| To: | Jun Sun <jsun@mvista.com> |
|---|---|
| Subject: | Re: when does do_fpe() get called? (or when does FPE happen?) |
| From: | Ralf Baechle <ralf@linux-mips.org> |
| Date: | Tue, 28 Jan 2003 18:45:29 +0100 |
| Cc: | linux-mips@linux-mips.org |
| In-reply-to: | <20030128093742.V11633@mvista.com>; from jsun@mvista.com on Tue, Jan 28, 2003 at 09:37:42AM -0800 |
| Original-recipient: | rfc822;linux-mips@linux-mips.org |
| References: | <20030127190423.U11633@mvista.com> <20030128043744.A24686@linux-mips.org> <20030128093742.V11633@mvista.com> |
| Sender: | linux-mips-bounce@linux-mips.org |
| User-agent: | Mutt/1.2.5.1i |
On Tue, Jan 28, 2003 at 09:37:42AM -0800, Jun Sun wrote: > > > Can someone enlighten me a little? I am trying > > > to figure out what the FPU state should be (or can be) when > > > we are inside do_fpe() routine. > > > > Checkout the various flags in $fcr31. Whenever one of the enabled > > exceptions is triggered we get to handle_fpe via do_fpe. In addition > > the unimplemented exception can also result in invocation of do_fpe. > > > > So it seems safe to assume FPU should have been enabled when we get > here, right? Yes, otherwise we'd get a coprocessur unusable exception. Ralf |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: when does do_fpe() get called? (or when does FPE happen?), Jun Sun |
|---|---|
| Next by Date: | Re: unaligned load in branch delay slot, Jun Sun |
| Previous by Thread: | Re: when does do_fpe() get called? (or when does FPE happen?), Jun Sun |
| Next by Thread: | Cross compiler installation, Victor I. Zaslavsky |
| Indexes: | [Date] [Thread] [Top] [All Lists] |