Re: [hatari-devel] FPU trig functions emulation accuracy?

[ Thread Index | Date Index | More lists.tuxfamily.org/hatari-devel Archives ]


>> Was there ever effort to fix trig errors reported
> 
>> by Douglas test tool?
> 
> I don't know how douglas's tools work (especially, how does it qualify
> results of random data as correct or not?), but Toni Willen and me have
> gone through great details to verify a lot of test cases.
> 
> Note also the especially the trig functions produce slightly different
> results on real hardware, depending on FPU type. So in order to
> determine whether a result is correct or not, you will need at least a
> printout of the input values that were used, the expected result, and
> the actual result.

Assuming this is using softfloat mode: it returns same results as
68040/060 FPSP which does not return exactly same result as 6888x. FPSP
is more accurate.

6888x internal logaritmic/trigonometic algorithms are not known except
that they are CORDIC based but that does not help much.

Differences are very minimal, no program cares.

I added partial FPU support to my tester tool few months ago which can
report expected value and returned value and in my tests last few bits
of (trig/log) results are usually different when comparing between FPSP
and 6888x.

Other (non-trig/log) instructions are accurate.



Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/