Wrong Results from multiScan for large number of rows about cudpp

[GoogleCodeExporter]

Original comment by [email protected] on 19 Nov 2009 at 1:38

• Added labels: Component-Logic, OpSys-Windows, Priority-High, Usability
• Removed labels: Priority-Medium

[GoogleCodeExporter]

Original comment by [email protected] on 19 Nov 2009 at 1:39

• Added labels: Milestone-Release1.2

[GoogleCodeExporter]

I cannot reproduce this issue using the attached code.  On my G84 laptop with 
CUDA 2.3 
I ran sumTest(100, 50000, 1) and it does not report failure.

inthecrossfire: if you are getting this, please provide more information.  
Note, your 
test did not have a main() function, so I had to add one.  All it does is 
execute 
sumTest(100, 50000, 1).

Original comment by [email protected] on 14 Dec 2009 at 7:32

[GoogleCodeExporter]

Original comment by [email protected] on 20 Jan 2010 at 8:25

• Added labels: Milestone-Release2.0
• Removed labels: Milestone-Release1.2

[GoogleCodeExporter]

I do apologise for taking so long to respond. Unfortunately I've no longer got 
access
to the computer that suffered that bug. Perhaps it was something specific to 
the set
up. I just tested the code on my laptop and I agree that there doesn't seem to 
be a
problem. So I guess there isn't much more that can be done.

Original comment by [email protected] on 21 Jan 2010 at 12:54

[GoogleCodeExporter]

Thanks for responding, inthecrossfire.  Since we don't have a repro, I'm going 
to close 
this issue.  If you run into the problem again, please do report it!

Original comment by [email protected] on 21 Jan 2010 at 12:58

• Changed state: Invalid