Data

Tools

Indexes

Applications

Experiments

Open Source Science

energy-languages

https://github.com/nicovank/energy-languages

Science Score: 46.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ✓
    Committers with academic emails
    1 of 13 committers (7.7%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary

Keywords from Contributors

projection interactive standardization optim embedded genomics observability autograding hacking shellcodes
Last synced: 6 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: nicovank
  • License: apache-2.0
  • Language: C
  • Default Branch: master
  • Homepage:
  • Size: 48.6 MB
Statistics
  • Stars: 12
  • Watchers: 2
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed 9 months ago
Metadata Files
Readme License

README.md

Energy Efficiency in Programming Languages

Nicolas van Kempen, Hyuk-Je Kwon, Dung Tuan Nguyen, Emery Berger.

Read the paper!

Documentation

Requirements

Running the measurement tool requires: - an Intel processor with RAPL support. - Linux (tested on Ubuntu 22.04).

Docker

The easiest way to run these benchmarks is using Docker: bash % sudo modprobe msr # Enable msr kernel module. % sudo python3 -m scripts.build_docker_image % sudo docker run --privileged -v [OUTPUT_DIRECTORY]:/root/data energy-languages [OPTIONS]

Here is an example running all languages/benchmarks pairs: bash % sudo docker run -it --rm --privileged -v `pwd`/data/`hostname -s`/docker-default:/root/data energy-languages \ --languages C C++ Rust Go Java C\# JavaScript TypeScript PHP Python PyPy Lua LuaJIT \ --warmup 1 \ --iterations 21 \ --timeout 10000

Running additional experiments: bash % sudo docker run -it --rm --privileged -v `pwd`/data/`hostname -s`/docker-default:/root/data energy-languages \ --benchmark-root experiments \ --languages "C as C++" "Go-no-GC" "JavaScript as TypeScript" \ --warmup 1 \ --iterations 21 \ --timeout 10000

Running Java-N experiments: bash % sudo ./scripts/docker-java-n.sh Java docker-default

Processors can be set to their minimum frequency with the following commands: ```bash

Use frequency-info to check the defaults for your machine.

% cpupower frequency-info

Pin to lowest possible frequency.

% echo 1 | sudo tee /sys/devices/system/cpu/intelpstate/noturbo % sudo cpupower frequency-set --governor powersave % sudo cpupower frequency-set --max 800Mhz

Restore defaults after running experiments.

% echo 0 | sudo tee /sys/devices/system/cpu/intelpstate/noturbo % sudo cpupower frequency-set --governor powersave % sudo cpupower frequency-set --max 3.4GHz ```

Finally, experiments can be pinned to a single code by using Docker's --cpuset-cpus option, specifying a core number. For example: bash % sudo docker run -it --rm --privileged --cpuset-cpus=13 [...]

Figures

Average power draw as a function of the average number of cores used

Average power draw as a function of the average number of cores used

bash % python3 -m scripts.normalize_cores \ --data-root data/`hostname -s`/docker-default \ --languages C C++ Rust Go Java C\# JavaScript TypeScript PHP Python PyPy Lua LuaJIT

Average power draw as a function of memory activity

Average power draw as a function of memory activity

bash % python3 -m scripts.dram \ --data-root data/`hostname -s`/docker-default \ --languages C C++ Rust Go Java C\# JavaScript TypeScript PHP Python PyPy Lua LuaJIT

Average power draw controlling for external factors

Average power draw controlling for external factors

bash % python3 -m scripts.fixed_time \ --data-root data/`hostname -s`/docker-min-freq-cpuset-13 \ --languages C C++ Rust Go Java C\# JavaScript TypeScript PHP Python PyPy Lua LuaJIT

Other

A few other scripts can be useful to generate figures and results. Their options are self-explanatory and/or documented in the --help message. Notably: - scripts.table: Build two tables comparing runtime and energy consumption for a list of languages. - scripts.barchart: Compare two implementations of the same programming language. - scripts.java_n: Generate a figure for a given benchmark of time per iteration as a function of number of iterations.

License

The original benchmark suite, the Computer Language Benchmark Game, is under BSD-3-Clause.

Code from the repository this one originally forked from is under MIT.

Any other code in this repository is under Apache-2.0.

Owner

  • Name: Nicolas van Kempen
  • Login: nicovank
  • Kind: user

GitHub Events

Total
  • Watch event: 7
  • Push event: 20
  • Create event: 1
Last Year
  • Watch event: 7
  • Push event: 20
  • Create event: 1

Committers

Last synced: 6 months ago

All Time
  • Total Commits: 642
  • Total Committers: 13
  • Avg Commits per committer: 49.385
  • Development Distribution Score (DDS): 0.109
Past Year
  • Commits: 97
  • Committers: 2
  • Avg Commits per committer: 48.5
  • Development Distribution Score (DDS): 0.01
Top Committers
Name Email Commits
Nicolas van Kempen n****p@g****m 572
Dung Tuan Nguyen n****r@g****m 28
MarcoCouto m****0@g****m 11
Hyuk-Je Kwon h****n@g****m 7
root r****t@o****u 7
dependabot[bot] 4****] 6
States r****3@g****m 4
Green Software Lab g****b@d****t 2
Ben Albrecht b****t 1
Felipe Móz 6****z 1
José Nuno Macedo j****o@i****t 1
Logan Kilpatrick 2****3@g****m 1
michaljroszak 4****k 1
Committer Domains (Top 20 + Academic)
inesctec.pt: 1 di.uminho.pt: 1 obelix96.cs.umass.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 5
  • Total pull requests: 40
  • Average time to close issues: 2 months
  • Average time to close pull requests: 3 days
  • Total issue authors: 1
  • Total pull request authors: 4
  • Average comments per issue: 0.8
  • Average comments per pull request: 0.5
  • Merged pull requests: 35
  • Bot issues: 0
  • Bot pull requests: 6
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: about 8 hours
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 7.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • nicovank (4)
Pull Request Authors
  • nicovank (25)
  • dependabot[bot] (9)
  • hyukjekwon (6)
  • dungwinux (4)
Top Labels
Issue Labels
Pull Request Labels
dependencies (9)

