Sharif Digital Repository

Non-volatile memory (NVM) technologies are promising alternatives to traditional CMOS memory technologies. While NVMs were primarily studied to be used in the memory hierarchy, they can also provide benefits in reconfigurable systems such as Field-Programmable Gate Arrays (FPGAs). In this paper, we investigate the applicability of different NVM technologies for the configuration bits of FPGAs and propose a power-efficient reconfigurable architecture based on Phase Change Memory (PCM). Quantitative analysis for various FPGA architectures using different memory technologies shows the benefits of the proposed scheme  

With the recent development in Non-Volatile Memory (NVM) technologies, several studies have suggested using them as an alternative to SRAMs in on-chip caches. However, limited endurance of NVMs is a major challenge when employed in the caches. This paper proposes a data manipulation technique, so-called Wearout Informed Pattern Elimination (WIPE), to improve the endurance of NVM-based caches by reducing the activity of frequent data patterns. Simulation results show that WIPE improves the endurance by up to 93% with negligible overheads. © 2017 IEEE  

Emerging non-volatile memories (NVMs) are notable candidates for replacing traditional DRAMs. Although NVMs are scalable, dissipate lower power, and do not require refreshes, they face new challenges including shorter lifetime and security issues. Efforts toward securing the NVMs against probe attacks pose a serious downside in terms of lifetime. Cryptography algorithms increase the information density of data blocks and consequently handicap the existing lifetime enhancement solutions like Flip-N-Write. In this paper, based on the insight that compression can relax the constraints of lifetime-security trade-off, we propose CryptoComp, an architecture that, taking the advantage of block size... 

Non-Volatile Memory (NVM) technology is a promising solution to fulfill the ever-growing need for higher capacity in the main memory of modern systems. Despite having many great features, however, NVM's poor write performance remains a severe obstacle, preventing it from being used as a DRAM alternative in the main memory. Most of the prior work targeted optimizing writes at the main memory side and neglected the decisive role of upper-level cache management policies on reducing the number of writes. In this article, we propose a novel cache management policy that attempts to maximize write-coalescing in the on-chip SRAM last-level cache (LLC) for the sake of reducing the number of costly... 

Energy consumption and predictability are two important constraints in designing real-time embedded systems and one of the recently proposed solutions for the energy consumption problem is the use of non-volatile memories due to their lower leakage power consumption. Furthermore, because of their non-volatile nature, the use of these memories helps normally-off computing and energy harvesting systems. However, the write access latency of non-volatile memories is considerably more than that of SRAM which can decrease the performance and predictability of the system. We present a predictable non-volatile data memory for real-time embedded systems which improves both worst-case execution time... 

As technology size scales down, magnetic tunnel junctions (MTJs) as a promising technology are becoming more and more sensitive to process variation, especially in oxide barrier thickness. Process variation particularly affects the cell resistance and the critical switching current for the smaller dimensions. This article proposes an MTJ cell with one free and two pinned layers, which highly improves the process variation robustness. By employing the spin transfer torque (STT)-spin-Hall effect (SHE) switching method, our proposed MTJ cell improves the switching speed and lowers the switching power consumption. Per simulations, an MRAM cell built with the proposed MTJ cell offers up to 36%... 

Scratch Pad Memory (SPM) is an important part of most modern embedded processors. The use of embedded processors in safety-critical applications implies including fault tolerance in the design of SPM. This paper proposes a method, called FTSPM, which integrates a multi-priority mapping algorithm with a hybrid SPM structure. The proposed structure divides SPM into three parts: 1) a part is equipped with Non-Volatile Memory (NVM) which is immune against soft errors, 2) a part is equipped with Error-Correcting Code, and 3) a part is equipped with parity. The proposed mapping algorithm is responsible to distribute the program blocks among the above three parts with regards to their vulnerability... 

