Architecting SOT-RAM Based GPU Register File
Architecting SOT-RAM Based GPU Register File
复制标题
DOI：
10.1109/isvlsi.2017.17
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Sparsh Mittal;R. Bishnoi;Fabian Oboril;Haonan Wang;M. Tahoori;Adwait Jog;J. Vetter
中科院分区：
文献类型：
--
作者：
Sparsh Mittal;R. Bishnoi;Fabian Oboril;Haonan Wang;M. Tahoori;Adwait Jog;J. Vetter
随着GPU寄存器文件（RF）大小的增加，其功耗也增加。由于RF存在于高速缓存层级中的最高级别，因此将其设计为具有高写入延迟/能量的存储器（例如，自旋转移力矩RAM）可导致大的能量损失。在本文中，我们提出了一个自旋轨道力矩RAM（SOT-RAM）的RF设计，提供了更高的能量效率比SRAM和STT-RAM RF，同时保持性能相同的SRAM RF。为了进一步提高基于SOT-RAM的RF的能量效率，我们建议避免对RF的冗余位写入。与SRAM RF相比，SOT-RAM RF节省了18.6%的能量，并且通过使用我们的技术来避免冗余写入，可以将能量节省增加到44.3%，而不会影响性能。
With increase in GPU register file (RF) size, its power consumption has also increased. Since RF exists at the highest level in cache hierarchy, designing it with memories with high write latency/energy (e.g., spin transfer torque RAM) can lead to large energy loss. In this paper, we present an spin orbit torque RAM (SOT-RAM) based RF design which provides higher energy efficiency than SRAM and STT-RAM RFs while maintaining performance same as that of SRAM RF. To further improve energy efficiency of SOT-RAM based RF, we propose avoiding redundant bit-writes to RF. Compared to SRAM RF, SOT-RAM RF saves 18.6% energy and by using our technique for avoiding redundant writes, the energy saving can be increased to 44.3%, without harming performance.