For the past few years, I have delivered some guest lectures and training for the University of Melbourne master's level course Cluster and Cloud Computing. This year's contribution has been expanded, which is not surprising as the course is apparently required for data science students as well as computer science students. Thus, for 2023 four presentations were given, with the workshop repeated three times!

Unique identifiers for 263 users who received HPC training in 2022 was determined from collected attendee records. Note that users may enrol in multiple courses (e.g., Introduction to Spartan, Advanced Spartan, Parallel Processing, etc) and may return for revision. All these users are counted once only.

From the unique users a total of 212 usernames could be determined from email addresses. When enrolling for training users do not include their Spartan usernmae or their university ID; sometimes they don't even use a university email address, despite requests.

Most people use their computers (which includes mobile phones) for communication, social media, games, entertainment, office applications, and the like. Most of the time these activities are not particularly onerous in terms of computing as such or do not lead to enormous benefits in productivity, inventions, and discovery. There is one field, however, rarely discussed, that does do this - and that is supercomputing.

In the past I have posted two sets of instructions for installing VASP (Vienna Ab-initio Simulation Package for quantum-mechanical molecular dynamics (MD) using pseudopotentials and a plane wave basis set), each for VASP 5.X on an Opteron system. Now, many years later, I find myself in the position of having to install VASP once again.

In late 2015 I started using Duolingo, completing sixteen skills trees across ten languages since then. These were mainly, but not exclusively, European languages (including that pan-European auxiliary language, Esperanto). All of which gave some practical use on what were annual trips. In addition to the skill trees I made reasonable progress in Dutch, some progress in Catalan (from Spanish), Czech, and even the trio of Norwegian, Swedish, and Danish (on account of someone saying they were so similar). To say that I am a consistently active user of the application is fair; last year I was rated in the top 0.1% of users in the world.

This is a summary of what I have learned over the past two years, after my first direct encounter with what is called Borderline Personality Disorder (BPD). Whilst I do not have BPD (although everyone is a little bit on every mental health continuum), I do endeavour to be a loyal and committed ally of people with BPD (pwBPD). In a very real sense, I wish I knew then what I do now; but at least I have made the effort to learn. I hope that these notes are useful to others. For anyone who wishes to be a sincere ally (a catch-all term that should include partners, family, and friends) of a person with BPD it is absolutely necessary to make the effort to listen to the pwBPD and to educate yourself using scholarly sources. Not making the effort means that you're not an ally, regardless of how close you think you are to the person, and not using scholarly sources will cause more harm and prejudice than good.

This document was initially written at the end of BPD Awareness Week 2022 in Australia and for World Mental Health Day, and will be updated as new information comes to hand. Throughout all the content here it is emphasised that (a) quantifiers are always required (many, most, some, etc) and even a BPD person is unique and will not show all characteristics and (b) always see the person. Please note that I am not a psychologist, although I am a student of the subject and have completed most of a Graduate Diploma of Applied Psychology at the University of Auckland. I encourage people to donate to the Australian BPD Foundation.

It still generates a little bit of surprise to discover that there are people who use Python on a daily basis that are apparently quite unfamiliar with compiling said code. Or perhaps not; it is, after all, the world's most popular programming language, it has a syntax that's cleaner than many older languages, it has an enormous collection of extensions, and so forth. As a result, there are many people who use Python, but perhaps not so many who have the inquisitiveness and courage, to dive a little deeper. This short article is a deeper dive to understand a little more about the language.

The first common (novice) mistake is that Python is an interpreted language and can't be compiled. It most certainly can and is "compiled", but not in the same way that a compiled language (e.g., C/C++, Fortran, Pascal) is. If this sounds confusing one needs to dig a little into the architecture.

A Python program is compiled before being interpreted, but this step is hidden at the surface level. When Python is executed it generates byte code. This byte code is transformed and interpreted by the Python Virtual Machine which then converts the byte code to binary machine code that the computer processor can output.

The past few days I've been quite influenced by a short essay by Brianna Wiest, which starts with quite a kicker: "It is the hardest thing you will ever have to do, and it will also be the most important: stop giving your love to those who aren’t ready to love you. Stop having hard conversations with people who don't want to change." Ultimately, this is arguing for equality in all relationships. Equality is not a matter of capability or social position.

This year I completed my MHEd thesis (early) to complete the degree in this field. The following is the abstract and link to the study.

Abstract

Background

In 2018 Intel x86 microprocessors were particularly susceptible to the Meltdown security vulnerabilities, whereby any system that allowed out-of-order execution was potentially vulnerable to an attack where a process could read memory that it was not authorised to do so [1]. As this vulnerability did not affect AMD processors, suggestions were raised that AMD could be a more effective choice for HPC environments. In the same year, as a topic at International Supercomputing Conference, the European Processor Initiative (EPI), a program to develop processors for domestic supercomputers, based on ARM (Advanced RISC Machine) and RISC-V, "European Processor Accelerator" system-on-a-chip [2]. With the benefits of four years of hindsight, it is valuable to consider the current trends in microprocessor architecture.

A wide analysis was recently presented at HPCAsia2021 [3] that conducts a detailed analysis of the trends of the last 27 year from over 10,000 computers from the Top500, with even more detailed analysis of 28 systems from 2009 to 2019. Of particular note in this context is the steady growth in recent years of heterogeneous supercomputers i.e., systems with GPGPUs to 28% of the Top500 with an increase of 1% per annum. The authors note: "We expect this increasing trend will continue, particularly for addressing technological limitations controlling the power consumption", a claim that could certainly be justified with the use of Nvidia GPUs or Intel Xeon Phi (discontinued as of 2020) as co-processors. At the time most systems were clustered around 1 GB per core with only three contemporary systems at 2 GB per CPU core, there was a wide variation in compute performance and parallel file system storage, and an increasing use among the most powerful systems of burst buffer storage to overcome the performance gap between memory and the file system.