Just got this from the numpy tracker, seems like the hashing bug got
fixed upstream:
#2017: On 32 bit, uintp and uint32 do not have the same hash
-------------------------+--------------------------------------------------
Reporter: twiecki | Owner: somebody
Type: defect | Status: closed
Priority: normal | Milestone: 1.7.0
Component: numpy.core | Version: 1.6.1
Resolution: fixed | Keywords:
-------------------------+--------------------------------------------------
Changes (by charris):
* status: new => closed
* resolution: => fixed
* milestone: Unscheduled => 1.7.0
Comment:
Fixed in 39029f5..bb7e5e2
On Tue, Jan 17, 2012 at 2:29 AM, Andreas Kloeckner
<[email protected]> wrote:
> Great, thanks!
>
> Andreas
>
> On Tue, 17 Jan 2012 08:07:19 +0100, Thomas Wiecki <[email protected]>
> wrote:
>> Not following that list, but I hope it got resolved.
>>
>> This works fine now for me. Danke!
>>
>> Thomas
>>
>> On Tue, Jan 17, 2012 at 2:31 AM, Andreas Kloeckner
>> <[email protected]> wrote:
>> > On Sat, 14 Jan 2012 12:45:12 +0100, Thomas Wiecki
>> > <[email protected]> wrote:
>> >> On Fri, Jan 13, 2012 at 10:13 PM, Andreas Kloeckner
>> >> <[email protected]> wrote:
>> >> > You mean uintp (not uintp32), right? I've made that fix in compyte. Can
>> >> > you please verify? (requires a submodule update, fixed in both PyOpenCL
>> >> > and PyCUDA)
>> >>
>> >> Yes, that's a typo.
>> >>
>> >> > I was a bit unsure what C type to map this to, but decided in favor of
>> >> > uintptr_t, even though that requires the user to have stdint.h included,
>> >> > which none of the other types do. Hope that's ok, but I am open to
>> >> > suggestions.
>> >>
>> >> The current fix doesn't work for me:
>> >> CompileError: nvcc compilation of /tmp/tmp2ru5rp/kernel.cu failed
>> >> [command: nvcc --cubin -arch sm_11
>> >> -I/usr/local/lib/python2.7/dist-packages/pycuda-2011.2.2-py2.7-linux-i686.egg/pycuda/../include/pycuda
>> >> kernel.cu]
>> >> [stderr:
>> >> kernel.cu(7): error: identifier "uintptr_t" is undefined
>> >
>> > Can you try again now? Sorry for the wait. If you follow the PyOpenCL
>> > list, you'll know what held me up. :(
>> >
>> > Andreas
>>
>
_______________________________________________
PyCUDA mailing list
[email protected]
http://lists.tiker.net/listinfo/pycuda
