multi core

i need to parallelise our code using MPI. You can parallelise any element of the code (e.g.
including the initialisation).
To example the performance of your code you should determine the wall-clock time taken
(a) by the whole code (including initialisation and so on)
and, more interestingly,
(b) to perform all the work within the time steps (i.e. excluding initialisation and outputting final
results).
You should compare results and (time) performance of your MPI code with the serial code. You
should also look at the parallel performance of the region you have parallelised.
You should run the parallel code on varying numbers of cores (but do not use more than 3 nodes),
with timings performed using exclusive compute nodes via the Chadwick batch system .
All compilations should be done using the Intel compiler and with the -O0 optimisation flag. The
assignment is to explore and discuss parallelism (via MPI) so we do not want optimisation and
therefore turn off compiler optimisations via the -O0 flag.
About the recuiter
Member since Jul 7, 2017
Jason M.
from Ohio, United States

---

---

Looking for help? Checkout our video tutorial
How to search and apply for jobs

How to apply? Do you have more questions about the Job?
See frequently asked questions