Architectural Support for NVRAM Persistence in GPUs

doi:10.1109/TPDS.2019.2960233

	Architectural Support for NVRAM Persistence in GPUs
	Chen, Sui 1; Liu, Lei 2; Zhang, Weihua 3; Peng, Lu 1
	2020-05-01
发表期刊	IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
ISSN	1045-9219
卷号	31 期号:5 页码:1107-1120
摘要	Non-volatile Random Access Memories (NVRAM) have emerged in recent years to bridge the performance gap between the main memory and external storage devices, such as Solid State Drives (SSD). In addition to higher storage density, NVRAM provides byte-addressability, higher bandwidth, near-DRAM latency, and easier access compared to block devices such as traditional SSDs. This enables new programming paradigms taking advantage of durability and larger memory footprint. With the range and size of GPU workloads expanding, NVRAM will present itself as a promising addition to GPU's memory hierarchy. To utilize the non-volatility of NVRAMs, programs should allow durable stores, maintaining consistency through a power loss event. This is usually done through a logging mechanism that works in tandem with a transaction execution layer which can consist of a transactional memory or a locking mechanism. Together, this results in a transaction processing system that preserves the ACID properties. GPUs are designed with high throughput in mind, leveraging high degrees of parallelism. Transactional memory proposals enable fine-grained transactions at the GPU thread-level. However, with lower write bandwidths compared to that of DRAMs, using NVRAM as-is may yield sub-optimal overall system performance when threads experience long latency. To address this problem, we propose using Helper Warps to move persistence out of the critical path of transaction execution, alleviating the impact of latencies. Our mechanism achieves a speedup of 4.4 and 1.5 under bandwidth limits of 1.6 GB/s and 12 GB/s and is projected to maintain speed advantage even when NVRAM bandwidth gets as high as hundreds of GB/s in certain cases. Due to the speedup, our proposed method also results in reduction in overall energy consumption.
关键词	NVRAM persistence GPUs helper warps
DOI	10.1109/TPDS.2019.2960233
收录类别	SCI
语种	英语
资助项目	US National Science Foundation (NSF)[CCF-1422408] ; US National Science Foundation (NSF)[CNS-1527318]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000526526100008
出版者	IEEE COMPUTER SOC
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/14189
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Sui
作者单位	1.Louisiana State Univ, Div Elect & Comp Engn, Baton Rouge, LA 70803 USA 2.Chinese Acad Sci, SKLCA, Inst Comp Technol, Beijing 100864, Peoples R China 3.Fudan Univ, Software Sch, Shanghai 201203, Peoples R China
推荐引用方式 GB/T 7714	Chen, Sui,Liu, Lei,Zhang, Weihua,et al. Architectural Support for NVRAM Persistence in GPUs[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,2020,31(5):1107-1120.
APA	Chen, Sui,Liu, Lei,Zhang, Weihua,&Peng, Lu.(2020).Architectural Support for NVRAM Persistence in GPUs.IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,31(5),1107-1120.
MLA	Chen, Sui,et al."Architectural Support for NVRAM Persistence in GPUs".IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 31.5(2020):1107-1120.