Abstract — STT-RAM is an emerging NVRAM technology that promises high density, low energy and a comparable access speed to conventional SRAM. This paper proposes a hybrid L1 cache architecture that incorporates both SRAM and STT-RAM. The key novelty of the proposal is the exploition of the MESI cache coherence protocol to perform dynamic block reallocation between different cache partitions. Compared to the pure SRAM-based design, our hybrid scheme achieves 38 % of energy saving with a mere 0.8 % IPC degradation while extending the lifespan of STT-RAM partition at the same time. I
Modern architectures adopt large on-chip cache memory hierarchies with more than two levels. While t...
As the memory wall issue continues in the era of big data, researchers have been exploring emerging ...
“©2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
International audienceThis chapter presents a technique for reducing energy consumed by hybrid cache...
International audienceMemories are currently a real bottleneck to design high speed and energy-effic...
Emerging Non-Volatile Memories (NVM) such as Spin-Torque Transfer RAM (STT-RAM) and Resistive RAM (R...
Cache memories have been usually implemented with Static Random-Access Memory (SRAM) technology sin...
Caching techniques have been an efficient mechanism for mitigating the effects of the processor-memo...
(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for...
As technology scales down, energy consumption is becoming a big problem for traditional SRAM-based c...
Increasing demand for implementing highly-miniaturized battery-powered ultra-low-cost systems (e.g.,...
With continued technology scaling, process variations will be especially detrimental to six-transist...
SRAM based cache becomes a more critical source of power dissipation, particularly for large last le...
Abstract — This paper introduces our research status focusing on 3D-implemented microprocessors. 3D-...
This paper presents a novel cache architecture using 7T/14T hybrid SRAM, which can dynamically impro...
Modern architectures adopt large on-chip cache memory hierarchies with more than two levels. While t...
As the memory wall issue continues in the era of big data, researchers have been exploring emerging ...
“©2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
International audienceThis chapter presents a technique for reducing energy consumed by hybrid cache...
International audienceMemories are currently a real bottleneck to design high speed and energy-effic...
Emerging Non-Volatile Memories (NVM) such as Spin-Torque Transfer RAM (STT-RAM) and Resistive RAM (R...
Cache memories have been usually implemented with Static Random-Access Memory (SRAM) technology sin...
Caching techniques have been an efficient mechanism for mitigating the effects of the processor-memo...
(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for...
As technology scales down, energy consumption is becoming a big problem for traditional SRAM-based c...
Increasing demand for implementing highly-miniaturized battery-powered ultra-low-cost systems (e.g.,...
With continued technology scaling, process variations will be especially detrimental to six-transist...
SRAM based cache becomes a more critical source of power dissipation, particularly for large last le...
Abstract — This paper introduces our research status focusing on 3D-implemented microprocessors. 3D-...
This paper presents a novel cache architecture using 7T/14T hybrid SRAM, which can dynamically impro...
Modern architectures adopt large on-chip cache memory hierarchies with more than two levels. While t...
As the memory wall issue continues in the era of big data, researchers have been exploring emerging ...
“©2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...