Joint program and layout transformations to enable convolutional operators on specialized hardware based on constraint programming

D Rieber, A Acosta, H Fröning - ACM Transactions on Architecture and …, 2021 - dl.acm.org
The success of Deep Artificial Neural Networks (DNNs) in many domains created a rich
body of research concerned with hardware accelerators for compute-intensive DNN …

Search space complexity of iteration domain based instruction embedding for deep learning accelerators

D Rieber, H Fröning - IoT Streams for Data-Driven Predictive Maintenance …, 2020 - Springer
With the success of deep learning applications in many domains, the number of new deep
learning operators and hardware accelerators increased significantly in recent years …

Deployment of Deep Neural Networks on Dedicated Hardware Accelerators

DS Rieber - 2023 - archiv.ub.uni-heidelberg.de
Deep Neural Networks (DNNs) have established themselves as powerful tools for a wide
range of complex tasks, for example computer vision or natural language processing. DNNs …

[HTML][HTML] Pattern Mining and Genetic Improvement in Compilers and Interpreters/submitted by Oliver Krauss MSc

O Krauss - 2022 - epub.jku.at
Writing source code is a challenging task, requiring the understanding of complex concepts,
algorithms and programming paradigms. This task becomes increasingly challenging when …

[PDF][PDF] The Programming of Deep Learning Accelerators as a Constraint Satisfaction Problem.

D Rieber, A Acosta, H Fröning - arXiv preprint arXiv:2104.04731, 2021 - ask.qcloudimg.com
A detailed evaluation using the VTA hardware accelerator with the Baidu DeepBench
inference benchmark suite shows that our approach can automatically generate code …