Displaying 3 results from an estimated 3 matches for "2ulp".
Did you mean:
2ul
2011 Sep 07
3
[LLVMdev] Proposal: floating point accuracy metadata (OpenCL related)
...to 2.5ulp, per OpenCL 1.1 s7.4). I would imagine
that in the future we may want to allow the user to control the level
of accuracy (one idea is that we can provide a __builtin_fpaccuracy
function, which could be used like this):
__builtin_fpaccuracy(x/y, 2) // compute x/y with a maximum error of 2ulp
The backend is not my area of expertise, so I won't venture to say
how difficult it would be to recognise and act on the attribute there.
Alternatives
------------
I am proposing metadata here, since it may be removed without
negatively affecting accuracy.
We could add fpaccuracy as a core...
2011 Sep 08
1
[LLVMdev] [cfe-dev] Proposal: floating point accuracy metadata (OpenCL related)
...1 s7.4). I would imagine
> that in the future we may want to allow the user to control the level
> of accuracy (one idea is that we can provide a __builtin_fpaccuracy
> function, which could be used like this):
>
> __builtin_fpaccuracy(x/y, 2) // compute x/y with a maximum error of 2ulp
>
> The backend is not my area of expertise, so I won't venture to say
> how difficult it would be to recognise and act on the attribute there.
>
> Alternatives
> ------------
>
> I am proposing metadata here, since it may be removed without
> negatively affecting...
2011 Sep 08
0
[LLVMdev] [cfe-dev] Proposal: floating point accuracy metadata (OpenCL related)
...; > that in the future we may want to allow the user to control the level
> > of accuracy (one idea is that we can provide a __builtin_fpaccuracy
> > function, which could be used like this):
> >
> > __builtin_fpaccuracy(x/y, 2) // compute x/y with a maximum error of
> 2ulp
> >
> > The backend is not my area of expertise, so I won't venture to say
> > how difficult it would be to recognise and act on the attribute
> there.
> >
> > Alternatives
> > ------------
> >
> > I am proposing metadata here, since it may be...