82 citations · 146 across the 7 of their papers we have counts for
8 papers
Ansor: Generating High-Performance Tensor Programs for Deep Learning
Lianmin Zheng, Chengfan Jia, Minmin Sun +9
High-performance tensor programs are crucial to guarantee efficient execution of deep neural networks. However, obtaining performant tensor programs for different operators on vari…
ProTuner: Tuning Programs with Monte Carlo Tree Search
Ameer Haj-Ali, Hasan Genc, Qijing Huang +4
We explore applying the Monte Carlo Tree Search (MCTS) algorithm in a notoriously difficult task: tuning programs for high-performance deep learning and image processing. We build…
AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning
Qijing Huang, Ameer Haj-Ali, William Moses +4
The performance of the code a compiler generates depends on the order in which it applies the optimization passes. Choosing a good order--often referred to as the phase-ordering pr…
AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs
Keertana Settaluri, Ameer Haj-Ali, Qijing Huang +2
Domain specialization under energy constraints in deeply-scaled CMOS has been driving the need for agile development of Systems on a Chip (SoCs). While digital subsystems have desi…
Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration
Hasan Genc, Seah Kim, Alon Amid +16
DNN accelerators are often developed and evaluated in isolation without considering the cross-stack, system-level effects in real-world environments. This makes it difficult to app…
A View on Deep Reinforcement Learning in System Optimization
Ameer Haj-Ali, Nesreen K. Ahmed, Ted Willke +3
Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often seque…
NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning
Ameer Haj-Ali, Nesreen K. Ahmed, Ted Willke +3
One of the key challenges arising when compilers vectorize loops for today's SIMD-compatible architectures is to decide if vectorization or interleaving is beneficial. Then, the co…
AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning
Ameer Haj-Ali, Qijing Huang, William Moses +4
The performance of the code generated by a compiler depends on the order in which the optimization passes are applied. In high-level synthesis, the quality of the generated circuit…