You are here

Energy-Aware Data Movement In Non-Volatile Memory Hierarchies

Download pdf | Full Screen View

Date Issued:
2017
Abstract/Description:
While technology scaling enables increased density for memory cells, the intrinsic high leakagepower of conventional CMOS technology and the demand for reduced energy consumption inspiresthe use of emerging technology alternatives such as eDRAM and Non-Volatile Memory (NVM) including STT-MRAM, PCM, and RRAM. The utilization of emerging technology in Last Level Cache (LLC) designs which occupies a signi?cant fraction of total die area in Chip Multi Processors (CMPs) introduces new dimensions of vulnerability, energy consumption, and performance delivery. To be speci?c, a part of this research focuses on eDRAM Bit Upset Vulnerability Factor (BUVF) to assess vulnerable portion of the eDRAM refresh cycle where the critical charge varies depending on the write voltage, storage and bit-line capacitance. This dissertation broaden the study on vulnerability assessment of LLC through investigating the impact of Process Variations (PV) on narrow resistive sensing margins in high-density NVM arrays, including on-chip cache and primary memory. Large-latency and power-hungry Sense Ampli?ers (SAs) have been adapted to combat PV in the past. Herein, a novel approach is proposed to leverage the PV in NVM arrays using Self-Organized Sub-bank (SOS) design. SOS engages the preferred SA alternative based on the intrinsic as-built behavior of the resistive sensing timing margin to reduce the latency and power consumption while maintaining acceptable access time.On the other hand, this dissertation investigates a novel technique to prioritize the service to 1)Extensive Read Reused Accessed blocks of the LLC that are silently dropped from higher levelsof cache, and 2) the portion of the working set that may exhibit distant re-reference interval in L2. In particular, we develop a lightweight Multi-level Access History Pro?ler to ef?ciently identifyERRA blocks through aggregating the LLC block addresses tagged with identical Most Signi?cantBits into a single entry. Experimental results indicate that the proposed technique can reduce theL2 read miss ratio by 51.7% on average across PARSEC and SPEC2006 workloads.In addition, this dissertation will broaden and apply advancements in theories of subspace recoveryto pioneer computationally-aware in-situ operand reconstruction via the novel Logic In Intercon-nect (LI2) scheme. LI2 will be developed, validated, and re?ned both theoretically and experimentally to realize a radically different approach to post-Moore's Law computing by leveraginglow-rank matrices features offering data reconstruction instead of fetching data from main memory to reduce energy/latency cost per data movement. We propose LI2 enhancement to attain highperformance delivery in the post-Moore's Law era through equipping the contemporary micro-architecture design with a customized memory controller which orchestrates the memory requestfor fetching low-rank matrices to customized Fine Grain Recon?gurable Accelerator (FGRA) forreconstruction while the other memory requests are serviced as before. The goal of LI2 is to conquer the high latency/energy required to traverse main memory arrays in the case of LLC miss, by using in-situ construction of the requested data dealing with low-rank matrices. Thus, LI2 exchanges a high volume of data transfers with a novel lightweight reconstruction method under speci?c conditions using a cross-layer hardware/algorithm approach.
Title: Energy-Aware Data Movement In Non-Volatile Memory Hierarchies.
114 views
89 downloads
Name(s): Khoshavi Najafabadi, Navid, Author
DeMara, Ronald, Committee Chair
Yuan, Jiann-Shiun, Committee Member
Song, Zixia, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2017
Publisher: University of Central Florida
Language(s): English
Abstract/Description: While technology scaling enables increased density for memory cells, the intrinsic high leakagepower of conventional CMOS technology and the demand for reduced energy consumption inspiresthe use of emerging technology alternatives such as eDRAM and Non-Volatile Memory (NVM) including STT-MRAM, PCM, and RRAM. The utilization of emerging technology in Last Level Cache (LLC) designs which occupies a signi?cant fraction of total die area in Chip Multi Processors (CMPs) introduces new dimensions of vulnerability, energy consumption, and performance delivery. To be speci?c, a part of this research focuses on eDRAM Bit Upset Vulnerability Factor (BUVF) to assess vulnerable portion of the eDRAM refresh cycle where the critical charge varies depending on the write voltage, storage and bit-line capacitance. This dissertation broaden the study on vulnerability assessment of LLC through investigating the impact of Process Variations (PV) on narrow resistive sensing margins in high-density NVM arrays, including on-chip cache and primary memory. Large-latency and power-hungry Sense Ampli?ers (SAs) have been adapted to combat PV in the past. Herein, a novel approach is proposed to leverage the PV in NVM arrays using Self-Organized Sub-bank (SOS) design. SOS engages the preferred SA alternative based on the intrinsic as-built behavior of the resistive sensing timing margin to reduce the latency and power consumption while maintaining acceptable access time.On the other hand, this dissertation investigates a novel technique to prioritize the service to 1)Extensive Read Reused Accessed blocks of the LLC that are silently dropped from higher levelsof cache, and 2) the portion of the working set that may exhibit distant re-reference interval in L2. In particular, we develop a lightweight Multi-level Access History Pro?ler to ef?ciently identifyERRA blocks through aggregating the LLC block addresses tagged with identical Most Signi?cantBits into a single entry. Experimental results indicate that the proposed technique can reduce theL2 read miss ratio by 51.7% on average across PARSEC and SPEC2006 workloads.In addition, this dissertation will broaden and apply advancements in theories of subspace recoveryto pioneer computationally-aware in-situ operand reconstruction via the novel Logic In Intercon-nect (LI2) scheme. LI2 will be developed, validated, and re?ned both theoretically and experimentally to realize a radically different approach to post-Moore's Law computing by leveraginglow-rank matrices features offering data reconstruction instead of fetching data from main memory to reduce energy/latency cost per data movement. We propose LI2 enhancement to attain highperformance delivery in the post-Moore's Law era through equipping the contemporary micro-architecture design with a customized memory controller which orchestrates the memory requestfor fetching low-rank matrices to customized Fine Grain Recon?gurable Accelerator (FGRA) forreconstruction while the other memory requests are serviced as before. The goal of LI2 is to conquer the high latency/energy required to traverse main memory arrays in the case of LLC miss, by using in-situ construction of the requested data dealing with low-rank matrices. Thus, LI2 exchanges a high volume of data transfers with a novel lightweight reconstruction method under speci?c conditions using a cross-layer hardware/algorithm approach.
Identifier: CFE0006754 (IID), ucf:51859 (fedora)
Note(s): 2017-08-01
Ph.D.
Engineering and Computer Science, Electrical Engineering and Computer Engineering
Doctoral
This record was generated from author submitted information.
Subject(s): memory hierarchy -- cache migration policy -- data movement
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0006754
Restrictions on Access: campus 2018-08-15
Host Institution: UCF

In Collections