ML-CGRA: An Integrated Compilation Framework to Enable Efficient Machine Learning Acceleration on CGRAs

Conference · Fri Sep 15 04:00:00 EDT 2023

DOI:https://doi.org/10.1109/DAC56929.2023.10247873· OSTI ID:2280647

Luo, Yixuan ^[1]; Tan, Cheng ^[2]; Bohm Agostini, Nicolas ^[3]; Li, Ang ^[3]; Tumeo, Antonino ^[3]; Dave, Nirav ^[2]; Geng, Tong ^[1]

---

1. University of Rochester
2. Microsoft
3. BATTELLE (PACIFIC NW LAB)

Coarse-Grained Reconfigurable Arrays (CGRAs) can achieve higher energy-efficiency than general-purpose processors and accelerators or fine-grained reconfigurable devices, while maintaining adaptability to different computational patterns. CGRAs have shown some success as a platform to accelerate machine learning (ML) thanks to their flexibility, which allows them to support new models not considered by fixed accelerators. However, current solutions for CGRAs employ low level instruction-based compiler approaches and lack specialized compilation infrastructures from high-level ML frameworks that could leverage semantic information from the models, limiting the ability to efficiently map them on the recon- figurable substrate. This paper proposes ML-CGRA, an integrated compilation framework based on the MLIR infrastructure that en- ables efficient ML acceleration on CGRAs. ML-CGRA provides an end-to-end solution for mapping ML models on CGRAs that out- performs conventional approaches by 3.15× and 6.02 × on 4×4 and 8×8 CGRAs, respectively.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 2280647
• Report Number(s): PNNL-SA-180015
• Country of Publication: United States
• Language: English

Related Subjects

machine learning