Skip to content

Welcome to the QMUL HPC blog

Some Pleasingly Parallel GPU Case Studies in Machine Learning

In a previous blog, we discussed ways we could use multiprocessing and mpi4py together to use multiple nodes of GPUs. We will cover some machine learning principles and two examples of pleasingly parallel machine learning problems. Also known as embarrassingly parallel problems, I rather call them pleasingly because there isn't anything embarrassing when you design your problem to be run in parallel. When doing so, you could launch very similar functions to each GPU and collate their results when needed.

A look at the Grace Hopper superchip

NVIDIA recently announced the GH200 Grace Hopper Superchip which is a combined CPU+GPU with high memory bandwidth, designed for AI workloads. These will also feature in the forthcoming Isambard AI National supercomputer. We were offered the chance to pick up a couple of these new servers for a very attractive launch price.

The CPU is a 72-core ARM-based Grace processor, which is connected to an H100 GPU via the NVIDIA chip-2-chip interconnect, which delivers 7x the bandwidth of PCIe Gen5, commonly found in our other GPU nodes. This effectively allows the GPU to seamlessly access the system memory. This datasheet contains further details.

Since this new chip offers a lot of potential for accelerating AI workloads, particularly for workloads requiring large amounts of GPU RAM or involving a lot of memory copying between the host and the GPU, we've been running a few tests to see how this compares with the alternatives.

Some Strategies for Using Multiple Nodes of GPUs

Using multiple GPUs is one option to speed up your code. On Apocrita, we have V100, A100 and H100 GPUs available, with up to 4 GPUs per node. On other compute clusters, JADE2 has 8 V100 GPUs per node and Sulis has 3 A100 GPUs per node. If your problem is pleasingly parallel, you can distribute identical or similar tasks to each GPU on a node, or even on multiple nodes.

Apocrita Workshop

We held a 2-hour HPC workshop last Friday, December 15th. We arranged an agenda in coordination with the research student at QMUL, Peter Alexander Lock. It covered the generalities of Linux, accessing Apocrita, submitting jobs, and HPC commands.

Modules Update December 2023

Since the last module update in December 2022, we have:

  • added/moved 61 modules to production
  • added 2 modules to the development environment
  • deprecated 3 modules
  • deleted 12 modules

Let's talk about Linux and High Performance Computing

On November 15th, our HPC team organised an event called “Let’s talk about Linux and HPC”, which focused on giving an overview of HPC at QMUL. The conference was open to the public and published on Eventbrite.

Approximately 30 people were in attendance between organisers and online or onsite attendees that came to our 2-hour event in the Engineering building at the Mile End campus. During the conference, attendees shared opinions, thoughts and suggestions for future workshops dealing with Linux, Ubuntu and setting up scripts in more detail. They were able to express themselves with the help of mentimeter.

R Workflow

Nowadays, there seems to be an R package for anything and everything. While this makes starting a project in R seem quick and easy, there are considerations to take into account that will make your life easier in the long run.