This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc 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: [PATCH] Implement fma correctly

From: Ulrich Drepper <drepper at gmail dot com>
To: Richard Henderson <rth at twiddle dot net>
Cc: Jakub Jelinek <jakub at redhat dot com>, libc-alpha at sources dot redhat dot com
Date: Wed, 13 Oct 2010 12:21:03 -0400
Subject: Re: [PATCH] Implement fma correctly
References: <20101012191605.GQ2652@sunsite.ms.mff.cuni.cz> <4CB4DAF7.6080301@twiddle.net><AANLkTim=tMjkL1TKHx6hEmhtc1kQ5eD+HFb6T4GwgYKM@mail.gmail.com> <4CB5D08D.8090603@twiddle.net>

On Wed, Oct 13, 2010 at 11:30, Richard Henderson <rth@twiddle.net> wrote:
> The x86 kernel doesn't set up a known fpu state on signal entry?
> That seems like a bug to be fixed to me.

I don't know when it changed and whether it works in all situations,
but it seems at least on recent kernels the signal handler is always
run with FE_TONEAREST.  On x86-64.

Follow-Ups:
- Re: [PATCH] Implement fma correctly
  - From: Jakub Jelinek

References:
- [PATCH] Implement fma correctly
  - From: Jakub Jelinek
- Re: [PATCH] Implement fma correctly
  - From: Richard Henderson
- Re: [PATCH] Implement fma correctly
  - From: Ulrich Drepper
- Re: [PATCH] Implement fma correctly
  - From: Richard Henderson

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