Group 29: Comparing the energy consumption of running oxipng benchmarks using different Rust compiler versions

[ninasemjanova]

Use only this template to open a pull request for project 1: Measuring Energy Consumption.
Use the title below for your pull request title.

Group 29: Comparing the energy consumption of running oxipng benchmarks using different Rust compiler versions

Make sure to fill out the information under each of the headers.
Open the pull request from a repository + branch everyone in your group has access to, and use that branch to contiuously update your work throughout the project weeks.

Group number on Brightspace:

29

Group members (only names, leave out student numbers):

(You will have been assigned a group of 4 members on Brightspace)
Tess Hobbes, Kristian Hristov, Nina Semjanova

Agreed communication channel within the group:

WhatsApp group

Did you manage to contact all group members?:

we contacted 3 members of our team, the fourth member informed us today that he is not taking this class anymore

Your topic idea for Project 1:

(We will review the topics and comment on the PRs whether the projects are appropriate or need adjustment. Don't hesitate to come up to us after the lectures / in the labs to discuss project ideas)

Comparing the energy consumed by running the oxipng benchmarks, where oxipng is compiled using different Rust compiler versions.

https://github.com/oxipng/oxipng

Why oxipng:

1. contains benchmarks
2. The Rust compiler version is hopefully not too hard to switch out programmatically
3. The project is not too big

Maybe we should find another codebase that also meets the requirements but that is also guaranteed to be compilable on Rust versions released a long time ago.

Plan:

1. Rent a server or run it on our own hardware (preference goes out to the server to have less variability between tests; if it’s a server, maybe try and see if we can rent it somewhere with renewable power in the spirit of the course).
2. Compile the program that we want to measure using the different Rust versions.
3. To keep the power usage equal between runs, warm up the CPU using an artificial load, while monitoring the temperature, until it starts to throttle.
4. Run the benchmarks back-to-back, using the built-in CPU power meters we measure the power consumed by running the different benchmarks benchmark.

Basic version:

1. Skip out on the warming of the CPU. Just use two different Rust compilers, possibly the oldest and the newest.
2. Run the benchmarks, making sure there’s a bit of time between the runs, measuring the power consumed by running the benchmarks using the built-in CPU power meters.

Filename of your Project 1 blog post in p1_measuring_software/ (contributed in this pull request):

(Fill out the yaml header fitting to your group)
g29_diff_compiler_versions.md

Did you succeed to build the website locally and look at your blogpost?

no