CGRA-ME 2.0: A Research Framework for Next-Generation CGRA Architectures and CAD
Authors:
- 27 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 642-649
Abstract
Coarse-grained reconfigurable arrays (CGRAs) belong to the family of configurable processing architectures that have recently attracted increasing interest for their adaptability and efficiency. Research on CGRA architectures and their associated CAD tools is typically conducted empirically, by modelling a CGRA fabric, mapping applications onto it, and then assessing performance, power, and/or area (PPA). In this paper, we describe an open-source framework for such CGRA research - CGRA-ME - CGRA modelling and exploration. We describe the recently released version 2.0 of CGRA - ME, which incorporates a new mapping approach, support for elastic CGRAs, floating point, predication, hybrid RISC-V+CGRA systems, and more.Keywords
This publication has 37 references indexed in Scilit:
- Power, Performance and Area Consequences of Multi-Context Support in CGRAs2021
- OpenCGRA: Democratizing Coarse-Grained Reconfigurable Arrays2021
- MLIR: Scaling Compiler Infrastructure for Domain Specific Computation2021
- Accelerating Nested Conditionals on CGRA With Tag-Based Full Predication MethodIEEE Access, 2020
- LLVM: A compilation framework for lifelong program analysis & transformation2004
- ADRES: An Architecture with Tightly Coupled VLIW Processor and Coarse-Grained Reconfigurable Matrix2003
- PACT XPP—A Self-Reconfigurable Data Processing ArchitectureThe Journal of Supercomputing, 2003
- Exploiting loop-level parallelism on coarse-grained reconfigurable architectures using modulo schedulingIEE Proceedings - Computers and Digital Techniques, 2003
- VPR: a new packing, placement and routing tool for FPGA research1997
- The directed subgraph homeomorphism problemTheoretical Computer Science, 1980