An architecture-level cache simulation framework supporting advanced PMA STT-MRAM - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2015

An architecture-level cache simulation framework supporting advanced PMA STT-MRAM


With integration density on-chip rocketing up, leakage power dominates the whole power budget of contemporary CMOS technology based memory, especially for SRAM based on-chip cache. To overcome the aggravating “power wall” issue, some emerging memory technologies such as STT-MRAM (Spin transfer torque magnetic RAM), PCRAM (Phase change RAM), and ReRAM(Resistive RAM) are proposed as promising candidates for next generation cache design. Although there are several existing simulation tools available for cache design, such as NVSim and CACTI, they either cannot support the most advanced PMA (Perpendicular magnetic anisotropy) STT-MRAM model or lack the ability for multi-banked large capacity cache simulation. In this paper, we propose an architecture level design framework for cache design from device level up to array structure level, which can support the most advanced PMA STT-MRAM technology. The simulation results are analyzed and compared with those produced by NVSim, which prove the correctness of our framework. The potential benefits of PMA STT-MRAM used as multi-banked L2 and L3 cache are also investigated in the paper. We believe that our framework will be helpful for computer architecture researchers to adopt the PMA STT-MRAM in on-chip cache design.
Fichier principal
Vignette du fichier
05.pdf (144.4 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

lirmm-01248586 , version 1 (27-03-2019)



Bi Wu, Yuanqing Cheng, Ying Wang, Aida Todri-Sanial, Guangyu Sun, et al.. An architecture-level cache simulation framework supporting advanced PMA STT-MRAM. NANOARCH: Nanoscale Architectures, Jun 2015, Boston, MA, United States. pp.7-12, ⟨10.1109/NANOARCH.2015.7180576⟩. ⟨lirmm-01248586⟩
219 View
264 Download



Gmail Facebook X LinkedIn More