ISSN 1000-1239 CN 11-1777/TP

Journal of Computer Research and Development ›› 2015, Vol. 52 ›› Issue (11): 2577-2588.doi: 10.7544/issn1000-1239.2015.20148178

Previous Articles     Next Articles

Decoupling Contention with VRB Mechanism for Multi-Threaded Applications

Gao Ke1,3, Fan Dongrui1, Liu Zhiyong1,2   

  1. 1(State Key Laboratory of Computer Architecture (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190);2(Beijing Key Laboratory of Mobile Computing and New Terminals (Institute of Computing Technology, Chinese Academy of Sciences ), Beijing 100190);3(University of Chinese Academy of Sciences, Beijing 100049)
  • Online:2015-11-01

Abstract: Currently, the processors improve system performance by increasing the number of cores and simultaneously running threads. However, increasing the number of processor cores and threads which share the memory system will decrease the memory row-buffer hit rate (RBHR), causing more memory power consumption and longer memory access latencies. We design and develop a fine-grained victim row-buffer (VRB) memory system to solve this problem. VRB mechanism provides an additional row-buffer (VRB) which temporarily stores the expelled data due to the row-buffer (RB) conflict for a possible access in the near future. This mechanism mitigates the multi-threaded interference phenomenon and increases the reuse ratio of row-buffer data in DRAM and avoids unnecessary accesses of the array of cells, thus some row activations, precharge operations and data transmission activities can be reduced. VRB can improve system performance and power consumption while incurring minor hardware complexity. Through full-system cycle-accurate simulations of many threads applications, we demonstrate that VRB mechanism achieves an up to 17.6% (8.7% on average) system-level throughput improvement, an up to 142.9% (51.4% on average) RBHR improvement, and saves an up to 17.6% (9.2% on average) power consumption compared with an 8-core Intel Xeon server.

Key words: DRAM architecture design, row buffer (RB), power consumption, multi-threaded, victim row-buffer (VRB) mechanism

CLC Number: