Abstract
In the deep sub-micron region, “spin-transfer torque RAM” (STT-RAM) suffers from “read-disturbance error” (RDE), whereby a read operation disturbs the stored data. Mitigation of RDE requires restore operations, which imposes latency and energy penalties. Hence, RDE presents a crucial threat to the scaling of STT-RAM. In this paper, we offer three techniques to reduce the restore overhead. First, we avoid the restore operations for those reads, where the block will get updated at a higher level cache in the near future. Second, we identify read-intensive blocks using a lightweight mechanism and then migrate these blocks to a small SRAM buffer. On a future read to these blocks, the restore operation is avoided. Third, for data blocks having zero value, a write operation is avoided, and only a flag is set. Based on this flag, both read and restore operations to this block are avoided. We combine these three techniques to design our final policy, named CORIDOR. Compared to a baseline policy, which performs restore operation after each read, CORIDOR achieves a 31.6% reduction in total energy and brings the relative CPI (cycle-per-instruction) to 0.64×. By contrast, an ideal RDE-free STT-RAM saves 42.7% energy and brings the relative CPI to 0.62×. Thus, our CORIDOR policy achieves nearly the same performance as an ideal RDE-free STT-RAM cache. Also, it reaches three-fourths of the energy-saving achieved by the ideal RDE-free cache. We also compare CORIDOR with four previous techniques and show that CORIDOR provides higher restore energy savings than these techniques.
- [1] . 2003. A single-V/sub t/low-leakage gated-ground cache for deep submicron. IEEE Journal of Solid-state circuits 38, 2 (2003), 319–328.Google Scholar
Cross Ref
- [2] . 2018. Reuse-distance-aware write-intensity prediction of dataless entries for energy-efficient hybrid caches. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 26, 10 (2018), 1881–1894. https://doi.org/10.1109/TVLSI.2018.2836156Google Scholar
Cross Ref
- [3] . 2019. Improving the lifetime of non-volatile cache by write restriction. IEEE Trans. Comput. 68, 9 (2019), 1297–1312.Google Scholar
Digital Library
- [4] . 2020. Improving the performance of hybrid caches using partitioned victim caching. ACM Transactions on Embedded Computing Systems (TECS) 20, 1 (2020), 1–27. Google Scholar
Digital Library
- [5] . 2013. Refrint: Intelligent refresh to minimize power in on-chip multiprocessor cache hierarchies. In 2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA). 400–411. https://doi.org/10.1109/HPCA.2013.6522336Google Scholar
Digital Library
- [6] . 2013. Write intensity prediction for energy-efficient non-volatile caches. In Low Power Electronics and Design (ISLPED), 2013 IEEE International Symposium on. IEEE, 223–228. Google Scholar
Digital Library
- [7] . 2019. REACT: Read/write error rate aware coding technique for emerging STT-MRAM caches. IEEE Transactions on Magnetics 55, 5 (2019), 1–8.Google Scholar
Cross Ref
- [8] . 2008. The PARSEC benchmark suite: Characterization and architectural implications(
PACT’08 ). Association for Computing Machinery, New York, NY, USA, 72–81. Google ScholarDigital Library
- [9] . 2011. The Gem5 simulator. SIGARCH Comput. Archit. News 39, 2 (
Aug. 2011), 1–7. Google ScholarDigital Library
- [10] . 2014. Read disturb fault detection in STT-MRAM. In 2014 International Test Conference. 1–7. https://doi.org/10.1109/TEST.2014.7035342Google Scholar
Cross Ref
- [11] . 2004. Value-conscious cache: Simple technique for reducing cache access power. In Proceedings of the Conference on Design, Automation and Test in Europe - Volume 1 (DATE’04). IEEE Computer Society, Washington, DC, USA, 10016–. Google Scholar
Digital Library
- [12] . 2013. Free-ECC: An efficient error protection for compressed last-level caches. In ICCD. 278–285.Google Scholar
- [13] . 2019. A system-level framework for analytical and empirical reliability exploration of STT-MRAM caches. IEEE Transactions on Reliability 69, 2 (2019), 594–610.Google Scholar
Cross Ref
- [14] . 2019. Enhancing reliability of STT-MRAM caches by eliminating read disturbance accumulation. In 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 854–859.Google Scholar
Cross Ref
- [15] . 2021. 3RSeT: Read disturbance rate reduction in STT-MRAM caches by selective tag comparison. IEEE Trans. Comput. (2021).Google Scholar
Cross Ref
- [16] . 2016. Investigating the effects of process variations and system workloads on reliability of STT-RAM caches. In 12th European Dependable Computing Conference (EDCC). 120–129.Google Scholar
Cross Ref
- [17] . 2005. A robust main-memory compression scheme. In Proceedings of the 32nd Annual International Symposium on Computer Architecture (ISCA’05). IEEE Computer Society, Washington, DC, USA, 74–85. https://doi.org/10.1109/ISCA.2005.6 Google Scholar
Digital Library
- [18] 2009. Zero-content augmented caches. In Proceedings of the 23rd International Conference on Supercomputing (Yorktown Heights, NY, USA) (
ICS’09 ). ACM, New York, NY, USA, 46–55. Google ScholarDigital Library
