High-Performance Computing: An overview

Loosely, from R’s perspective, we can think of HPC in terms of two, maybe three things:

1. Big data: How to work with data that doesn’t fit your computer

2. Parallel computing: How to take advantage of multiple core systems

3. Compiled code: Write your own low-level code (if R doesn’t has it yet…)

(Checkout CRAN Task View on HPC)

Some vocabulary for HPC

In raw terms

• Supercomputer: A single big machine with thousands of cores/gpus.

• High Performance Computing (HPC): Multiple machines within a single network.

• High Throughput Computing (HTC): Multiple machines across multiple networks.

You may not have access to a supercomputer, but certainly HPC/HTC clusters are more accesible these days, e.g. AWS provides a service to create HPC clusters at a low cost (allegedly, since nobody understands how pricing works)

What’s “a core”?

Taxonomy of CPUs (Downloaded from de https://slurm.schedmd.com/mc_support.html)

Now, how many cores does your computer has, the parallel package can tell you that:

parallel::detectCores()

## [1] 4

What is parallel computing, anyway?

f <- function(n) n*2
f(1:4)

Here we are using a single core. The function is applied one element at a time, leaving the other 3 cores without usage.

What is parallel computing, anyway? (cont’d)

f <- function(n) n*2
f(1:4)

In this more intelligent way of computation, we are taking full advantage of our computer by using all 4 cores at the same time. This will translate in a reduced computation time which, in the case of complicated/long calculations, can be an important speed gain.

Let’s think before we start…