STD-TLB: A STT-RAM-based dynamically-configurable translation lookaside buffer for GPU architectures
Authors:
- 1 January 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21536961,p. 355-360
Abstract
Translation lookaside buffer (TLB) was recently introduced into modern graphics processing unit (GPU) architectures to support virtual memory addressing. Compared to CPUs, the performance of GPUs is more sensitive to the capacity of TLBs because of heavier memory accesses. However, large SRAM cell area greatly limits the implementable capacity of conventional SRAM-based TLBs. In this work, we propose using STT-RAM to construct TLBs in light of the unique memory access pattern in GPUs, i.e., infrequent data updates. STT-RAM TLB can replace its same-area SRAM counterpart with greater capacity, similar read performance and lower energy consumption. As an optimization of STT-RAM TLB, we further propose a STT-RAM-based dynamically-configurable TLB (STD-TLB) by leveraging differential sensing technique. STD-TLB can switch between high-capacity mode and high-performance mode on-the-fly based on real-time application needs. Our experiments show that compared to SRAM TLB, standard STT-RAM TLB improves the performance and energy delay product of GPU address translation by 32% and 75%, respectively, while STD-TLB achieves additional 15% and 13% improvements over standard STT-RAM TLB.Keywords
This publication has 16 references indexed in Scilit:
- ADAMS: Asymmetric differential STT-RAM cell structure for reliable and high-performance applications2013
- On-chip caches built on multilevel spin-transfer torque RAM cells and its optimizationsACM Journal on Emerging Technologies in Computing Systems, 2013
- Optimizing bandwidth and power of graphics memory with hybrid memory technologies and adaptive data migration2012
- Multi retention level STT-RAM cache designs with a dynamic refresh scheme2011
- Device-architecture co-optimization of STT-RAM based memory for low power embedded systems2011
- Shared last-level TLBs for chip multiprocessors2011
- Demystifying GPU microarchitecture through microbenchmarking2010
- Hybrid cache architecture with disparate memory technologies2009
- Analyzing CUDA workloads using a detailed GPU simulator2009
- A novel nonvolatile memory with spin torque transfer magnetization switching: spin-ram2006