High static power consumption and insufficient scalability of the commonly used DRAM main memory technology appear to be tough challenges in upcoming years. Hence, adopting new technologies, i.e. non-volatile memories (NVMs), is a proper choice. NVMs tolerate a low number of write operations while having good scalability and low static power consumption. Due to the non-destructive nature of a read operation and the long latency of a write operation in NVMs, designers use read-before-write (RBW) mechanism to mask the unchanged bits during write operation in order to reduce bit flips. Based on this observation that some specific locations of blocks are responsible for the majority of bit... 

Emerging nonvolatile memory technologies, such as spin-transfer torque RAM or resistive RAM, can increase the capacity of the last-level cache (LLC) in a latency and power-efficient manner. These technologies endure 109 - 1012 writes per cell, making a nonvolatile cache (NV-cache) with a lifetime of dozens of years under ideal working conditions. However, nonuniformity in writes to different cache lines considerably reduces the NV-cache lifetime to a few months. Writes to cache lines can be made uniformly by wear-leveling. A suitable wear-leveling for NV-cache should not incur high storage and performance overheads. We propose a novel, simple, and effective wear-leveling technique with... 

Energy consumption is an important issue in designing embedded systems and the emerging Internet of Things (IoT). The use of non-volatile memories instead of SRAM in these systems improves their energy consumption since non-volatile memories consume much less leakage power and provide better capacity given the same die area as SRAM. However, this can impose significant performance overhead because the write operation latency of non-volatile memories is more than that of SRAM. In this paper we presented an NVM-based data memory architecture for embedded systems which improves the performance of the system at the cost of a slight energy consumption overhead. The architecture employs... 

Existing memory approximation techniques focus on employing approximations at an individual level of the memory hierarchy (e.g., cache, scratchpad, or main memory). However, to exploit the full potential of approximations, there is a need to manage different approximation knobs across the complete memory hierarchy. Towards this, we model a system including STT-RAM scratchpad and PCM main memory with different approximation knobs (e.g., read/write pulse magnitude/duration) in order to synergistically trade data accuracy for both STT-RAM access delay and PCM lifetime by means of an integer linear programming (ILP) problem at design-time. Furthermore, a runtime algorithm is proposed to... 

With the development of Non-Volatile Memory (NVM) technologies in recent years, several studies suggest using them as an alternative for SRAMs in on-chip caches. One of the main challenges in replacing SRAMs with NVMs is limited endurance of NVMs (i.e. the maximum allowed number of write operations in an NVM cell). The endurance of NVM caches is directly affected not only by workload behaviors, but also by process variations (PVs). Several studies characterized the endurance of NVM caches but they do not consider the simultaneous effects of the PVs and the workloads. In this paper, we propose a high-level framework to investigate the endurance of NVM caches affected by the per-cell endurance... 

Emerging Non-Volatile Memories (NVMs) have promising advantages (e.g., lower idle power, higher density, and non-volatility) over the existing predominant main memory technology, DRAM. Yet, NVMs also have disadvantages (e.g., longer latencies, higher active power, and limited endurance). System architects are therefore examining hybrid DRAM-NVM main memories to enable the advantages of NVMs while avoiding the disadvantages as much as possible. Unfortunately, the hybrid memory design space is very large and complex due to the existence of very different types of NVMs and their rapidly-changing characteristics. Therefore, optimization of performance and lifetime of hybrid memory based... 

Emerging non-volatile memories (NVMs) are known as promising alternatives to SRAMs in on-chip caches. However, their limited write endurance is a major challenge when NVMs are employed in these highly frequently written caches. Early wear-out of NVM cells makes the lifetime of the caches extremely insufficient for nowadays computational systems. Previous studies only addressed the lifetime of data part in the cache. This paper first demonstrates that the age bits field of the cache replacement algorithm is the most frequently written part of a cache block and its lifetime is shorter than that of data part by more than 27×. Second, it investigates the effect of age bits wear-out on the cache...