Journal
ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS
Volume 27, Issue 4, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3503540
Keywords
High-level synthesis; correlated multi-objective optimization; multi-fidelity optimization; design space exploration; Gaussian process
Funding
- Research Grants Council of Hong Kong SAR [CUHK14209420]
- Innovation and Technology Fund [PRP/065/20FX]
- SmartMore
Ask authors/readers for more resources
High-level synthesis (HLS) tools simplify the implementation of modern applications on FPGA by using high-level languages and HLS directives. However, finding good HLS directives is challenging. To address this, a novel automatic optimization algorithm is proposed to explore multiple objectives by utilizing data from different FPGA design stages.
High-level synthesis (HLS) tools have gained great attention in recent years because it emancipates engineers from the complicated and heavy hardware description language writing and facilitates the implementations of modern applications (e.g., deep learning models) on Field-programmable Gate Array (FPGA), by using high-level languages and HLS directives. However, finding good HLS directives is challenging, due to the time-consuming design processes, the balances among different design objectives, and the diverse fidelities (accuracies of data) of the performance values between the consecutive FPGA design stages. To find good HLS directives, a novel automatic optimization algorithm is proposed to explore the Pareto designs of the multiple objectives while making full use of the data with different fidelities from different FPGA design stages. Firstly, a non-linear Gaussian process (GP) is proposed to model the relationships among the different FPGA design stages. Secondly, for the first time, the GP model is enhanced as correlated GP (CGP) by considering the correlations between the multiple design objectives, to find better Pareto designs. Furthermore, we extend our model to be a deep version deep CGP (DCGP) by using the deep neural network to improve the kernel functions in Gaussian process models, to improve the characterization capability of the models, and learn better feature representations. We test our design method on some public benchmarks (including generalmatrixmultiplication and sparse matrix-vectormultiplication) and deep learning-based object detection model iSmart2 on FPGA. Experimental results show that our methods outperform the baselines significantly and facilitate the deep learning designs on FPGA.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available