HP XC System 3.x Software Debugging Applications, Tuning Applications, Using Slurm, Using LSF

Running Preexecution Programs	51
6 Debugging Applications
Debugging Serial Applications	53
Debugging Parallel Applications	53
Debugging with TotalView	53
SSH and TotalView	54
Setting Up TotalView	54
Using TotalView with SLURM	54
Using TotalView with LSF-HPC	55
Setting TotalView Preferences	55
Debugging an Application	55
Debugging Running Applications	56
Exiting TotalView	57
7 Tuning Applications
Using the Intel Trace Collector and Intel Trace Analyzer	59
Building a Program — Intel Trace Collector and HP-MPI	59
Running a Program – Intel Trace Collector and HP-MPI	60
Visualizing Data – Intel Trace Analyzer and HP-MPI	60
8 Using SLURM
Introduction to SLURM	63
SLURM Utilities	63
Launching Jobs with the srun Command	63
The srun Roles and Modes	64
The srun Roles	64
The srun Modes	64
Using the srun Command with HP-MPI	64
Using the srun Command with LSF-HPC	64
Monitoring Jobs with the squeue Command	64
Terminating Jobs with the scancel Command	65
Getting System Information with the sinfo Command	65
Job Accounting	65
Fault Tolerance	66
Security	66
9 Using LSF
Using Standard LSF on an HP XC System	67
Using LSF-HPC	67
Introduction to LSF-HPC in the HP XC Environment	68
Overview of LSF-HPC	68
Differences Between LSF-HPC and Standard LSF	69
Job Terminology	70
HP XCCompute Node Resource Support	71
Notes on LSF-HPC	72
How LSF-HPC and SLURM Launch and Manage a Job	73
Notes About Using LSF-HPC in the HP XC Environment	74
Job Startup and Job Control	74
Preemption	75
Determining the LSF Execution Host	75
Determining Available LSF-HPC System Resources	75
Getting the Status of LSF-HPC	75
Getting Information About LSF Execution Host Node	75
Getting Host Load Information	76
Examining LSF-HPC System Queues	76

Table of Contents 5