Automated Design Space Exploration of CGRA Processing Element Architectures using Frequent Subgraph Analysis

Caleb Donovick; Clark Barrett; Jackson Melchert; Kathleen Feng; Mark Horowitz; Pat Hanrahan; Priyanka Raina; Ross Daly

arxiv: 2104.14155 · v1 · pith:U24PDHGPnew · submitted 2021-04-29 · 💻 cs.AR

Automated Design Space Exploration of CGRA Processing Element Architectures using Frequent Subgraph Analysis

Jackson Melchert , Kathleen Feng , Caleb Donovick , Ross Daly , Clark Barrett , Mark Horowitz , Pat Hanrahan , Priyanka Raina This is my paper

classification 💻 cs.AR

keywords applicationcgraprocessingspecializedarchitecturearchitecturesautomateddomain

0 comments

read the original abstract

The architecture of a coarse-grained reconfigurable array (CGRA) processing element (PE) has a significant effect on the performance and energy efficiency of an application running on the CGRA. This paper presents an automated approach for generating specialized PE architectures for an application or an application domain. Frequent subgraphs mined from a set of applications are merged to form a PE architecture specialized to that application domain. For the image processing and machine learning domains, we generate specialized PEs that are up to 10.5x more energy efficient and consume 9.1x less area than a baseline PE.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

DICE: Enabling Efficient General-Purpose SIMT Execution with Statically Scheduled Coarse-Grained Reconfigurable Arrays
cs.AR 2026-05 conditional novelty 6.0

DICE achieves 1.77-1.90x dynamic energy efficiency and 42-46% power reduction versus modeled NVIDIA Turing SMs by executing SIMT workloads on pipelined CGRAs with p-graphs handling dynamism and 68% fewer register file...