Packages

  • Total packages: 2
  • Total downloads: unknown
  • Total dependent packages: 0
    (may contain duplicates)
  • Total dependent repositories: 0
    (may contain duplicates)
  • Total versions: 0
proxy.golang.org: github.com/nicovank/Energy-Languages
  • Versions: 0
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 5.3%
Average: 5.5%
Dependent repos count: 5.7%
Last synced: 7 months ago
proxy.golang.org: github.com/nicovank/energy-languages
  • Versions: 0
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 5.3%
Average: 5.5%
Dependent repos count: 5.7%
Last synced: 7 months ago

Dependencies

TypeScript/package-lock.json npm
  • @types/node 18.11.9
TypeScript/package.json npm
  • @types/node ^18.11.9
.github/workflows/docker.yml actions
  • actions/checkout v3 composite
.github/workflows/rapl.yml actions
  • actions/checkout v3 composite
Rust/binary-trees/Cargo.lock cargo
  • autocfg 1.1.0
  • cfg-if 1.0.0
  • crossbeam-channel 0.5.8
  • crossbeam-deque 0.8.3
  • crossbeam-epoch 0.9.14
  • crossbeam-utils 0.8.15
  • either 1.8.1
  • hermit-abi 0.2.6
  • libc 0.2.141
  • memoffset 0.8.0
  • num_cpus 1.15.0
  • rayon 1.7.0
  • rayon-core 1.11.0
  • scopeguard 1.1.0
  • typed-arena 2.0.2
Rust/binary-trees/Cargo.toml cargo
Rust/fannkuch-redux/Cargo.lock cargo
  • autocfg 1.1.0
  • cfg-if 1.0.0
  • crossbeam-channel 0.5.8
  • crossbeam-deque 0.8.3
  • crossbeam-epoch 0.9.14
  • crossbeam-utils 0.8.15
  • either 1.8.1
  • hermit-abi 0.2.6
  • libc 0.2.141
  • memoffset 0.8.0
  • num_cpus 1.15.0
  • rayon 1.7.0
  • rayon-core 1.11.0
  • scopeguard 1.1.0
Rust/fannkuch-redux/Cargo.toml cargo
Rust/fasta/Cargo.lock cargo
  • hermit-abi 0.2.6
  • libc 0.2.141
  • num_cpus 1.15.0
Rust/fasta/Cargo.toml cargo
Rust/n-body/Cargo.lock cargo
Rust/n-body/Cargo.toml cargo
Rust/pidigits/Cargo.lock cargo
Rust/pidigits/Cargo.toml cargo
Rust/regex-redux/Cargo.lock cargo
  • aho-corasick 0.7.20
  • memchr 2.5.0
  • regex 1.7.3
  • regex-syntax 0.6.29
Rust/regex-redux/Cargo.toml cargo
Rust/reverse-complement/Cargo.lock cargo
  • autocfg 1.1.0
  • cfg-if 1.0.0
  • crossbeam-channel 0.5.8
  • crossbeam-deque 0.8.3
  • crossbeam-epoch 0.9.14
  • crossbeam-utils 0.8.15
  • either 1.8.1
  • hermit-abi 0.2.6
  • libc 0.2.141
  • memoffset 0.8.0
  • num_cpus 1.15.0
  • rayon 1.7.0
  • rayon-core 1.11.0
  • scopeguard 1.1.0
Rust/reverse-complement/Cargo.toml cargo
Rust/spectral-norm/Cargo.lock cargo
  • autocfg 1.1.0
  • cfg-if 1.0.0
  • crossbeam-channel 0.5.8
  • crossbeam-deque 0.8.3
  • crossbeam-epoch 0.9.14
  • crossbeam-utils 0.8.15
  • either 1.8.1
  • hermit-abi 0.2.6
  • libc 0.2.141
  • memoffset 0.8.0
  • num_cpus 1.15.0
  • rayon 1.7.0
  • rayon-core 1.11.0
  • scopeguard 1.1.0
Rust/spectral-norm/Cargo.toml cargo
TypeScript/k-nucleotide/package-lock.json npm
TypeScript/k-nucleotide/package.json npm
experiments/JavaScript as TypeScript/k-nucleotide/package-lock.json npm
experiments/JavaScript as TypeScript/k-nucleotide/package.json npm
experiments/JavaScript as TypeScript/package-lock.json npm
  • @types/node 18.16.1
experiments/JavaScript as TypeScript/package.json npm
  • @types/node 18.16.1
.github/workflows/scripts.yml actions
  • actions/checkout v4 composite
Python/requirements.txt pypi
  • gmpy2 ==2.1.5
scripts/requirements.txt pypi
  • black ==24.4.2
  • matplotlib ==3.9.0
  • mypy ==1.10.0
  • numpy ==1.26.4
  • pandas ==2.2.2
  • pandas-stubs ==2.2.2.240514
  • rich ==13.7.1
  • scipy ==1.13.1