Collective Knowledge repository with reproducible experimental results from collaborative program autotuning on Raspberry Pi (program reactions to most efficient compiler optimizations)
收藏DataCite Commons2025-05-01 更新2024-07-27 收录
下载链接：
https://figshare.com/articles/Collective_Knowledge_repository_with_reproducible_experimental_results_from_collaborative_program_autotuning_on_Raspberry_Pi_program_reactions_to_most_efficient_compiler_optimizations_/5789007/2
下载链接
链接失效反馈官方服务：
资源简介：
Optimization results to demonstrate compiler autotuning, crowd-tuning and machine learning on RPi3 via customizable Collective Knowledge workflow framework with a portable package manager.<br><br>These results in the Collective Knowledge format help prototype a common and reproducible optimization methodology to support Artifact evaluation and Pareto-efficient co-design competitions of the whole software and hardware stack for emerging workloads such as deep learning in terms of speed, accuracy, energy and costs:<br>* http://cKnowledge.org/request<br>* http://cTuning.org/ae<br><br>Interactive CK report: http://cKnowledge.org/rpi-crowd-tuning<br><br>ArXiv report: https://arxiv.org/abs/1801.08024<br><br>
本数据集为通过搭载便携包管理器的可定制Collective Knowledge (CK) 工作流框架，在树莓派3代（RPi3）上演示编译器自动调优、众包调优与机器学习的优化结果。<br><br>这些采用Collective Knowledge格式的结果可用于原型化通用且可复现的优化方法论，以支撑面向深度学习等新兴工作负载的全软硬件栈的工件评估与帕累托高效协同设计竞赛，相关评估维度涵盖速度、精度、能耗与成本：<br>* http://cKnowledge.org/request<br>* http://cTuning.org/ae<br><br>交互式CK报告：http://cKnowledge.org/rpi-crowd-tuning<br><br>arXiv报告：https://arxiv.org/abs/1801.08024<br><br>
提供机构：
figshare
创建时间：
2018-01-16
