TY - GEN
T1 - Improving the performance of ADAS application in heterogeneous context
T2 - 20th IEEE International Conference on Intelligent Transportation Systems, ITSC 2017
AU - Wang, Xiebing
AU - Cui, Mingyue
AU - Huang, Kai
AU - Knoll, Alois
AU - Chen, Long
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - This paper investigates the optimization of OpenCL-based ADAS applications in heterogeneous context. In particular, we take the widely-used lane detection algorithm (LDA) as a case study. The application is profiled to identify the performance bottlenecks and then three optimization strategies are adopted. On the kernel side, the parallel granularity is regulated via compute unit replication and loop unrolling. On the host side, the kernel API function calls are scheduled in an interleaved manner to overlap the accelerator execution time. Moreover, the computation workload of the algorithm is tuned by dynamically adjusting the processed image ROI size. Experimental results reveal that the optimized implementation can achieve an average 2.27x speedup when compared with the naive parallel application.
AB - This paper investigates the optimization of OpenCL-based ADAS applications in heterogeneous context. In particular, we take the widely-used lane detection algorithm (LDA) as a case study. The application is profiled to identify the performance bottlenecks and then three optimization strategies are adopted. On the kernel side, the parallel granularity is regulated via compute unit replication and loop unrolling. On the host side, the kernel API function calls are scheduled in an interleaved manner to overlap the accelerator execution time. Moreover, the computation workload of the algorithm is tuned by dynamically adjusting the processed image ROI size. Experimental results reveal that the optimized implementation can achieve an average 2.27x speedup when compared with the naive parallel application.
UR - http://www.scopus.com/inward/record.url?scp=85046267317&partnerID=8YFLogxK
U2 - 10.1109/ITSC.2017.8317725
DO - 10.1109/ITSC.2017.8317725
M3 - Conference contribution
AN - SCOPUS:85046267317
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 1
EP - 6
BT - 2017 IEEE 20th International Conference on Intelligent Transportation Systems, ITSC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 October 2017 through 19 October 2017
ER -