This is the mail archive of the
mailing list for the GCC project.
Re: Fourth Draft "Unsafe fp optimizations" project description.
- To: <dewar at gnat dot com>, <kaih at khms dot westfalen dot de>, <moshier at moshier dot ne dot mediaone dot net>
- Subject: Re: Fourth Draft "Unsafe fp optimizations" project description.
- From: "Tim Prince" <tprince at computer dot org>
- Date: Wed, 15 Aug 2001 19:45:25 -0700
- Cc: <gcc at gcc dot gnu dot org>
- References: <20010815233806.22FEAF2B7B@nile.gnat.com>
----- Original Message -----
Sent: Wednesday, August 15, 2001 4:38 PM
Subject: Re: Fourth Draft "Unsafe fp optimizations" project
> <<Whatever the IEEE 754 committee may say about it, however,
the fact is
> that vendors are going to continue to offer flush to zero
> because there are good engineering reasons to do so. It
would be most
> helpful if the committee would seek to determine and codify
> industry practice. It will be much less helpful if the
> comes out with unpracticed rules that the industry is going
> as it has already done in the past.
> THat's a little fierce. It is true that some companies have
> denormals (notably Alpha -- to be discontinued in 2004, and
> with SGI stock at 50 cents, destined to play a smaller role
> future of high end numerical computing I fear :-)
> However, most architectures do adequately support denormals.
The hardware designers' idea of adequacy has moved in the
direction of giving the choice of correct denormal (soon to be
officially subnormal) results with inadequate performance, or
abrupt underflow with good performance, usually without
adequate facilities in the compiler to specify a preference.