick Piggin wrote:
> static inline int dentry_memcmp_long(const unsigned char *cs,
> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?const unsigned char *ct, ssize_t count)
> {
> ? ? ? ?int ret;
> ? ? ? ?const unsigned long *ls = (const unsigned long *)cs;
> ? ? ? ?const unsigned long *lt = (const unsigned long *)ct;
>
> ? ? ? ?while (count > 8) {
> ? ? ? ? ? ? ? ?ret = (*cs != *ct);
> ? ? ? ? ? ? ? ?if (ret)
> ? ? ? ? ? ? ? ? ? ? ? ?break;
> ? ? ? ? ? ? ? ?cs++;
> ? ? ? ? ? ? ? ?ct++;
> ? ? ? ? ? ? ? ?count-=8;
> ? ? ? ?}
> ? ? ? ?if (count) {
> ? ? ? ? ? ? ? ?unsigned long t = *ct & ((0xffffffffffffffff >> ((8 - count) * 8))
> ? ? ? ? ? ? ? ?ret = (*cs != t)
> ? ? ? ?}
>
> ? ? ? ?return ret;
> }
>
> Same as yours but just to avoid the branch inside the loop
> and slightly smaller code.

That's true, it should make the branch more predictable too. Well,
maybe. I'm going to leave it as-is for now, but I would welcome any
test results or ideas for improvements.


> BTW: On some ARCHs ++foo is faster than foo++
> ? ? and Also, is there a reason not to write the above loop as:
>
> ? ? while(c-- && (ret = (*cs++ != *ct++)))
> ? ? ? ? ? ? ? ?;

gcc should turn it into the same thing these days. I prefer avoiding
expressions with side effects in control statements (other than a
simple counter).

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