Re: [ViennaCL-devel] Call for testing: PyViennaCL on Windows

2014-02-27 Thread Karl Rupp
Hi Toby, alright, some progress here: Installed Python, the Windows SDK, and NumPy as described. Then things got complicated: - Had to install setuptools. This should be mentioned in the README. - python and git need to be in PATH for `python setup.py build` to work. This is a nontrivial ste

Re: [ViennaCL-devel] Call for testing: PyViennaCL on Windows

2014-02-27 Thread Toby St Clere Smithe
Hi Karl, Karl Rupp writes: > alright, some progress here: Installed Python, the Windows SDK, and > NumPy as described. Then things got complicated: > - Had to install setuptools. This should be mentioned in the README. > - python and git need to be in PATH for `python setup.py build` to > w

[ViennaCL-devel] [ViennaCL-Devel] Adaptive padding size...

2014-02-27 Thread Philippe Tillet
Hello everybody ! So, it seems like padding sizes really do matter, and that imho making ViennaCL truly peformance-portable will require at some point hardware-adaptive padding size. For now, the generator only handles NonTrans x Trans multiplication, but I can already tell that : --

Re: [ViennaCL-devel] [ViennaCL-Devel] Adaptive padding size...

2014-02-27 Thread Philippe Tillet
Oops, Something else I forgot to mention. GEMM is not the only routine on the Earth ;) It may very well be the case that an optimized FFT would require a different padding size. It gets tricky. We might have to run the auto-tuner for a lot of different padding sizes... Philippe 2014-02-28 5:30