This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: GCC and Floating-Point (A proposal)

From: Scott Robert Ladd <scott dot ladd at coyotegulch dot com>
To: Paul Brook <paul at codesourcery dot com>
Cc: gcc at gcc dot gnu dot org, Richard Guenther <richard dot guenther at gmail dot com>, Vincent Lefevre <vincent+gcc at vinc17 dot org>
Date: Thu, 26 May 2005 09:54:30 -0400
Subject: Re: GCC and Floating-Point (A proposal)
References: <1116918251.4292d1eb490f6@ssl.kss-loka.si> <84fc9c0005052605045c75fe72@mail.gmail.com> <4295CE45.4000402@coyotegulch.com> <200505261440.34538.paul@codesourcery.com>

Paul Brook wrote:
> I thought the x86 sin/cos intrinsics were unsafe. ie. they don't gave accurate 
> results in all cases.

If memory serves, Intel's fsin (for example) has an error > 1 ulp for
value flose to multiples of pi (2pi, for example).

Now, I'm not certain this is true for the K8 and later Pentiums. Looks
like I need to run another round of tests. ;)

..Scott

References:
- Re: GCC and Floating-Point
  - From: Uros Bizjak
- Re: GCC and Floating-Point (A proposal)
  - From: Richard Guenther
- Re: GCC and Floating-Point (A proposal)
  - From: Scott Robert Ladd
- Re: GCC and Floating-Point (A proposal)
  - From: Paul Brook

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]