Re: [Numpy-discussion] Single-Precision FFT

2007-05-24 Thread Benjamin M. Schwartz
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Thank you both for your excellent suggestions. I'll re-read fftpack.c and try to puzzle out what to do next. Thanks, Ben -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.6 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org i

Re: [Numpy-discussion] Single-Precision FFT

2007-05-24 Thread Anne Archibald
On 24/05/07, Benjamin M. Schwartz <[EMAIL PROTECTED]> wrote: > I know that FFTW can be compiled to run in single precision. What would it > take > to make NumPy use a single-precision FFT library? > > If absolutely necessary, it might be possible to ship a patched version of > NumPy, but any oth

Re: [Numpy-discussion] Single-Precision FFT

2007-05-24 Thread Robert Kern
Benjamin M. Schwartz wrote: > I am working on two programs using NumPy for the OLPC project. In both cases > the performance is limited by the FFT. The OLPC machine uses a AMD Geode CPU, > which is generally slow, but especially bad at double-precision floating > point. > It would be a major impr

[Numpy-discussion] Single-Precision FFT

2007-05-24 Thread Benjamin M. Schwartz
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 I am working on two programs using NumPy for the OLPC project. In both cases the performance is limited by the FFT. The OLPC machine uses a AMD Geode CPU, which is generally slow, but especially bad at double-precision floating point. It would be a ma