This version is outdated by a newer approved version.This version (2020/09/24 11:34) is a draft.Approvals: 0/1
This is an old revision of the document!
forge = map + ddt (VSC-3)
Synopsis:
<html> <font color=#cc3300><b>map</b></font> </html> and <html> <font color=#cc3300><b>ddt</b></font> </html> are ARM's (formerly Allinea's) advanced tools for performance analysis, see https://developer.arm.com/tools-and-software/server-and-hpc/debug-and-profile/arm-forge. Licenses for up to 512 parallel tasks are available. Of additional note, <html> <font color=#cc3300><b>perf-report</b></font> </html> — a related lightweight profiling tool — has now been integrated into forge in more recent releases.
Usage of map:
Profiling may be split into two steps, where the initial task is to create a *.map file from within a regular job script submitted to SLURM. In a subsequent step this *.map file can then be analyzed within an interactive session on the login node. Suppose we had previously prepared an application for profiling, for instance via mpicc -g -O3 ./my_prog.c then we could call for a corresponding profile with the following submit script,
#!/bin/bash # #SBATCH -J map #SBATCH -N 4 #SBATCH -L allinea@vsc #SBATCH --ntasks-per-node 16 #SBATCH --ntasks-per-core 1 module purge module load intel/18 intel-mpi/2018 allinea/20.1_FORGE map --profile srun --jobid $SLURM_JOB_ID --mpi=pmi2 -n 64 ./a.out
which generates a *.map file (note the mention of #tasks and #nodes together with the date/time stamp in the filename) that may then be analyzed via the gui, ie
ssh vsc3.vsc.ac.at -l my_uid -X
cd wherever/the/map/file/may/be
module purge
module load allinea/20.1_FORGE
map ./a_64p_4n_2020-09-24_11-42.map
Usage of ddt:
Debugging with ddt is currently limited to the Remote Launch option. There are two ways to launch this type of ddt-sessions:
<!–
1.) ddt (semi-interactive via sbatch):
The following steps need to be carried out:
ssh vsc3.vsc.ac.at -l my_uid -X
my_uid@l33$ module load allinea/18.2_FORGE
my_uid@l33$ rm -rf ~/.allinea/ ( to get rid of obsolete configurations from previous sessions )
my_uid@l33$ ddt &
... select 'Remote Launch - Configure'
... click 'Add'
... set my_uid@l33.vsc.ac.at as 'Host Name' depending on which l3[1-5] node we currently are
... set 'Remote Installation Directory' to /opt/sw/x86_64/glibc-2.17/ivybridge-ep/allinea/18.2_FORGE
... check it with 'Test Remote Launch' ( will ask for a Password/OTP then monitor successful testing )
... click OK twice to close the dialogues
... click Close to exit from the Configure menu
... next really select 'Remote Launch' by clicking the name tag that was auto-assigned ( will again ask for a Password/OTP, then the licence label should come up ok in the lower left corner and the connecting client should appear in the lower right corner )
ssh vsc3.vsc.ac.at -l my_uid ( a second terminal will be needed to actually start the debug session )
my_uid@l35$ cd wherever/my/app/may/be
my_uid@l35$ module load intel/16 intel-mpi/5 ( or whatever else suite of MPI )
my_uid@l35$ mpiicc -g -O0 my_app.c
my_uid@l35$ vi ./run.ddt.slrm.scrpt
... insert the usual '#SBATCH ...' commands
... don't forget to include 'module load allinea/18.2_FORGE' and '#SBATCH -L allinea@vsc'
... the actual program execution should be prefixed with 'ddt --connect --np=32 ...' ie better avoid express launch style
my_uid@l35$ sbatch ./run.ddt.slrm.scrpt ( in the other ddt-window sent into the background initially, a separate window pops up saying 'Reverse Connect Request' which needs to be accepted, then the usual ddt options will become available and the actual session may be launched by clicking 'Run' ) -->
2.) ddt (fully interactive via salloc):
The following steps need to be carried out:
ssh vsc3.vsc.ac.at -l my_uid -X
my_uid@l33$ module load intel/16 intel-mpi/5 allinea/18.2_FORGE ( or whatever else suite of MPI )
my_uid@l33$ cd wherever/my/app/may/be
my_uid@l33$ mpicc -g -O0 my_app.c
my_uid@l33$ salloc -N 4 -L allinea@vsc
my_uid@l33$ scontrol show hostnames $SLURM_NODELIST > ./machines.txt
... let's assume we got n12-[045,051,068,071] which should now be listed inside file 'machines.txt'
my_uid@l33$ rm -rf ~/.allinea/ ( to get rid of obsolete configurations from previous sessions )
my_uid@l33$ srun -n 4 hostname ( this is important ! it looks like a redundant command but will actually fix a lot of the prerequisites usually taken care of in the SLURM prologue of regular submit scripts, one of them being provisioning of required licenses )
my_uid@l33$ ddt &
... select 'Remote Launch - Configure'
... click 'Add'
... set my_uid@n12-045 as 'Host Name' or any other node from the above list
... set 'Remote Installation Directory' to /opt/sw/x86_64/glibc-2.17/ivybridge-ep/allinea/18.2_FORGE
... check it with 'Test Remote Launch' ( should be ok )
... click OK twice to close the dialogues
... click Close to exit from the Configure menu
... next really select 'Remote Launch' by clicking the name tag that was auto-assigned above ( licence label should be ok in the lower left corner and the connecting client should appear in the lower right corner )
ssh vsc3.vsc.ac.at -l my_uid ( a second terminal will be needed to actually start the debug session )
my_uid@l34$ ssh n12-045 ( log into that compute node that was selected/prepared above for remote launch )
my_uid@n12-045$ module load intel/16 intel-mpi/5 allinea/18.2_FORGE
my_uid@n12-045$ cd wherever/my/app/may/be
my_uid@n12-045$ mpirun -np 16 -machinefile ./machines.txt hostname ( just a dummy check to see whether all is set up correctly )
my_uid@n12-045$ ddt --connect mpirun -np 64 -machinefile ./machines.txt ./a.out -arg1 -arg2 ( in the initial ddt-window a dialogue will pop up prompting for a Reverse Connection request; accept it and click Run and the usual debug session will start )
Further Reading:
/opt/sw/x86_64/glibc-2.17/ivybridge-ep/allinea/18.2_FORGE/doc/userguide-forge.pdf
Tutorial (by Patrick Wohlschlegel, Allinea):
- Overflow: 5_makefile 5_mmult2.c