Memory checker is not running.

[GoogleCodeExporter]

Hi,
i downloaded ocelot from svn today, ran
libtoolize
aclocal
autoconf
automake
./configure --prefix=SOMEPATH
make
make install

and then used your example from wiki, for memory checker
Compiled it with 
g++ -o mem mem.cu.cpp -L /usr/local/cuda/lib64/ -L SOME_PATH/lib -lcudart -
lOcelotIr -lOcelotParser -lOcelotExecutive -lOcelotTrace -lOcelotAnalysis -
lhydrazine
and running it by
./mem 1
doesn't print anything.

For a simple test whether ocelot is running at all, i did:
export CUDA_PROFILE=1
and ran
./mem 3
which, did not procude cuda_profile.log, which might suggest that ocelot 
took over normal execution.

Also, running ./mem 1 doesn't produce any files.

CHECK_GLOBAL_ACCESSES is defined to 1.

I am using CUDA 2.3, but i as far as i understand that shouldn't be an 
issue, as this kernel shouldn't produce unknown ptx instructions.

Original issue reported on code.google.com by korgulec@gmail.com on 16 Aug 2009 at 12:58

[GoogleCodeExporter]

I was mistaken, running with CUDA_PROFILE=1 does produce files, which suggests 
that 
ocelot didn't work at all.

Original comment by korgulec@gmail.com on 16 Aug 2009 at 1:06

[GoogleCodeExporter]

Downgraded to 2.2 and got it running, although there are some problems with 
example 
kernel from trace generator example,

==Ocelot== Emulator failed to run kernel "_Z12sampleKernelPi" with exception: 
==Ocelot== [PC 8] [thread 0] [cta 0] exit - barrier deadlock

Original comment by korgulec@gmail.com on 16 Aug 2009 at 1:30

[GoogleCodeExporter]

nvm this issue, the last error was because of an older version of boost, the 
constructor for it was a little different.

Original comment by korgulec@gmail.com on 16 Aug 2009 at 2:50

[GoogleCodeExporter]

The problem in your example is that you are specifying the path to your CUDA
libraries before ocelot's libraries: -L /usr/local/cuda/lib64/ can be omitted 
as long
as you don't use cufft or cublas.  In your case, your program was being linked
against CUDA rather than Ocelot and being run on your GPU.

Original comment by gregory....@gatech.edu on 16 Aug 2009 at 4:32

• Changed state: Invalid