Skip to content
conftrace_
2022 OSDI OSDI 2022

ROLLER: Fast and Efficient Tensor Compilation for Deep Learning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, Gennady Pekhimenko

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Application Areas > Efficient Computing Deep Learning > Techniques > Model Architecture

Keywords

performance model tensor compilation kernel generation tile abstraction search space
Download PDF

More from OSDI 2022

All OSDI 2022 papers →
ODINFS: Scaling PM Performance with Opportunistic Delegation
DURINN: Adversarial Memory and Thread Interleaving for Detecting Durable Linearizability Bugs
SparTA: Deep-Learning Model Sparsity via Tensor-with-Sparsity-Attribute
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization
Trinity: High-Performance Mobile Emulation through Graphics Projection