Fast and Accurate Estimation of Quality of Results in High-Level Synthesis with Machine Learning
Authors:
- Steve DaiSDSteve Dai
- Yuan ZhouYZYuan Zhou
- Hang ZhangHZHang Zhang
- Ecenur UstunEUEcenur Ustun
- Evangeline F.Y. YoungEYEvangeline F.Y. Young
- Zhiru ZhangZZZhiru Zhang
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-132
Abstract
While high-level synthesis (HLS) offers sophisticated techniques to optimize designs for area and performance, HLS-estimated resource usage and timing often deviate significantly from actual quality of results (QoR) achieved by FPGA-targeted designs. Inaccurate HLS estimates prevent designers from performing meaningful design space exploration without resorting to the time-consuming downstream implementation process. To address this challenge, we first build a large collection of C-to-FPGA results from a diverse set of realistic HLS applications and identify relevant features from HLS reports for estimating post-implementation metrics. We then leverage these features and data to train and compare a number of promising machine learning models to effectively and efficiently bridge the accuracy gap. Experiments demonstrate that our proposed approach is able to dramatically reduce the estimation errors for different families of FPGA devices. By extracting domain-specific insights from our experiments, we explore the implications of our models and predictive influence of various features for enabling fast and accurate QoR estimation in HLS. We have released our dataset to springboard future efforts in this area.Keywords
This publication has 6 references indexed in Scilit:
- XGBoost2016
- Automatic generation of efficient accelerators for reconfigurable hardwareACM SIGARCH Computer Architecture News, 2016
- AladdinACM SIGARCH Computer Architecture News, 2014
- S2CBench: Synthesizable SystemC Benchmark Suite for High-Level SynthesisIEEE Embedded Systems Letters, 2014
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989