[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Gcl-devel] [Maxima] Out of range floating point number determinatio

From: Raymond Toy
Subject: Re: [Gcl-devel] [Maxima] Out of range floating point number determination
Date: Sat, 03 Nov 2012 09:22:01 -0700
User-agent: Gnus/5.1008 (Gnus v5.10.8) XEmacs/21.5-b32 (darwin)

>>>>> "Camm" == Camm Maguire <address@hidden> writes:

    Camm> Greetings, and thanks!
    Camm> Raymond Toy <address@hidden> writes:

    >> Don't know about the value fop or foff regs.  But as I understand it,
    >> the sse instructions signal exceptions at the offending instruction,
    >> unlike x87 where the exception is signaled at the *next* x87
    >> instruction.  Hence, you need the fop and fooff regs to tell you what
    >> the offending instruction actually is.  I think; I haven't looked at
    >> that stuff in decades, probably.

    Camm> Exactly.  The code needs to look at the instruction pointer contents 
    Camm> case of SSE.  fop is not zeroed out in this case, so I suppose either
    Camm> differentially examining the status words for the two fpus, or 
    Camm> the instruction pointer and defaulting to fop if an x87 instruction,
    Camm> would suffice.

Oh, you don't know if you're using x87 or sse at runtime?  You should
be able to tell at compile time, right?  Isn't something like __SSE2
defined (with gcc) when compiling if sse2 instructions are being used?

    Camm> All of this is identical on i386 and amd64, to my understanding.

I believe so, except I think amd64 might have more xmm registers.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]