GAHLS: an optimized graph analytics based high level synthesis framework

Xiao, Yao; Nazarian, Shahin; Bogdan, Paul

doi:10.1038/s41598-023-48981-x

Title: GAHLS: an optimized graph analytics based high level synthesis framework

Journal Article · 19 December 2023 · Scientific Reports

DOI: https://doi.org/10.1038/s41598-023-48981-x · OSTI ID:2470347

Xiao, Yao ^[1]; Nazarian, Shahin ^[1]; Bogdan, Paul ^[1]

Univ. of Southern California, Los Angeles, CA (United States)

The urgent need for low latency, high-compute and low power on-board intelligence in autonomous systems, cyber-physical systems, robotics, edge computing, evolvable computing, and complex data science calls for determining the optimal amount and type of specialized hardware together with reconfigurability capabilities. With these goals in mind, we propose a novel comprehensive graph analytics based high level synthesis (GAHLS) framework that efficiently analyzes complex high level programs through a combined compiler-based approach and graph theoretic optimization and synthesizes them into message passing domain-specific accelerators. This GAHLS framework first constructs a compiler-assisted dependency graph (CaDG) from low level virtual machine (LLVM) intermediate representation (IR) of high level programs and converts it into a hardware friendly description representation. Next, the GAHLS framework performs a memory design space exploration while account for the identified computational properties from the CaDG and optimizing the system performance for higher bandwidth. The GAHLS framework also performs a robust optimization to identify the CaDG subgraphs with similar computational structures and aggregate them into intelligent processing clusters in order to optimize the usage of underlying hardware resources. Finally, the GAHLS framework synthesizes this compressed specialized CaDG into processing elements while optimizing the system performance and area metrics. Evaluations of the GAHLS framework on several real-life applications (e.g., deep learning, brain machine interfaces) demonstrate that it provides 14.27× performance improvements compared to state-of-the-art approaches such as LegUp 6.2.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Univ. of Southern California, Los Angeles, CA (United States)

Sponsoring Organization:: USDOE

OSTI ID:: 2470347

Journal Information:: Scientific Reports, Journal Name: Scientific Reports Journal Issue: 1 Vol. 13; ISSN 2045-2322

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

References (42)