- [19] 2009. Zero-Value caches: Cancelling loads that return zero. In 2009 18th International Conference on Parallel Architectures and Compilation Techniques. 237–245. https://doi.org/10.1109/PACT.2009.29 Google Scholar
Digital Library
- [20] . 2013. Failure mitigation techniques for 1T-1MTJ spin-transfer torque MRAM bit-cells. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 22, 2 (2013), 384–395. Google Scholar
Digital Library
- [21] . 2019. Compiler-directed and architecture-independent mitigation of read disturbance errors in STT-RAM. In Design, Automation & Test in Europe Conference & Exhibition (DATE). 222–227.Google Scholar
Cross Ref
- [22] . 2013. A novel STT-MRAM cell with disturbance-free read operation. IEEE Transactions on Circuits and Systems I: Regular Papers 60, 6 (2013), 1534–1547.Google Scholar
Cross Ref
- [23] . 2016. Improving read performance of STT-MRAM based main memories through smash read and flexible read. ASP-DAC (2016).Google Scholar
- [24] . 2014. Readability challenges in deeply scaled STT-MRAM. In NVMTS. 1–4.Google Scholar
- [25] . 2014. Variation-tolerant and disturbance-free sensing circuit for deep nanometer STT-MRAM. IEEE Transactions on Nanotechnology 13, 6 (2014), 1088–1092.Google Scholar
Cross Ref
- [26] . 2017. Towards refresh-optimized EDRAM-based caches with a selective fine-grain round-robin refresh scheme. Microprocessors and Microsystems 49 (2017), 95–104. https://doi.org/10.1016/j.micpro.2016.11.007 Google Scholar
Digital Library
- [27] . 2019. Dynamic reconfiguration of embedded-DRAM caches employing zero data detection based refresh optimisation. Journal of Systems Architecture 100 (2019), 101648.Google Scholar
Cross Ref
- [28] . 2017. A survey of soft-error mitigation techniques for non-volatile memories. Computers 6, 8 (2017).Google Scholar
- [29] . 2017. Addressing read-disturbance issue in STT-RAM by data compression and selective duplication. IEEE Computer Architecture Letters 16, 2 (
Jul-Dec 2017), 94–98.Google ScholarCross Ref
- [30] . 2014. A survey of architectural approaches for managing embedded DRAM and non-volatile on-chip caches. IEEE TPDS (2014). Google Scholar
Digital Library
- [31] . 2017. DESTINY: A comprehensive tool with 3D and multi-level cell memory modeling capability. Journal of Low Power Electronics and Applications 7, 3 (2017), 23.Google Scholar
Cross Ref
- [32] . 2012. Base-delta-immediate compression: Practical data compression for on-chip caches. In PACT. Google Scholar
Digital Library
- [33] . 2020. SALE: Smartly allocating low-cost many-bit ECC for mitigating read and write errors in STT-RAM caches. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 28, 6 (2020), 1357–1370.Google Scholar
Cross Ref
- [34] . 2012. A dual-mode architecture for fast-switching STT-RAM. In ISLPED. 45–50. Google Scholar
Digital Library
- [35] . 2010. Highly-scalable disruptive reading scheme for Gb-scale SPRAM and beyond. In IEEE IMW. 1–2.Google Scholar
- [36] . 2015. Selective restore: An energy efficient read disturbance mitigation scheme for future STT-MRAM. In DAC. Google Scholar
Digital Library
- [37] . 2009. Power and performance of read-write aware hybrid caches with non-volatile memories. In Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 737–742. Google Scholar
Digital Library
- [38] . 2002. Frequent value locality and its applications. ACM Trans. Embed. Comput. Syst. 1, 1 (
Nov. 2002), 79–105. https://doi.org/10.1145/581888.581894 Google ScholarDigital Library
- [39] . 2016. RED-SHIELD: Shielding read disturbance for STT-RAM based register files on GPUs. In 2016 International Great Lakes Symposium on VLSI (GLSVLSI). 389–392. Google Scholar
Digital Library
- [40] . 2009. Characterizing and mitigating the impact of process variations on phase change based memory systems. In MICRO. 2–13.Google Scholar
Index Terms
CORIDOR: Using COherence and TempoRal LocalIty to Mitigate Read Disurbance ErrOR in STT-RAM Caches
Recommendations
Endurance enhancement of write-optimized STT-RAM caches
MEMSYS '19: Proceedings of the International Symposium on Memory SystemsLow density and high leakage power of SRAM are the major setbacks for its scalability. Non-volatile memory (NVM) like spin-transfer torque random access memory (STT-RAM) is a suitable replacement for SRAM at the last level cache (LLC). NVM offers high ...
Low-energy volatile STT-RAM cache design using cache-coherence-enabled adaptive refresh
Spin-Torque Transfer RAM (STT-RAM) is a promising candidate for SRAM replacement because of its excellent features, such as fast read access, high density, low leakage power, and CMOS technology compatibility. However, wide adoption of STT-RAM as cache ...
Cache coherence enabled adaptive refresh for volatile STT-RAM
DATE '13: Proceedings of the Conference on Design, Automation and Test in EuropeSpin-Transfer Torque RAM (STT-RAM) is extensively studied in recent years. Recent work proposed to improve the write performance of STT-RAM through relaxing the retention time of STT-RAM cell, magnetic tunnel junction (MTJ). Unfortunately, frequent ...






Comments