Beefy Boxes and Bandwidth Generously Provided by pair Networks
Don't ask to ask, just ask
 
PerlMonks  

Re: powerpc double-double arithmetic

by johngg (Abbot)
on Oct 09, 2013 at 14:18 UTC ( #1057553=note: print w/ replies, xml ) Need Help??


in reply to powerpc double-double arithmetic

I'm not sure as I no longer have access to a SPARC machine to test. However, I do recall that sizeof() applied to a long double on the SPARC architecture showed that it used 16 bytes whereas a long double on x86_64 used only 12 bytes. This might imply increased precision on SPARC boxes, perhaps another Monk will have the access to test it out.

Cheers,

JohnGG


Comment on Re: powerpc double-double arithmetic
Download Code
Re^2: powerpc double-double arithmetic
by syphilis (Canon) on Oct 10, 2013 at 02:55 UTC
    This might imply increased precision on SPARC boxes

    In many instances the 16 byte long double provides the same (64-bit) precision as the 12 byte variant ... and the same exponent range, too, I think.

    But it's the double-double arrangement that enables contrived comparisons (such as the one I provided) to work.
    It would take a data type providing 663 bits of precision to detect that 1.0 + 5e-200 > 1.0, whereas the double-double arrangement of the PowerPC long double stores 1.0 in one double and 5e-200 in the other. The processor then knows that the sum of both is greater than either of the 2 doubles because both doubles are positive and non-zero.
    At least, that's how I surmise.

    The processor cannot detect that 1.1 + 5e-200 > 1.1 because the "1.1" value gets written over both doubles - and adding 5e-200 then makes no difference to the 2 stored double values.

    I was hoping that a printf "%.200Le", ... of the 1.0 + 5e-200 value might print out the actual value of 1.00000...005 but, alas, doesn't even get close (in perl or C).

    BTW, the "bitch" part is that, with certain values, you can get rounding errors if you try to print out more than 15 decimal digits of precision (in perl or C).

    All in all, an intriguing arrangement - and one that almost works beautifully.

    Cheers,
    Rob
      From what I know about the x86 long double is that, for PPC, I guess sizeof is returning 16 for alignment reasons. 12 is the actual used portion. A long double is 80 bits/10 bytes on x86. Mingw claims it is 12 bytes in a sizeof.
        for PPC, I guess sizeof is returning 16 for alignment reasons

        With PPC, it actually uses the 16 bytes (in the form of 2 8-byte doubles).
        There are other processors that use 12 bytes but assign 16 bytes (for alignment purposes, as you said).

        Cheers,
        Rob

Log In?
Username:
Password:

What's my password?
Create A New User
Node Status?
node history
Node Type: note [id://1057553]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this? | Other CB clients
Other Users?
Others pondering the Monastery: (10)
As of 2014-08-30 08:39 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    The best computer themed movie is:











    Results (291 votes), past polls