Gaussian Processes in Machine Learning Rasmussen, Carl Edward Advanced Lectures on Machine Learning https://doi.org/10.1007/978-3-540-28650-9_4	book	January 2004
Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation Gabriel, Edgar; Fagg, Graham E.; Bosilca, George Recent Advances in Parallel Virtual Machine and Message Passing Interface https://doi.org/10.1007/978-3-540-30218-6_19	book	January 2004
Application of Bayesian approach to numerical methods of global and stochastic optimization Mockus, Jonas Journal of Global Optimization, Vol. 4, Issue 4 https://doi.org/10.1007/BF01099263	journal	June 1994
An analysis of approximations for maximizing submodular set functions—I Nemhauser, G. L.; Wolsey, L. A.; Fisher, M. L. Mathematical Programming, Vol. 14, Issue 1 https://doi.org/10.1007/BF01588971	journal	December 1978
Balanced Partitions of Trees and Applications Feldmann, Andreas Emil; Foschini, Luca Algorithmica, Vol. 71, Issue 2 https://doi.org/10.1007/s00453-013-9802-3	journal	July 2013
Brain–computer interfaces for communication and rehabilitation Chaudhary, Ujwal; Birbaumer, Niels; Ramos-Murguialday, Ander Nature Reviews Neurology, Vol. 12, Issue 9 https://doi.org/10.1038/nrneurol.2016.113	journal	August 2016
Reliable Multi-Fractal Characterization of Weighted Complex Networks: Algorithms and Implications Xue, Yuankun; Bogdan, Paul Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-07209-5	journal	August 2017
Deciphering the generating rules and functionalities of complex networks Xiao, Xiongye; Chen, Hanlong; Bogdan, Paul Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-02203-4	journal	November 2021
Opportunities for neuromorphic computing algorithms and applications Schuman, Catherine D.; Kulkarni, Shruti R.; Parsa, Maryam Nature Computational Science, Vol. 2, Issue 1 https://doi.org/10.1038/s43588-021-00184-y	journal	January 2022
Fast and accurate short read alignment with Burrows-Wheeler transform Li, H.; Durbin, R. Bioinformatics, Vol. 25, Issue 14 https://doi.org/10.1093/bioinformatics/btp324	journal	May 2009
MLP aware heterogeneous memory system Phadke, S.; Narayanasamy, S. 2011 Design, Automation & Test in Europe https://doi.org/10.1109/DATE.2011.5763155	conference	March 2011
High-level synthesis of dynamic data structures: A case study using Vivado HLS Winterstein, Felix; Bayliss, Samuel; Constantinides, George A. 2013 International Conference on Field-Programmable Technology (FPT) https://doi.org/10.1109/FPT.2013.6718388	conference	December 2013
Hybrid memory cube (HMC) Pawlowski, J. Thomas 2011 IEEE Hot Chips 23 Symposium (HCS) https://doi.org/10.1109/HOTCHIPS.2011.7477494	conference	August 2011
A load balancing inspired optimization framework for exascale multicore systems: A complex networks approach Xiao, Yao; Xue, Yuankun; Nazarian, Shahin 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) https://doi.org/10.1109/ICCAD.2017.8203781	conference	November 2017
Re-Thinking EEG-Based Non-Invasive Brain Interfaces: Modeling and Analysis Gupta, Gaurav; Pequito, Sergio; Bogdan, Paul 2018 ACM/IEEE 9th International Conference on Cyber-Physical Systems (ICCPS) https://doi.org/10.1109/ICCPS.2018.00034	conference	April 2018
25.2 A 1.2V 8Gb 8-channel 128GB/s high-bandwidth memory (HBM) stacked DRAM with effective microbump I/O test methods using 29nm process and TSV Lee, Dong Uk; Kim, Kyung Whan; Kim, Kwan Weon 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) https://doi.org/10.1109/ISSCC.2014.6757501	conference	February 2014
A 16Gb/s/pin 8Gb GDDR6 DRAM with bandwidth extension techniques for high-speed applications Hwang, Kyu-Dong; Kim, Boram; Byeon, Sang-Yeon 2018 IEEE International Solid - State Circuits Conference - (ISSCC) https://doi.org/10.1109/ISSCC.2018.8310258	conference	February 2018
Taking the Human Out of the Loop: A Review of Bayesian Optimization Shahriari, Bobak; Swersky, Kevin; Wang, Ziyu Proceedings of the IEEE, Vol. 104, Issue 1 https://doi.org/10.1109/JPROC.2015.2494218	journal	January 2016
Platform Storage Performance With 3D XPoint Technology Hady, Frank T.; Foong, Annie; Veal, Bryan Proceedings of the IEEE, Vol. 105, Issue 9 https://doi.org/10.1109/JPROC.2017.2731776	journal	September 2017
Enabling Efficient and Scalable Hybrid Memories Using Fine-Granularity DRAM Cache Management Meza, Justin; Chang, Jichuan; Yoon, HanBin IEEE Computer Architecture Letters, Vol. 11, Issue 2 https://doi.org/10.1109/L-CA.2012.2	journal	July 2012
Where to go Next: Learning a Subgoal Recommendation Policy for Navigation in Dynamic Environments Brito, Bruno; Everett, Michael; How, Jonathan P. IEEE Robotics and Automation Letters, Vol. 6, Issue 3 https://doi.org/10.1109/LRA.2021.3068662	journal	July 2021
CHAMELEON: A Dynamically Reconfigurable Heterogeneous Memory System Kotra, Jagadish B.; Zhang, Haibo; Alameldeen, Alaa R. 2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) https://doi.org/10.1109/MICRO.2018.00050	conference	October 2018
Siena: Exploring the Design Space of Heterogeneous Memory Systems Peng, Ivy B.; Vetter, Jeffrey S. SC18: International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1109/SC.2018.00036	conference	November 2018
