
Abstract STT–RAM is considered as a promising alternative to SRAM due to its low static power (non-volatility) and high density. However, write operation of STT–RAM is inefficient in terms of energy and speed compared to SRAM and thus various device-/circuit-/architecture-level solutions have been proposed to tackle this inefficiency. One of the proposed solutions is redesigning STT–RAM cell for better write characteristics at the cost of shortened retention time (volatile STT–RAM). Because the retention failure of STT–RAM has a stochastic property, an extra overhead of periodic scrubbing with error correcting code (ECC) is required to tolerate the failure. The more frequent scrubbing and stronger ECC are used, the shorter retention time is allowed. With an analysis based on analytic STT–RAM model, we have conducted extensive experiments on various volatile STT–RAM cache design parameters including scrubbing period, ECC strength, and target failure rate. The experimental results show the impact of the parameter variations on last-level cache energy and performance and provide a guideline for designing a volatile STT–RAM with ECC and scrubbing.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 6 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
