From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:55400)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <owasserm@redhat.com>) id 1UK4EM-0003XO-JF
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:02:20 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <owasserm@redhat.com>) id 1UK4EJ-0002Cm-Tu
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:02:18 -0400
Received: from mx1.redhat.com ([209.132.183.28]:31170)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <owasserm@redhat.com>) id 1UK4EJ-0002Cf-M6
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:02:15 -0400
Message-ID: <515020E8.2050901@redhat.com>
Date: Mon, 25 Mar 2013 12:03:20 +0200
From: Orit Wasserman <owasserm@redhat.com>
MIME-Version: 1.0
References: <939022496.13000836.1364204547097.JavaMail.root@redhat.com>
In-Reply-To: <939022496.13000836.1364204547097.JavaMail.root@redhat.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCHv4 2/9] cutils: add a function to find
 non-zero content in a buffer
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Stefan Hajnoczi <stefanha@gmail.com>, Peter Lieven <pl@kamp.de>, qemu-devel@nongnu.org, quintela@redhat.com

On 03/25/2013 11:42 AM, Paolo Bonzini wrote:
> 
>>>>> +size_t buffer_find_nonzero_offset(const void *buf, size_t len)
>>>>> +{
>>>>> +    VECTYPE *p = (VECTYPE *)buf;
>>>>> +    VECTYPE zero = ZERO_SPLAT;
>>>>> +    size_t i;
>>>>> +
>>>>> +    assert(len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR
>>>>> +        * sizeof(VECTYPE)) == 0);
>>>>> +    assert(((uintptr_t) buf) % sizeof(VECTYPE) == 0);
>>>>> +
>>>>> +    if (*((const long *) buf)) {
>>>>> +        return 0;
>>>>> +    }
>>>>> +
>>>>> +    for (i = 0; i < len / sizeof(VECTYPE);
>>>> Why not put len/sizeof(VECTYPE) in a variable?
>>>
>>> are you afraid that there is a division at each iteration?
>>>
>>> sizeof(VECTYPE) is a power of 2 so i think the compiler will
>>> optimize it
>>> to a >> at compile time.
>> true, but it still is done every iteration.
> 
> len is an invariant, the compiler will move it out of the loop
> automatically.  Write readable code unless you have good clues
> that it is also slow.
> 
I know it does for x86 but I wasn't sure for other platforms.
I'm fine with as is.

Orit
> Paolo
>