yes..for example if i do:dim_x=33dim_y=33then chenge grid and block to this: 
(32,32,1) and (2,1) because i do ( 33*33=1089 threads, so grid= 
1089/1024=1,063--> 2)

> Date: Thu, 19 Jul 2012 16:34:22 +1000
> Subject: Re: [PyCUDA] Thread Problem
> From: [email protected]
> To: [email protected]
> CC: [email protected]
> 
> Hi Andrea,
> 
> On Thu, Jul 19, 2012 at 4:26 PM, Andrea Cesari <[email protected]> 
> wrote:
> > The problem is that the results match with cpu only for dim_x and dim_y
> > minor of 32.
> > For higher dimensions the cpu and gpu results are different.
> 
> When you change dim_x and dim_y values, do you also change grid and
> block size in call to findmin? Judging by the code, they are hardcoded
> to always be (32,32,1) and (1,1).
                                          
_______________________________________________
PyCUDA mailing list
[email protected]
http://lists.tiker.net/listinfo/pycuda

Reply via email to