
Recent developments in non-volatile memories (NVMs) have introduced them as an alternative for SRAMs in on-chip caches. Besides the promising features of NVMs, e.g., near-zero leakage power, immunity to radiation-induced particle strike, and higher density, a major drawback of NVM-based caches is their short lifetime due to limited write endurance. This brief first reveals that in L1 caches, the lifetime of data-cache is about 472 $\times$ shorter than that of instruction-cache (I-cache) due to extreme imbalance write stress between the two. Then, we propose a technique, so-called alternating cache allocation to conduct higher endurance (A-CACHE), to improve the lifetime of frequently written D-cache by exploiting rarely written I-cache. The key idea in A-CACHE is to alternate the locations of storing instructions and data between I-cache and D-cache. The evaluation results show that A-CACHE improves the lifetime of the cache by 83% with negligible overheads.
| 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). | 15 | |
| 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. | Top 10% | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 10% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