Self-Optimizing and Self-Programming Computing Systems: A Combined Compiler, Complex Networks, and Machine Learning Approach Xiao, Yao; Nazarian, Shahin; Bogdan, Paul IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Vol. 27, Issue 6 https://doi.org/10.1109/TVLSI.2019.2897650	journal	June 2019
Optimization by Simulated Annealing Kirkpatrick, S.; Gelatt, C. D.; Vecchi, M. P. Science, Vol. 220, Issue 4598 https://doi.org/10.1126/science.220.4598.671	journal	May 1983
The grand challenges of Science Robotics Yang, Guang-Zhong; Bellingham, Jim; Dupont, Pierre E. Science Robotics, Vol. 3, Issue 14 https://doi.org/10.1126/scirobotics.aar7650	journal	January 2018
Insect-inspired AI for autonomous robots de Croon, G. C. H. E.; Dupeyroux, J. J. G.; Fuller, S. B. Science Robotics, Vol. 7, Issue 67 https://doi.org/10.1126/scirobotics.abl6334	journal	June 2022
Outer-loop vectorization: revisited for short SIMD architectures Nuzman, Dorit; Zaks, Ayal Proceedings of the 17th international conference on Parallel architectures and compilation techniques - PACT '08 https://doi.org/10.1145/1454115.1454119	conference	January 2008
Architecting phase change memory as a scalable dram alternative Lee, Benjamin C.; Ipek, Engin; Mutlu, Onur Proceedings of the 36th annual international symposium on Computer architecture - ISCA '09 https://doi.org/10.1145/1555754.1555758	conference	January 2009
PDRAM: a hybrid PRAM and DRAM main memory system Dhiman, Gaurav; Ayoub, Raid; Rosing, Tajana Proceedings of the 46th Annual Design Automation Conference on ZZZ - DAC '09 https://doi.org/10.1145/1629911.1630086	conference	January 2009
LegUp: high-level synthesis for FPGA-based processor/accelerator systems Canis, Andrew; Choi, Jongsok; Aldham, Mark Proceedings of the 19th ACM/SIGDA international symposium on Field programmable gate arrays - FPGA '11 https://doi.org/10.1145/1950413.1950423	conference	January 2011
LegUp Canis, Andrew; Choi, Jongsok; Aldham, Mark ACM Transactions on Embedded Computing Systems, Vol. 13, Issue 2 https://doi.org/10.1145/2514740	journal	September 2013
System-Level Design of Networks-on-Chip for Heterogeneous Systems-on-Chip Yoon, Young Jin; Mantovani, Paolo; Carloni, Luca P. Proceedings of the Eleventh IEEE/ACM International Symposium on Networks-on-Chip https://doi.org/10.1145/3130218.3130238	conference	October 2017
Gas Zhou, Minxuan; Imani, Mohsen; Gupta, Saransh Proceedings of the International Symposium on Low Power Electronics and Design https://doi.org/10.1145/3218603.3218631	conference	July 2018
DNNBuilder Zhang, Xiaofan; Wang, Junsong; Zhu, Chao Proceedings of the International Conference on Computer-Aided Design https://doi.org/10.1145/3240765.3240801	conference	November 2018
NEURA ghe Meloni, Paolo; Capotondi, Alessandro; Deriu, Gianfranco ACM Transactions on Reconfigurable Technology and Systems, Vol. 11, Issue 3 https://doi.org/10.1145/3284357	journal	September 2018
code2vec: learning distributed representations of code Alon, Uri; Zilberstein, Meital; Levy, Omer Proceedings of the ACM on Programming Languages, Vol. 3, Issue POPL https://doi.org/10.1145/3290353	journal	January 2019
ScaleHLS Ye, Hanchen; Jun, HyeGang; Jeong, Hyunmin Proceedings of the 59th ACM/IEEE Design Automation Conference https://doi.org/10.1145/3489517.3530631	conference	July 2022
Early DSE and Automatic Generation of Coarse-grained Merged Accelerators Brumar, Iulian; Zacharopoulos, Georgios; Yao, Yuan ACM Transactions on Embedded Computing Systems, Vol. 22, Issue 2 https://doi.org/10.1145/3546070	journal	January 2023
The Chip Is the Network: Toward a Science of Network-on-Chip Design Marculescu, Radu; Bogdan, Paul Foundations and Trends® in Electronic Design Automation, Vol. 2, Issue 4 https://doi.org/10.1561/1000000011	journal	January 2009
Investigating Causal Relations by Econometric Models and Cross-spectral Methods Granger, C. W. J. Econometrica, Vol. 37, Issue 3 https://doi.org/10.2307/1912791	journal	August 1969
A Spatio-Temporal Fractal Model for a CPS Approach to Brain-Machine-Body Interfaces Xue, Yuankun; Rodriguez, Saul; Bogdan, Paul Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE) https://doi.org/10.3850/9783981537079_0502	conference	January 2016

Similar Records

Using MLIR Framework for Codesign of ML Architectures Algorithms and Simulation Tools

Technical Report · 2021 · OSTI ID:1764336

Lewis, Cannada; Hughes, Clayton; Hammond, Simon David; +1 more

Towards Automated Generation of Chiplet-Based Systems

Conference · 2024 · OSTI ID:2426424

Limaye, Ankur M.; Barone, Claudio; Bohm Agostini, Nicolas; +8 more

BioGraphE: High-performance bionetwork analysis using the Biological Graph Environment

Journal Article · 2008 · BMC Bioinformatics, 9(s6) · OSTI ID:949094

Chin, George; Chavarría-Miranda, Daniel; Nakamura, Grant C; +1 more

Related Subjects

97 MATHEMATICS AND COMPUTING
computer science
electrical engineering

Title: GAHLS: an optimized graph analytics based high level synthesis framework

Citation Formats

References (42)

Similar Records

Related Subjects