-
Notifications
You must be signed in to change notification settings - Fork 217
Debugging
You are here: Home > Developer Documentation > Debugging
This page collects some useful hints about how to debug a hybrid (CUDA + device) parallel (MPI) application.
Use the OpenMPI supressions list
mpiexec <mpi flags> valgrind --suppressions=$MPI_ROOT/share/openmpi/openmpi-valgrind.supp picongpu ...Multi-Node Host-Side
Login into an interactive shell/batch session with X-forwarding ssh -X.
Launch PIConGPU with gdb and trigger start and back trace automatically:
mpiexec <mpi flags> xterm -e gdb -ex r -ex tb --args picongpu ...mpiexec <mpi flags> cuda-memcheck --tool <memcheck|racecheck> picongpu ...Single-Node device-side
(!) Compile with nvcc -g -G <...> if you want to set device-side breakpoints.
cd <path>/simOutput
cuda-gdb --args <path2picongpu> -d 1 1 1 -g <...> -s 100 <...> in cuda-gdb:
b <FileName>:<LineNumber>
rAnother nice method to set the debug flags for PIConGPU can be used after configuring an example. Just use ccmake . in your build directory and a GUI with a list of flags pops up. Press t for this toggles the advanced mode. Useful flags to set on are SHOW_CODELINES , CUDA_BLOCKING_KERNELS and most importantly the value of CUDA_NVCC_DEBUG_FLAGS should be set to -g;-G. After manipulating the flags press c to configure the make files and generate them by pressing g.
All wiki entries describe the dev branch. Features may be different in the current master branch.
Before you start please read our README!
PIConGPU is a scientific project. If you present and/or publish scientific results that used PIConGPU, you should set a reference to show your support. Our according up-to-date publication at the time of your publication should be inquired from:
The documentation in this wiki is still not complete and we need your help keeping it up to date. Feel free to help improving this wiki!