TY - GEN
T1 - Exploring memory controller configurations for many-core systems with 3D stacked DRAMs
AU - Ge, Fen
AU - Zhan, Jia
AU - Xie, Yuan
AU - Narayanan, Vijaykrishnan
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/4/13
Y1 - 2015/4/13
N2 - Network-on-Chip (NoC) provides a scalable approach to integrate more and more cores on chip, while limited capacity and bandwidth of DRAMs becomes the performance bottleneck. To break the memory wall, 3D integration of DRAMs and processors using Through Silicon Vias (TSVs) has emerged. Distributed memory controllers (MCs) are allocated on chip in order to utilize the abundant bandwidth of stacked DRAMs, but unavoidably incur significant hardware overhead. In this paper, we analyze the design of memory controllers in NoC-based many-core systems with stack-DRAMs. By analyzing the interaction between NoCs and MCs, the optimal number and placement of MCs are explored. Specifically, a Genetic algorithm (GA) based approach is proposed to find the optimal memory controller placement with different number of DRAM partitions. We evaluate memory controller configurations for various memory-intensive applications in terms of network latency and energy, as well as thermal distribution.
AB - Network-on-Chip (NoC) provides a scalable approach to integrate more and more cores on chip, while limited capacity and bandwidth of DRAMs becomes the performance bottleneck. To break the memory wall, 3D integration of DRAMs and processors using Through Silicon Vias (TSVs) has emerged. Distributed memory controllers (MCs) are allocated on chip in order to utilize the abundant bandwidth of stacked DRAMs, but unavoidably incur significant hardware overhead. In this paper, we analyze the design of memory controllers in NoC-based many-core systems with stack-DRAMs. By analyzing the interaction between NoCs and MCs, the optimal number and placement of MCs are explored. Specifically, a Genetic algorithm (GA) based approach is proposed to find the optimal memory controller placement with different number of DRAM partitions. We evaluate memory controller configurations for various memory-intensive applications in terms of network latency and energy, as well as thermal distribution.
UR - http://www.scopus.com/inward/record.url?scp=84944314768&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84944314768&partnerID=8YFLogxK
U2 - 10.1109/ISQED.2015.7085489
DO - 10.1109/ISQED.2015.7085489
M3 - Conference contribution
AN - SCOPUS:84944314768
T3 - Proceedings - International Symposium on Quality Electronic Design, ISQED
SP - 565
EP - 570
BT - Proceedings of the 16th International Symposium on Quality Electronic Design, ISQED 2015
PB - IEEE Computer Society
T2 - 16th International Symposium on Quality Electronic Design, ISQED 2015
Y2 - 2 March 2015 through 4 March 2015
ER -