Skip to content

Latest commit

 

History

History
37 lines (29 loc) · 1.26 KB

devcloud.md

File metadata and controls

37 lines (29 loc) · 1.26 KB

Using DevCloud via SSH:

If you haven't done so already, follow this guide to build the exercise directory structure.

Compiling with DPC++

From the syclacademy directory

cd build/Code_Exercises/<Exercise directory>

and execute:

  • make <exercise name>_source - to build source.cpp
  • make <exercise name>_solution - to build the solution provided
  • make - to build both

Alternatively from a terminal at the command line:

icpx -fsycl -o <exercise name>_source -I../External/Catch2/single_include ../Code_Exercises/<Exercise directory>/source.cpp

In Intel DevCloud, to run computational applications, you will submit jobs to a queue for execution on compute nodes, especially some features like longer walltime and multi-node computation is only available through the job queue. Please refer to the guide.

So wrap the binary into a script job_submission

#!/bin/bash
./<exercise name>_source

and run:

qsub -l nodes=1:gpu:ppn=2 -d . job_submission

The stdout will be stored in job_submission.o<job id> and stderr in job_submission.e<job id>.