Bug#767138: fftw3: runtime detection of NEON is perhaps broken

[Julian Taylor]

On 29.10.2014 00:18, Edmund Grimley Evans wrote:
>> Though for Debian wouldn't it be enough to change the encoding to what
>> we are using?
>> possibly that could be automated by compiling a vand snipped and getting
>> the code with objdump during configure time.
> 
> That sounds as if it could be fragile and cause problems for Debian
> ports and derivatives that might target a different ARM variant.

thus the configure check. That allows different variants automatically,
but its still not really an elegant solution.

> 
> Alternatively, you could perhaps use the current signal-catching
> mechanism but run something based on the actual FFT code as a test
> instead of a VAND instruction. By the looks of it the actual code uses
> intrinsics such as vaddq_f32. Is there any reason why one couldn't use
> one of the same intrinsics to see if NEON is working? Well, I can
> think of a couple of issues:

intrinsics need the -mfpu=neon flag to work (assuming its similar to
x86). You can't do that for the whole file as the unsupported
instruction set might be used in other places of the file.
One could use a separate file with with only a test function using
intrinsics.