ASAP: Automatic Synthesis of Area-Efficient and Precision-Aware CGRAs

Tan, Cheng; Tambe, Thierry; Zhang, Jeff; Fang, Bo; Geng, Tong; Wei, Gu-Yeon; Brooks, David; Tumeo, Antonino; Gopalakrishnan, Ganesh; Li, Ang

doi:10.1145/3524059.3532359

ASAP: Automatic Synthesis of Area-Efficient and Precision-Aware CGRAs

Conference · Mon Jun 27 04:00:00 EDT 2022

DOI:https://doi.org/10.1145/3524059.3532359· OSTI ID:1886255

Tan, Cheng ^[1]; Tambe, Thierry ^[2]; Zhang, Jeff ^[2]; Fang, Bo ^[3]; Geng, Tong ^[3]; Wei, Gu-Yeon ^[2]; Brooks, David ^[2]; Tumeo, Antonino ^[3]; Gopalakrishnan, Ganesh ^[4]; Li, Ang ^[3]

Microsoft
Harvard University
BATTELLE (PACIFIC NW LAB)
University of Utah

Coarse-grained reconfigurable accelerators (CGRAs) are a promising accelerator design choice that strikes a balance between performance and adaptability to different computing patterns across various applications domains. Designing a CGRA for a specific application domain involves enormous software/hardware engineering effort. Recent research works explore loop transformations, functional unit types, network topology, and memory size to identify optimal CGRA designs given a set of kernels from a specific application do- main. Unfortunately, the impact of functional units with different precision support has rarely been investigated. To address this gap, we propose ASAP – a hardware/software co-design framework that automatically identifies and synthesizes optimal precision-aware CGRA for a set of applications of interest. Our evaluation shows that ASAP generates specialized designs 3.2×, 4.21×, and 5.8× more efficient (in terms of performance per unit of energy or area) than non-specialized homogeneous CGRAs, for the scientific computing, embedded, and edge machine learning domains, respectively, with limited accuracy loss. Moreover, ASAP provides more efficient designs than other state-of-the-art synthesis frameworks for specialized CGRAs.

🛈

OSTI does not have a digital full text copy available. For more information, please see document availability, search WorldCat, or search Google Scholar.

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE

DOE Contract Number:: AC05-76RL01830

OSTI ID:: 1886255

Report Number(s):: PNNL-SA-172791

Country of Publication:: United States

Language:: English

References (30)

