From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-return-79938-listarch-gcc=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 26034 invoked by alias); 29 Jul 2003 13:28:15 -0000
Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Archive: <http://gcc.gnu.org/ml/gcc/>
List-Post: <mailto:gcc@gcc.gnu.org>
List-Help: <http://gcc.gnu.org/ml/>
Sender: gcc-owner@gcc.gnu.org
Received: (qmail 26025 invoked from network); 29 Jul 2003 13:28:12 -0000
Received: from unknown (HELO mx01.uni-tuebingen.de) (134.2.3.11)
  by sources.redhat.com with SMTP; 29 Jul 2003 13:28:12 -0000
Received: from bellatrix.tat.physik.uni-tuebingen.de (bellatrix.tat.physik.uni-tuebingen.de [134.2.170.113])
	by mx01.uni-tuebingen.de (8.12.3/8.12.3) with ESMTP id h6TDS70w007035;
	Tue, 29 Jul 2003 15:28:07 +0200
Received: from bellatrix.tat.physik.uni-tuebingen.de (localhost [127.0.0.1])
	by bellatrix.tat.physik.uni-tuebingen.de (8.12.3/8.12.2/SuSE Linux 0.6) with ESMTP id h6TDS7KA005217;
	Tue, 29 Jul 2003 15:28:07 +0200
Received: from localhost (rguenth@localhost)
	by bellatrix.tat.physik.uni-tuebingen.de (8.12.3/8.12.3/Submit) with ESMTP id h6TDS7wM005214;
	Tue, 29 Jul 2003 15:28:07 +0200
X-Authentication-Warning: bellatrix.tat.physik.uni-tuebingen.de: rguenth owned process doing -bs
Date: Tue, 29 Jul 2003 14:22:00 -0000
From: Richard Guenther <rguenth@tat.physik.uni-tuebingen.de>
To: Steven Bosscher <s.bosscher@student.tudelft.nl>
cc: gcc@gcc.gnu.org
Subject: Re: std::pow implementation
In-Reply-To: <1059483713.3650.148.camel@steven.lr-s.tudelft.nl>
Message-ID: <Pine.LNX.4.44.0307291522170.14031-100000@bellatrix.tat.physik.uni-tuebingen.de>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-AntiVirus: checked by AntiVir Milter 1.0.2; AVE 6.20.0.1; VDF 6.20.0.50
X-SW-Source: 2003-07/txt/msg01988.txt.bz2

On 29 Jul 2003, Steven Bosscher wrote:

> Op di 29-07-2003, om 14:55 schreef Richard Guenther:
> > double foo2(double x)
> > {
> >   pow(x, 2);
> > }
>
> Not that it didn't even unroll the loop at all.
>
> I have no idea if it makes any difference, I'm just curious: What
> happens if you replace
>
>       while (__n >>= 1)
>
> with
>       while (__n = __n / 2)
> ?
>
> Maybe the loop stuff can't handle shifts...

I get it to unroll with

  template<typename _Tp>
    inline _Tp
    __cmath_power(_Tp __x, unsigned int __n)
    {
      _Tp __y = __n & 1 ? __x : 1;
      const int ni = __n == 0 ? 0 : sizeof(unsigned int)*8 - __builtin_clz(__n);
      for (int i=0; i<ni; ++i)
        {
          __n >>= 1;
          __x = __x * __x;
          if (__n & 1)
            __y = __y * __x;
        }

      return __y;
    }

But neither the __n >>= 1; (or __n /= 2), not the following bit test
is constant folded and we end up with

_Z4foo2d:
.LFB12:
        pushl   %ebp    #
.LCFI4:
        movl    %esp, %ebp      #,
.LCFI5:
        fldl    8(%ebp) # x
        movl    $2, %eax        #, __n
        fld1
        fxch    %st(1)  #
        shrl    %eax    # tmp91
        movb    %al, %dl        #, tmp93
        fmul    %st(0), %st     #,
        andb    $1, %dl #, tmp93
        testb   %dl, %dl        # tmp93
        je      .L92    #,
        fmul    %st, %st(1)     #,
.L92:
        shrl    %eax    # __n
        movb    %al, %dl        #, tmp93
        fmul    %st(0), %st     #,
        andb    $1, %dl #, tmp93
        testb   %dl, %dl        # tmp93
        je      .L97    #,
        fmulp   %st, %st(1)     #,
        jmp     .L80    #
        .p2align 4,,7
.L97:
        fstp    %st(0)  #
.L80:
        popl    %ebp    #
        ret

It seems this fact is worth another PR.

Richard.

--
Richard Guenther <richard dot guenther at uni-tuebingen dot de>
WWW: http://www.tat.physik.uni-tuebingen.de/~rguenth/