Presentation
Centralized Training and Decentralized Control through the Actor-Critic Paradigm for Highly Optimized Multicores
SessionML-Powered Logic Synthesis
DescriptionWhile distributed, neural-network-based resource con-
trollers represent the state of the art for their ability to cope with the
ever-expanding decision space, such approaches suffer from several limi-
tations, like conflicting control decisions and partial observability. These
effects can significantly impair the controllers' learning capabilities and
the robustness of their control policies, causing substantial performance
losses. We are the first to solve this problem by employing a centralized
training and decentralized control regime to mitigate the aforementioned
limitations. Specifically, we design a centralized neural network (critic)
that evaluates the behavior of multiple decentralized, neural controllers
(actors) in a system-wide context. The objective of our proposed technique
is to maximize the performance under a temperature constraint through
dynamic voltage frequency scaling. The evaluation of our technique on
a real processor shows its superiority to the state of the art technique,
yielding average (peak) performance improvements of 20% (34%), which
we consider a breakthrough as the gains are measured on a real-world
platform.
trollers represent the state of the art for their ability to cope with the
ever-expanding decision space, such approaches suffer from several limi-
tations, like conflicting control decisions and partial observability. These
effects can significantly impair the controllers' learning capabilities and
the robustness of their control policies, causing substantial performance
losses. We are the first to solve this problem by employing a centralized
training and decentralized control regime to mitigate the aforementioned
limitations. Specifically, we design a centralized neural network (critic)
that evaluates the behavior of multiple decentralized, neural controllers
(actors) in a system-wide context. The objective of our proposed technique
is to maximize the performance under a temperature constraint through
dynamic voltage frequency scaling. The evaluation of our technique on
a real processor shows its superiority to the state of the art technique,
yielding average (peak) performance improvements of 20% (34%), which
we consider a breakthrough as the gains are measured on a real-world
platform.
Event Type
Research Manuscript
TimeWednesday, June 2511:45am - 12:00pm PDT
Location3004, Level 3