Locus Tan, Cheng; Kulkarni, Aditi; Venkataramani, Vanchinathan ACM Transactions on Embedded Computing Systems, Vol. 17, Issue 1 https://doi.org/10.1145/3122786	journal	November 2017
HyCUBE Karunaratne, Manupa; Mohite, Aditi Kulkarni; Mitra, Tulika Proceedings of the 54th Annual Design Automation Conference 2017 https://doi.org/10.1145/3061639.3062262	conference	June 2017
OpenCGRA: An Open-Source Unified Framework for Modeling, Testing, and Evaluating CGRAs Tan, Cheng; Xie, Chenhao; Li, Ang 2020 IEEE 38th International Conference on Computer Design (ICCD) https://doi.org/10.1109/ICCD50377.2020.00070	conference	October 2020
Plasticine Prabhakar, Raghu; Zhang, Yaqi; Koeplinger, David Proceedings of the 44th Annual International Symposium on Computer Architecture https://doi.org/10.1145/3079856.3080256	conference	June 2017
ADRES: An Architecture with Tightly Coupled VLIW Processor and Coarse-Grained Reconfigurable Matrix Mei, Bingfeng; Vernalde, Serge; Verkest, Diederik Field Programmable Logic and Application https://doi.org/10.1007/978-3-540-45234-8_7	book	January 2003
Xilinx Adaptive Compute Acceleration Platform Gaide, Brian; Gaitonde, Dinesh; Ravishankar, Chirag Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays https://doi.org/10.1145/3289602.3293906	conference	February 2019
Trading Accuracy for Power with an Underdesigned Multiplier Architecture Kulkarni, P.; Gupta, P.; Ercegovac, M. 2011 24th International Conference on VLSI Design: concurrently with the 10th International Conference on Embedded Systems Design, 2011 24th Internatioal Conference on VLSI Design https://doi.org/10.1109/VLSID.2011.51	conference	January 2011
Ultra-Elastic CGRAs for Irregular Loop Specialization Torng, Christopher; Pan, Peitian; Ou, Yanghui 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) https://doi.org/10.1109/HPCA51647.2021.00042	conference	February 2021
Exploiting loop-level parallelism on coarse-grained reconfigurable architectures using modulo scheduling Mei, B.; Vernalde, S.; Verkest, D. IEE Proceedings - Computers and Digital Techniques, Vol. 150, Issue 5 https://doi.org/10.1049/ip-cdt:20030833	journal	January 2003
Spatial: a language and compiler for application accelerators Koeplinger, David; Feldman, Matthew; Prabhakar, Raghu PLDI '18: ACM SIGPLAN Conference on Programming Language Design and Implementation, Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation https://doi.org/10.1145/3192366.3192379	conference	June 2018
Branch-Aware Loop Mapping on CGRAs Hamzeh, Mahdi; Shrivastava, Aviral; Vrudhula, Sarma Proceedings of the 51st Annual Design Automation Conference https://doi.org/10.1145/2593069.2593100	conference	June 2014
In-Datacenter Performance Analysis of a Tensor Processing Unit Jouppi, Norman P.; Borchers, Al; Boyle, Rick Proceedings of the 44th Annual International Symposium on Computer Architecture - ISCA '17 https://doi.org/10.1145/3079856.3080246	conference	January 2017
Polymorphic pipeline array Park, Hyunchul; Park, Yongjun; Mahlke, Scott Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture https://doi.org/10.1145/1669112.1669160	conference	December 2009
Dnestmap Karunaratne, Manupa; Tan, Cheng; Kulkarni, Aditi Proceedings of the 55th Annual Design Automation Conference https://doi.org/10.1145/3195970.3196027	conference	June 2018
DSAGEN: Synthesizing Programmable Spatial Accelerators Weng, Jian; Liu, Sihao; Dadu, Vidushi 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) https://doi.org/10.1109/ISCA45697.2020.00032	conference	May 2020
PyMTL3: A Python Framework for Open-Source Hardware Modeling, Generation, Simulation, and Verification Jiang, Shunning; Pan, Peitian; Ou, Yanghui IEEE Micro, Vol. 40, Issue 4 https://doi.org/10.1109/MM.2020.2997638	journal	July 2020
Toward Approximate Computing for Coarse-Grained Reconfigurable Architectures Akbari, Omid; Kamal, Mehdi; Afzali-Kusha, Ali IEEE Micro, Vol. 38, Issue 6 https://doi.org/10.1109/MM.2018.2873951	journal	November 2018
EGRA: A Coarse Grained Reconfigurable Architectural Template Ansaloni, Giovanni; Bonzini, Paolo; Pozzi, Laura IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Vol. 19, Issue 6 https://doi.org/10.1109/TVLSI.2010.2044667	journal	June 2011
CQNN: a CGRA-based QNN Framework Geng, Tong; Wu, Chunshu; Tan, Cheng 2020 IEEE High Performance Extreme Computing Conference (HPEC) https://doi.org/10.1109/HPEC43674.2020.9286194	conference	September 2020
MAERI: Enabling Flexible Dataflow Mapping over DNN Accelerators via Reconfigurable Interconnects Kwon, Hyoukjun; Samajdar, Ananda; Krishna, Tushar ACM SIGPLAN Notices, Vol. 53, Issue 2 https://doi.org/10.1145/3296957.3173176	journal	November 2018
LLVM: A compilation framework for lifelong program analysis & transformation Lattner, C.; Adve, V. International Symposium on Code Generation and Optimization, 2004. CGO 2004. https://doi.org/10.1109/CGO.2004.1281665	conference	January 2004
DynPaC: Coarse-Grained, Dynamic, and Partially Reconfigurable Array for Streaming Applications Tan, Cheng; Geng, Tong; Xie, Chenhao 2021 IEEE 39th International Conference on Computer Design (ICCD) https://doi.org/10.1109/ICCD53106.2021.00018	conference	October 2021
BioCare: An Energy-Efficient CGRA for Bio-Signal Processing at the Edge Ebrahimi, Zahra; Kumar, Akash 2021 IEEE International Symposium on Circuits and Systems (ISCAS) https://doi.org/10.1109/ISCAS51556.2021.9401461	conference	May 2021
A high-level synthesis and verification tool for fixed to floating point conversion Aslan, Semih; Oruklu, Erdal; Saniie, Jafar 2012 IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS) https://doi.org/10.1109/MWSCAS.2012.6292168	conference	August 2012
Iterative Search for Reconfigurable Accelerator Blocks With a Compiler in the Loop Willsey, Max; Lee, Vincent T.; Cheung, Alvin IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 38, Issue 3 https://doi.org/10.1109/TCAD.2018.2878194	journal	March 2019
Using mobile phone barometer for low-power transportation context detection Sankaran, Kartik; Zhu, Minhui; Guo, Xiang Fa Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems https://doi.org/10.1145/2668332.2668343	conference	November 2014
CGRA-ME: A unified framework for CGRA modelling and exploration Chin, S. Alexander; Sakamoto, Noriaki; Rui, Allan 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP) https://doi.org/10.1109/ASAP.2017.7995277	conference	July 2017
Low-Power Digital Signal Processing Using Approximate Adders Gupta, Vaibhav; Mohapatra, Debabrata; Raghunathan, Anand IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 32, Issue 1 https://doi.org/10.1109/TCAD.2012.2217962	journal	January 2013
Stitch: Fusible Heterogeneous Accelerators Enmeshed with Many-Core Architecture for Wearables Tan, Cheng; Karunaratne, Manupa; Mitra, Tulika 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA) https://doi.org/10.1109/ISCA.2018.00054	conference	June 2018
ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing Tan, Cheng; Xie, Chenhao; Geng, Tong IEEE Transactions on Parallel and Distributed Systems, Vol. 32, Issue 12 https://doi.org/10.1109/TPDS.2021.3081074	journal	December 2021

Similar Records

AURORA: Automated Refinement of Coarse-Grained Reconfigurable Accelerators

Conference · Sun Jan 31 23:00:00 EST 2021 · OSTI ID:1820385

VecPAC: A Vectorizable and Precision-Aware CGRA

Conference · Wed Nov 29 23:00:00 EST 2023 · OSTI ID:2348882

ICED: An Integrated CGRA Framework Enabling DFVS-Aware Acceleration

Conference · Sun Nov 03 23:00:00 EST 2024 · OSTI ID:2564121

Related Subjects

artificial intelligence

ASAP: Automatic Synthesis of Area-Efficient and Precision-Aware CGRAs

Citation Formats

References (30)

Similar Records

Related Subjects