User Guide for NYBlue/L

Overview
Simple Example: Compile, Link, Run

• Compiler Invocation
• Compile and Link Tips
• Batch Job Submission
• Applications Support
• Math Libraries
• MPI Version
• IBM Fortran Blue Gene & Linux Manuals
• IBM C/C++ Blue Gene & Linux Manuals
• IBM LoadLeveler Redbook
• IBM Blue Gene Solution Problem Determination Guide Redbook
• IBM Blue Gene/L Application Development Redbook
• IBM Blue Gene/L Performance Analysis Tools Redbook
• IBM Unfolding the IBM eServer Blue Gene Solution Redbook

Overview

This user guide documents topics of interest to the end users of NY Blue such as using the compilers, interactive and batch job submission, and applications support.

Local and some offsite documentation can be found in the sidebar at the left.

Blue Gene is not a typical parallel computer. It is meant for codes that scale well into hundreds or even thousands of processors. The processors in Blue Gene are slower than those on the BNL Linux clusters. So, unless your code scales well and so can benefit from using a lot of processors, you may be better off running it with fewer processors on e.g. a standard Linux cluster.

The compute nodes on which your job runs are rebooted prior to running your job on them, ensuring that there is no "junk" remaining from whatever jobs ran on those nodes previously. The nodes are also exclusively allocated to your job.

To run on NYBlue, you must submit your job to the LoadLeveler batch system.

If you find any errors on these pages please notify NYBlue Web Administrator

Simple Example: Compile, Link, Run

 
1. Copy the source code for a C language "Hello World" MPI program to any test subdirectory of your home directory:
   cp /bgl/samplecodes/c/hello.c /home/johndoe/tests/c/
    
2. cd /home/johndoe/tests/c
    
3. Compile and Link:
   mpixlc -o helloc.exe hello.c
    
4. See all available predefined partitions for your LoadLeveler job at the moment:
   readyblocks.pl
    
5. Create a LoadLeveler batch file example.ll, specifying in it an available predefined partition, and submit it to LoadLeveler:
   llsubmit example.ll  
6. The output and (if any) error files 3236.out and 3236.err respectively appear in /home/johndoe/tests/c when the job has completed  
7. This is only a quick example, see the instructions for running LoadLeveler batch jobs.  

Example Description: The batch job submission example above uses the mpich wrapper mpixlc for the IBM C cross compiler to create an executable for the compute nodes, then submits a LoadLevler batch job to run that executable on the NY Blue compute nodes.

Last Modified: Tuesday, 15-Apr-2008 15:28:03 EDT
Please forward all questions about this site to: NYBlue Web Administrator

One of ten national laboratories overseen and primarily funded by the Office of Science of the U.S. Department of Energy (DOE), Brookhaven National Laboratory conducts research in the physical, biomedical, and environmental sciences, as well as in energy technologies and national security. Brookhaven Lab also builds and operates major scientific facilities available to university, industry and government researchers. Brookhaven is operated and managed for DOE’s Office of Science by Brookhaven Science Associates, a limited-liability company founded by Stony Brook University, the largest academic user of Laboratory facilities, and Battelle, a nonprofit, applied science and technology organization.

Privacy and Security Notice