TY - GEN
T1 - Resource-constrained spatial multi-tasking for embedded GPU
AU - Joo, Woohyun
AU - Shin, Dongkun
PY - 2014
Y1 - 2014
N2 - For recent smart devices, the embedded GPU is an indispensable unit and multi-task scheduling on the GPU becomes an important issue. To prevent the performance degradation on foreground GPU task by competing background GPU tasks, we propose a novel spatial multi-tasking which limits the number of available GPU cores for each task based on its priority. The proposed algorithm improved the performance of high priority task by up to 14% over the temporal budget based multi-tasking.
AB - For recent smart devices, the embedded GPU is an indispensable unit and multi-task scheduling on the GPU becomes an important issue. To prevent the performance degradation on foreground GPU task by competing background GPU tasks, we propose a novel spatial multi-tasking which limits the number of available GPU cores for each task based on its priority. The proposed algorithm improved the performance of high priority task by up to 14% over the temporal budget based multi-tasking.
UR - https://www.scopus.com/pages/publications/84898678993
U2 - 10.1109/ICCE.2014.6776031
DO - 10.1109/ICCE.2014.6776031
M3 - Conference contribution
AN - SCOPUS:84898678993
SN - 9781479912919
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
SP - 339
EP - 340
BT - 2014 IEEE International Conference on Consumer Electronics, ICCE 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Conference on Consumer Electronics, ICCE 2014
Y2 - 10 January 2014 through 13 January 2014
ER -