From 97fc3d2eb5def5dc00cbb6a049bcfce3ba07cdec Mon Sep 17 00:00:00 2001 From: Floris-Jan Willemsen Date: Fri, 17 May 2024 09:15:15 +0200 Subject: [PATCH] Added Citation file citation of the software --- CITATION.cff | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 CITATION.cff diff --git a/CITATION.cff b/CITATION.cff new file mode 100644 index 0000000..5a0a5f1 --- /dev/null +++ b/CITATION.cff @@ -0,0 +1,78 @@ +cff-version: 1.2.0 +title: Autotuning Methodology +message: >- + If you use this software, please cite both the article from preferred-citation and the software itself. +type: software +authors: + - given-names: Floris-Jan + family-names: Willemsen + email: f.q.willemsen@umail.leidenuniv.nl + affiliation: "Leiden University, Netherlands eScience Center" + orcid: "https://orcid.org/0000-0003-2295-8263" +identifiers: + - type: doi + value: 10.5281/zenodo.11207516 + description: Zenodo DOI +repository-code: >- + https://github.com/AutoTuningAssociation/autotuning_methodology +url: >- + https://autotuningassociation.github.io/autotuning_methodology/ +abstract: >- + This software package accompanies the paper "A Methodology + for Comparing Auto-Tuning Optimization Algorithms", making + the guidelines in the methodology easy to apply. +keywords: + - Auto-tuning + - Methodology + - Optimization Algorithms + - Performance Comparison + - Performance Metrics + - Performance Optimization +license: MIT +commit: 1c096e7ceabed2ffed53838a052c7188ac93124d +version: 1.0.0b3 +date-released: "2024-05-17" +preferred-citation: + type: article + title: A Methodology for Comparing Optimization Algorithms for Auto-Tuning + journal: "Future Generation Computer Systems" + year: 2024 + abstract: >- + Adapting applications to optimally utilize available hardware is no mean feat: the plethora of choices for optimization techniques are infeasible to maximize manually. + To this end, auto-tuning frameworksauto-tuning frameworks are used to automate this task, which in turn use optimization algorithms to efficiently search the vast search spaces. + However, there is a lack of comparability in studies presenting advances in auto-tuning frameworks and the optimization algorithms incorporated. + As each publication varies in the way experiments are conducted, metrics used, and results reported, comparing the performance of optimization algorithms among publications is infeasible. + The auto-tuning community identified this as a key challenge at the 2022 Lorentz Center workshop on auto-tuning. + The examination of the current state of the practice in this paper further underlines this. + We propose a community-driven methodology composed of four steps regarding experimental setup, tuning budget, dealing with stochasticity, and quantifying performance. + This methodology builds upon similar methodologies in other fields while taking into account the constraints and specific characteristics of the auto-tuning field, resulting in novel techniques. + The methodology is demonstrated in a simple case study that compares the performance of several optimization algorithms used to auto-tune CUDA kernels on a set of modern GPUs. + We provide a software tool to make the application of the methodology easy for authors, and simplifies reproducibility of results. + authors: + - given-names: Floris-Jan + family-names: Willemsen + email: f.q.willemsen@umail.leidenuniv.nl + affiliation: "Leiden University, Netherlands eScience Center" + orcid: "https://orcid.org/0000-0003-2295-8263" + - given-names: Richard + family-names: Schoonhoven + affiliation: Centrum Wiskunde & Informatica + orcid: "https://orcid.org/0000-0003-3659-929X" + - orcid: "https://orcid.org/0000-0002-5703-9673" + given-names: Jiří + family-names: Filipovič + affiliation: Masaryk University + - given-names: Jacob Odgård + family-names: Tørring + orcid: "https://orcid.org/0000-0002-9385-7948" + affiliation: Norwegian University of Science and Technology + - given-names: Rob + name-particle: van + family-names: Nieuwpoort + affiliation: Leiden University + orcid: "https://orcid.org/0000-0002-2947-9444" + - given-names: Ban + name-particle: van + family-names: Werkhoven + orcid: "https://orcid.org/0000-0002-7508-3272" + affiliation: "Leiden University, Netherlands eScience Center"