From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:59480)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <rth7680@gmail.com>) id 1YWUsV-0008Iv-Hf
	for qemu-devel@nongnu.org; Fri, 13 Mar 2015 15:04:12 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <rth7680@gmail.com>) id 1YWUsR-0003Yj-Hb
	for qemu-devel@nongnu.org; Fri, 13 Mar 2015 15:04:11 -0400
Received: from mail-qg0-x231.google.com ([2607:f8b0:400d:c04::231]:39483)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <rth7680@gmail.com>) id 1YWUsR-0003Ye-CF
	for qemu-devel@nongnu.org; Fri, 13 Mar 2015 15:04:07 -0400
Received: by qgdq107 with SMTP id q107so28232879qgd.6
	for <qemu-devel@nongnu.org>; Fri, 13 Mar 2015 12:04:07 -0700 (PDT)
Sender: Richard Henderson <rth7680@gmail.com>
Message-ID: <550334A2.10005@twiddle.net>
Date: Fri, 13 Mar 2015 12:04:02 -0700
From: Richard Henderson <rth@twiddle.net>
MIME-Version: 1.0
References: <1424694237-22786-1-git-send-email-aik@ozlabs.ru>	<877fv8sp97.fsf@blackfin.pond.sub.org>	<54ED19E9.4050503@ozlabs.ru>
	<877fv6gth5.fsf@blackfin.pond.sub.org>
	<5501B0CC.3090500@twiddle.net> <5501C2C6.1060501@redhat.com>
In-Reply-To: <5501C2C6.1060501@redhat.com>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH v2] utils: Add pow2ceil()
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: Eric Blake <eblake@redhat.com>, Markus Armbruster <armbru@redhat.com>, Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Peter Maydell <peter.maydell@linaro.org>, qemu-devel@nongnu.org

On 03/12/2015 09:45 AM, Eric Blake wrote:
> On 03/12/2015 09:29 AM, Richard Henderson wrote:
>> On 02/25/2015 02:45 AM, Markus Armbruster wrote:
>>> return 0x8000000000000000u >> (clz64(value - 1) - 1);
>>
>> I realize this was weeks ago, but it would certainly be preferable to shift a
>> small constant left than a large constant right.
>>
>> Most RISC machines can't form 0x8000000000000000ull without loading 1 and then
>> left shifting to start with.  So end the end you're better off with
>>
>>   return 1ull << (63 - clz64(value));
> 
> Since the value being shifted is a constant either way, can't gcc figure
> out the equivalence and generate the optimal code to begin with?  If
> not, should it be opened as a gcc bug for potential optimization?

With the simplest of tests,

unsigned long f(unsigned long x)
{
  return 1UL << (63 - x);
}

unsigned long g(unsigned long x)
{
  return 0x8000000000000000ul >> x;
}

the code is of similar size: 3 operations each.

But if you throw in the whole operation

  1ul << (63 - (__builtin_clzl(x - 1) - 1))
vs
  0x8...0ul >> (__builtin_clzl(x - 1) - 1)

then gcc is able to fold away one of the instructions and the 1UL alternative
is shorter.


r~