is aimed at providing a scalable and CK-powered tournament framework, a common experimental methodology
and an open repository for continuous evaluation and optimization of the quality vs. efficiency Pareto
optimality of a wide range of real-world applications, libraries and models across the whole hardware/software stack on complete platforms.
ReQuEST also promotes reproducibility of experimental results and reusability of systems research artifacts by standardizing evaluation methodologies
and facilitating the deployment of efficient solutions on heterogeneous platforms. The organizers
develop a supporting open-source and portable workflow framework to provide unified evaluation and real-time leader-board of shared solutions.
ReQuEST promotes quality-awareness to the architecture and systems community, and resource-awareness to the applications community and end-users.
We will keep and continuously update the best or original solutions close to a Pareto frontier in a multi-dimensional space of accuracy, execution time,
power consumption, memory usage, resiliency, code/hardware/model size, costs and other metrics in a public repository.
We collaborate with Raspberry Pi foundation
for a new educational initiative to teach students and researchers
how to automatically optimize and test (autotuning, crowd-tuning and crowd-fuzzing)
realistic workloads in terms of speed, size, energy usage, accuracy and costs
across diverse software and hardware stack
using CK workflow framework and
open optimization repository.
The non-profit cTuning foundation
and dividiti regularly help various
international projects (MILEPOST,
and assist scientists in crowdsourcing and reproducing experiments,
and developing customizable and sustainable research software
powered by CK
which can now survive in a Cambrian AI/SW/HW chaos
or when leading researchers leave!
We help colleagues from the University of Edinburgh and Glasgow
use CK to automate and crowdsource optimization of mathematical libraries
University of Cambridge colleagues
use Collective Knowledge framework
to develop sustainable software, accelerate research,
automate experimentation and reuse artifacts.
For example, portable and reproducible experimental workflow from the
"Software Prefetching for Indirect Memory Accesses" article
by Sam Ainsworth and Timothy M. Jones
received a distinguished artifact award at CGO'17.
Non-profit cTuning foundation is the main coordinator and sponsor of all CK developments
and CK-powered educational initiatives such
as Artifact Evaluation.
It also partnered with dividiti to facilitate technology transfer from academia to industry
while boosting innovation in science and technology!