Application specific non-volatile primary memory for embedded systems

Abstract

Memory subsystems have been considered as one of the most critical components in embedded systems and furthermore, displaying increasing complexity as application requirements diversify. Modern embedded systems are generally equipped with multiple heterogeneous memory devices to satisfy diverse requirements and constraints. NAND flash memory has been widely adopted for data storage because of its outstanding benefits on cost, power, capacity and nonvolatility. However, in NAND flash memory, the intrinsic costs for the read and write accesses are highly disproportionate in performance and access granularity. The consequent data management complexity and performance deterioration have precluded the adoption of NAND flash memory. In this paper, we introduce a highly effective non-volatile primary memory architecture which incorporates application specific information to develop a NAND flash based primary memory. The proposed architecture provides a unified non-volatile primary memory solution which relieves design complications caused by the growing complexity in memory subsystems. Our architecture aggressively minimizes the overhead and redundancy of the NAND based systems by exploiting efficient address space management and dynamic data migration based on accurate application behavioral analysis. We also propose a highly parallelized memory architecture through an active and dynamic data redistribution over the multiple flash memories based on run-time workload analysis. The experimental results show that our proposed architecture significantly enhances average memory access cycle time which is comparable to the standard DRAM access cycle time and also considerably prolongs the device life-cycle by autonomous wear-leveling and minimizing the program/erase operations.

A content-aware writing mechanism for reducing energy on non-volatile memory based embedded storage systems

“…Therefore, according to the length of each request, we design a behavior detector to detect the write requests into random and sequential requests. The length is a user defined threshold, which is determined by observing performance gains with different threshold values (e.g., 16,32,64) in the experiments. For example, if the length of a request is smaller than 32, then this request is treated as a random request; Otherwise, if the length of a request is greater than or equal to 32, then it is treated as a sequential request.…”

“…There is a large amount of research work on NVM based systems [10,16,25,28,36]. In general, these work can be categorized into three types, which are physic material [10,28,34], lifespan issues [4,12,20,26] and energy consumption saving [5,18,19,27,30,35].…”

“…A number of recent studies have revealed the potential energy savings in replacing DRAM with nonvolatile memory (NVM) technologies, such as phase change memory (PCM), magnetic RAM (MRAM) and ferroelectric RAM [11,16,17,24,36]. In addition, due to its non-volatile nature and rapid growth of capacity, NVM also holds great promise to be used as secondary storage for future computing systems [10,28].…”

Key-Study to Execute Code Using Demand Paging and NAND Flash at Smart Card Scale

“…In those conditions (Random worst case column of The researches on how to use NAND to execute code can be classified in four categories. First, we can distinguish pure hardware solutions since NAND is not a well-adapted device to do it [4,5,6,7]. On the opposite, some researchers [8,9,10,11,12,13,14,15] proposed software solutions using already available NAND, even if, here, software is often limited to firmware.…”

Cooperating Write Buffer Cache and Virtual Memory Management for Flash Memory Based Systems

“…INTRODUCTION Flash memory has been widely applied in mobile devices and embedded systems recently [4], [14], [15]. With characteristics such as small and lightweight form factor, shock resistance and low power consumption, flash memory is an ideal candidate in replacing traditional hard disk [1], [2], [3] as the secondary storage.…”