From mboxrd@z Thu Jan  1 00:00:00 1970
From: Joe Buck <jbuck@Synopsys.COM>
To: ejr@CS.Berkeley.EDU (Edward Jason Riedy)
Cc: hjstein@bfr.co.il, egcs@cygnus.com
Subject: Re: FWD: FLOATING-POINT CONSISTENCY, -FFLOAT-STORE, AND X86
Date: Mon, 14 Dec 1998 17:20:00 -0000
Message-id: <199812150119.RAA03420@yamato.synopsys.com>
References: <199812142256.OAA04732@lotus.CS.Berkeley.EDU>
X-SW-Source: 1998-12/msg00492.html

> A little thought, planning, and lack of -O flags, and you can get huge
> benefits from the 80-bit cells.

It would seem that if we did 80-bit spills, then the -O flags would not
affect the results (assuming that the original code uses parentheses
to constrain the order of evaluation of FP expressions and that the
optimizer avoids transformations that can change numerical results,
such as pre-evaluating expressions with 64-bit that would otherwise
be evaluated using 80-bit precision at runtime).