Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors - Network and Parallel Computing Access content directly
Conference Papers Year : 2010

Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors

Abstract

DRAM row buffer conflicts can increase the memory access latency significantly for single-threaded applications. In a chip multiprocessor system, multiple applications competing for DRAM will suffer additional row buffer conflicts due to interthread interference. This paper presents a new hardware and software cooperative DRAM bank partitioning method that combines page coloring and XOR cache mapping to evaluate the benefit potential of reducing interthread interference. Using SPECfp2000 as our benchmarks, our simulation results show that our scheme can boost the performance of the most benchmark combinations tested, with the speedups of up to 13%, 14% and 8.06% observed for two cores (with 16 banks), two cores (with 32 banks) and four cores (with 32 banks).
Fichier principal
Vignette du fichier
NPC_pape-1569314947_in_EDAS.pdf (538.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01054975 , version 1 (11-08-2014)

Licence

Attribution

Identifiers

Cite

Wei Mi, Xiaobing Feng, Jingling Xue, Yaocang Jia. Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. pp.329-343, ⟨10.1007/978-3-642-15672-4_28⟩. ⟨hal-01054975⟩
67 View
211 Download

Altmetric

Share

Gmail Facebook X LinkedIn More