ALIs
kommt nochThe Allinea DDT debugger
DDT, the Distributed Debugging Tool is a comprehensive graphical debugger for scalar, multi-threaded and large-scale parallel applications that are written in C, C++ and Fortran.
Allinea DDT
With Allinea DDT it is now possible to debug masive parallel program and deploying several hundreds of cores with very few clicks.
Using DDT
First, it is strongly recommended you clean and rebuild your code with debugging symbols For most compilers (C/C++ and Fortran) this is achieved with the -g option.
Additionally, you might specifiy other options, described briefly in the table below:
| Compiler | Options | Remarks |
| icc/icpc/mpicc/mpiCC | -g -O2 -traceback |
-traceback for C code mixed with Fortran |
| ifort/mpif90 | -g -O2 -check all -traceback |
-check all activates runtime error checking and may have performance impact. Refer to the compiler documentation for other check options, i.e., -check bounds |
| gcc/g++ | -g -O2 |
|
| gfortran | -g -O2 -fbacktrace -fcheck=<all|bounds> |
The use of -fcheck might impact severely performance. Consult the man page for detailed information. |
Now you should load the the appropriate environment module and call the ddt command
module load ddt ddt
As represented in Figure 1, DDT gives you the option to debug a program, launch manually a program, attach a running program or open core files
Figure 1. DDT main menu
If you choose to Debug a program, DDT will be automatically integrated with the IBM Load Leveler. Thus, DDT will generate a corresponding batch job and will connect to the compute nodes when the program starts execution.
As shown in Figure 2 the executable and the corresponding parameters can be specified. Memory debugging and other features can be activated by expanding the form with the Advanced buttom.
Figure 2. Run Window.
The user is also advised to specifiy the number of nodes along with the number of cores per node (through the PROCS_PER_NODE_TAG). Programs can be scheduled to the test or general queues. Refer to the Loadleveler site for information about limits and resources available on each queue. Keep in mind, the waiting times on each queue might increase with the amount of resources (compute nodes or Wall Clock limits) your request.
In order to modify some parameters for the Load Leveler scheduler, click Change.
Figure 3. Parallel Enviroment
As show in Figure 3, by defualt the IBM MPI parallel enviroment is chosen. You could specify, for example, intel-mpi if you want to debug programs with Intel MPI.
Figure 4. Batch job templates
In Figure 4 you can select a template for the job script that DDT will use to launch your program. Defualt is the IBM MPI. For Intel MPI, choose loadleveler_intel_mpi.qtf, located in the $HOME/.ddt subdirectory. This directory will be generated with your onw preferences when you load the ddt module for first time. Any modification or fine adjustment you do will be preserved in the $HOME/.ddt_templates directory.
Figure 5. Queue submition parameters.
In the job submittion window, it is possible to specify the number of processors per node with the value of PROCS_PER_NODE_TAG. A maximun of 40 can be allocated.
On the Queue Submission Parameters windows, Figure 5, it is possible to tell change the queue (general or test) , the class job (parallel or MPICH) , the number of MPI Tasks and OpenMP threads and the walltime. The meaning of each value and possible combinations are extensively described in the Loadleveler page.
Finally, the Loadleveler will decide when your batch job should start. Once your job is running you will be able to use the control buttoms (play, pause, step, etc.), or add break and watch points. Refer to the documention for a complete description of options.
Figure 6. Control Buttoms
Documentation
We strongly recomend you to read the documentaion in PDF-format which is accesible throught $DDT_DOC environment variable.