cTuning foundation (founding member of MLCommons)'s Projects
Validated Collective Knowledge workflows and results from the 1st ACM ReQuEST tournament on co-design of Pareto-efficient SW/HW stack for image classification at ASPLOS'18:
Collected experimental results in the CK format from the ReQuEST@ASPLOS'18 tournament on reproducible SW/HW co-design of Pareto-efficient deep learning for the following submission:
Collected experimental results in the CK format from the ReQuEST@ASPLOS'18 tournament on reproducible SW/HW co-design of Pareto-efficient deep learning for the following submission:
Collected experimental results in the CK format from the ReQuEST@ASPLOS'18 tournament on reproducible SW/HW co-design of Pareto-efficient deep learning for the following submission:
Collected experimental results in the CK format from the ReQuEST@ASPLOS'18 tournament on reproducible SW/HW co-design of Pareto-efficient deep learning for the following submission:
Collected experimental results in the CK format from the ReQuEST@ASPLOS'18 tournament on reproducible SW/HW co-design of Pareto-efficient deep learning for the following submission:
ResCuE-HPC workshop series (Reproducible, Customizable and Portable Workflows for HPC)
CK repository for Rigetti Computing workflows
CK repository to collaboratively optimize benchmarks, kernels and realistic workloads across Raspberry Pi devices provided by volunteers (starting from compiler flag autotuning). Interactive article with all results:
Demonstration of compiler autotuning, crowd-tuning and machine learning on RPi3 via customizable Collective Knowledge workflow framework with a portable package manager. This technology supports Pareto-efficient software/hardware co-design tournaments of deep learning in terms of speed, accuracy, energy, costs:
Some RPi3 autotuning results from Xored
The procedures and a workflow to prepare Student Cluster Competition submissions:
Beta Collective Knowledge workflow to automate installation, execution, customization and validation of SeisSol application from the SCC18 Reproducibility Challenge across different platforms and environments:
Collective Knowledge repository with CK package and virtual environment front-end for Spack packages:
Prototyping CK workflows for ML training
Collective Knowledge components for TensorFlow (code, data sets, models, packages, workflows):
Collective Knowledge repository for NVIDIA's TensorRT
Collective Knowledge experimental workflow to crowd-benchmark and crowd-tune Tiny DNN. Currently on stall due to lack of time and resources. Further info about collaborative DNN optimization:
Portable and customizable Collective Knowledge workflows for TVM and VTA:
Collective Knowledge workflow for ARM's workload automation tool: an open framework for gathering and sharing knowledge about system design and optimization using real-world workloads.
Extra resources in the Collective Knowledge Format for ARM's Workload Automation Framework:
ARM's workloads in the universal Collective Knowledge Format with JSON API and JSON meta information to power Workload Automation Framework
Collective Knowledge web extension to browse CK repositories, visualize interactive graphs and articles, render CK-based websites, implement simple web services with JSON API (for example to crowdsource experiments or unify access to DNN). Demos of interactive articles, graphs and crowdsourced experiments:
ADAPT workshop website powered by CK
CK repository for cKnowledge.org website:
Minimal CK components for Windows
Brainstorming and prototyping the 3rd generation of the Collective Knowledge technology:
MLPerf inference results in the MLCommons CM format for the Collective Knowledge Platform
Tuned OpenCL BLAS
Android application to participate in experiment crowdsourcing (such as workload crowd-benchmarking and crowd-tuning) using Collective Knowledge Framework and open repositories of knowledge: