High Performance Computing with R @ UC Santa Barbara

• What is high performance computing?
• Overview of UCSB resources
• Accessing pod and knot
• Running jobs
• Some specifics for R
• An example
• Give it a try
• Demo

Why and when to use HPC?

• Designed for when computational problems are either too large, take too long, and/or require large file storage for standard computers

• When HPC might not be your solution:

  • There’s lots of interaction with the program, and single runs (You need a really powerful desktop)
  • You need 1,000 nodes, but only once every 3 months (Cloud resources may be your solution)
  • You need 1,000 nodes, all the time (You need your own cluster)
  • You work with sensitive data

• Serial vs. Parallel computing
• Serial:
  • one core on one node at a time
• Parallel:
  • many tasks can be performed at once that are independent
  • or tasks can occur at the same time when 'boundry conditions' match up

• Center for Scientific Computing
  • pod cluster (2018), knot cluster (2011), braid (condo clusters)
• Letters and Science Information Technology - Aristotle cloud cluster
  • ideal for teaching e.g., Jypter notebooks
  • presistent internet connection collected data
• Extreme Science and Engineering Discovery Environment (XSEDE)
• West coast consumer wide consumer grade GPU cluster (machine learning) - Nautilus cluster
• Triton Shared Computing Cluster (TSCC) at San Diego Supercomputing Center (SDSC)

• Campus available cluster Knot (CentOS/RH 6):
  110 node, ~1400 core system
  4 ‘fat nodes’(1TB RAM)
  GPU nodes (12 M2050’s) (now too old)

• Campus available cluster Pod (CentOS/RH7):
  70 node, ~2600 core system
  4 ‘fat nodes’(1TB RAM)
  GPU nodes (3) (Quad NVIDIA V100/32 GB with NVLINK)
  GPU Development node (P100, 1080Ti, Titan V)

• Condo clusters: (PI’s buy compute nodes)
  Guild (60 nodes)
  Braid (120 nodes, also has GPUs)

• for pod and knot accounts
  Request access: http://csc.cnsi.ucsb.edu/acct

• Xsede: NSF sponsored service organization that provides access to computing resources.

Campus Champion (Sharon Solis): Represents XSEDE on the campus

• pwd
• cd
• ls
• mkdir
• mv
• rm
• nano
• (up arrow, stores 1000 lines)

Software Carpentry intro to Unix shell: http://swcarpentry.github.io/shell-novice/

ssh username@pod.cnsi.ucsb.edu

Lets make a quick R code to run On your computer in the terminal:

echo "data <- data.frame(x=seq(1:10),y=seq(1:10)); write.csv(data,"testcsv.csv",row.names=F)" > myscript.R

Now transfer that to pod:

scp myscript.R user@pod.cnsi.ucsb.edu:myscript.R

nano submit.job
#!/bin/bash -l
#Serial (1 core on one node) job...
#SBATCH --nodes=1 --ntasks-per-node=1

cd $SLURM_SUBMIT_DIR
module load R
Rscript myscript.R

sbatch submit.job
showq | grep mdono

For the short queue:

sbatch -p short submit.job

If you need to cancel:

qdel job_id

via GIPHY

scp user@pod.cnsi.ucsb.edu:testcsv.csv ./testcsv.csv

to start R on the command line

module load R

check R version

which R

installing packages?

• on first go it will ask you to make a folder on your home directory, choose Y and pick your cran mirror

• Remote login: UCSB VPN
  
• Try a small version of your code on your computer first to make sure it runs from beginning to end.
  
• Be explicit about location of input and output files
  

• For parallel stuff the parallel package is helpful

• Please include in your papers! “We acknowledge support from the Center for Scientific Computing from the CNSI, MRL: an NSF MRSEC (DMR-1720256) and NSF CNS-1725797.”

Your turn: Try running on pod

test_my_skillz.R

(use the short queue)