Non-volatile memory (NVM) has become a staple in the everyday life of consumers. NVM manifests inside cell phones, laptops, and most recently, wearable tech such as smart watches. NAND Flash has been an excellent solution to conditions requiring fast, compact NVM. Current technology nodes are nearing the physical limits of scaling, preventing flash from improving. To combat the limitations of flash and to appease consumer demand for progressively faster and denser NVM, new technologies are needed. One possible candidate for the replacement of NAND Flash is programmable metallization cells (PMC). PMC are a type of resistive memory, meaning that they do not rely on charge storage to maintain a logic state. Depending on their application, it is possible that devices containing NVM will be exposed to harsh radiation environments. As part of the process for developing a novel memory technology, it is important to characterize the effects irradiation has on the functionality of the devices.

This thesis characterizes the effects that ionizing γ-ray irradiation has on the retention of the programmed resistive state of a PMC. The PMC devices tested used Ge30Se70 doped with Ag as the solid electrolyte layer and were fabricated by the thesis author in a Class 100 clean room. Individual device tiles were wire bonded into ceramic packages and tested in a biased and floating contact scenario.

The first scenario presented shows that PMC devices are capable of retaining their programmed state up to the maximum exposed total ionizing dose (TID) of 3.1 Mrad(Si). In this first scenario, the contacts of the PMC devices were left floating during exposure. The second scenario tested shows that the PMC devices are capable of retaining their state until the maximum TID of 10.1 Mrad(Si) was reached. The contacts in the second scenario were biased, with a 50 mV read voltage applied to the anode contact. Analysis of the results show that Ge30Se70 PMC are ionizing radiation tolerant and can retain a programmed state to a higher TID than NAND Flash memory.

There is an ever growing need for larger memories which are reliable and fast. New technologies to implement non-volatile memories which are large, fast, compact and cost-efficient are being studied extensively. One of the most promising technologies being developed is the resistive RAM (ReRAM). In ReRAM the resistance of the device varies with the voltage applied across it. Programmable metallization cells (PMC) is one of the devices belonging to this category of non-volatile memories.

In order to advance the development of these devices, there is a need to develop simulation models which replicate the behavior of these devices in circuits. In this thesis, a verilogA model for the PMC has been developed. The behavior of the model has been tested using DC and transient simulations. Experimental data obtained from testing PMC devices fabricated at Arizona State University have been compared to results obtained from simulation.

A basic memory cell known as the 1T 1R cell built using the PMC has also been simulated and verified. These memory cells have the potential to be building blocks of large scale memories. I believe that the verilogA model developed in this thesis will prove to be a powerful tool for researchers and circuit developers looking to develop non-volatile memories using alternative technologies.

Nonvolatile memory (NVM) technologies have been an integral part of electronic systems for the past 30 years. The ideal non-volatile memory have minimal physical size, energy usage, and cost while having maximal speed, capacity, retention time, and radiation hardness. A promising candidate for next-generation memory is ion-conducting bridging RAM which is referred to as programmable metallization cell (PMC), conductive bridge RAM (CBRAM), or electrochemical metallization memory (ECM), which is likely to surpass flash memory in all the ideal memory characteristics. A comprehensive physics-based model is needed to completely understand PMC operation and assist in design optimization.

To advance the PMC modeling effort, this thesis presents a precise physical model parameterizing materials associated with both ion-rich and ion-poor layers of the PMC's solid electrolyte, so that captures the static electrical behavior of the PMC in both its low-resistance on-state (LRS) and high resistance off-state (HRS). The experimental data is measured from a chalcogenide glass PMC designed and manufactured at ASU. The static on- and off-state resistance of a PMC device composed of a layered (Ag-rich/Ag-poor) Ge30Se70 ChG film is characterized and modeled using three dimensional simulation code written in Silvaco Atlas finite element analysis software. Calibrating the model to experimental data enables the extraction of device parameters such as material bandgaps, workfunctions, density of states, carrier mobilities, dielectric constants, and affinities.

The sensitivity of our modeled PMC to the variation of its prominent achieved material parameters is examined on the HRS and LRS impedance behavior.

The obtained accurate set of material parameters for both Ag-rich and Ag-poor ChG systems and process variation verification on electrical characteristics enables greater fidelity in PMC device simulation, which significantly enhances our ability to understand the underlying physics of ChG-based resistive switching memory.

As the number of cores per chip increases, maintaining cache coherence becomes prohibitive for both power and performance. Non Coherent Cache (NCC) architectures do away with hardware-based cache coherence, but they become difficult to program. Some existing architectures provide a middle ground by providing some shared memory in the hardware. Specifically, the 48-core Intel Single-chip Cloud Computer (SCC) provides some off-chip (DRAM) shared memory some on-chip (SRAM) shared memory. We call such architectures Hybrid Shared Memory, or HSM, manycore architectures. However, how to efficiently execute multi-threaded programs on HSM architectures is an open problem. To be able to execute a multi-threaded program correctly on HSM architectures, the compiler must: i) identify all the shared data and map it to the shared memory, and ii) map the frequently accessed shared data to the on-chip shared memory. This work presents a source-to-source translator written using CETUS that identifies a conservative superset of all the shared data in a multi-threaded application and maps it to the shared memory such that it enables execution on HSM architectures.

This work focuses on the existence of multiple resistance states in a type of emerging non-volatile resistive memory device known commonly as Programmable Metallization Cell (PMC) or Conductive Bridge Random Access Memory (CBRAM), which can be important for applications such as multi-bit memory as well as non-volatile logic and neuromorphic computing. First, experimental data from small signal, quasi-static and pulsed mode electrical characterization of such devices are presented which clearly demonstrate the inherent multi-level resistance programmability property in CBRAM devices. A physics based analytical CBRAM compact model is then presented which simulates the ion-transport dynamics and filamentary growth mechanism that causes resistance change in such devices. Simulation results from the model are fitted to experimental dynamic resistance switching characteristics. The model designed using Verilog-a language is computation-efficient and can be integrated with industry standard circuit simulation tools for design and analysis of hybrid circuits involving both CMOS and CBRAM devices. Three main circuit applications for CBRAM devices are explored in this work. Firstly, the susceptibility of CBRAM memory arrays to single event induced upsets is analyzed via compact model simulation and experimental heavy ion testing data that show possibility of both high resistance to low resistance and low resistance to high resistance transitions due to ion strikes. Next, a non-volatile sense amplifier based flip-flop architecture is proposed which can help make leakage power consumption negligible by allowing complete shutdown of power supply while retaining its output data in CBRAM devices. Reliability and energy consumption of the flip-flop circuit for different CBRAM low resistance levels and supply voltage values are analyzed and compared to CMOS designs. Possible extension of this architecture for threshold logic function computation using the CBRAM devices as re-configurable resistive weights is also discussed. Lastly, Spike timing dependent plasticity (STDP) based gradual resistance change behavior in CBRAM device fabricated in back-end-of-line on a CMOS die containing integrate and fire CMOS neuron circuits is demonstrated for the first time which indicates the feasibility of using CBRAM devices as electronic synapses in spiking neural network hardware implementations for non-Boolean neuromorphic computing.

Programmable metallization cell (PMC) technology employs the mechanisms of metal ion transport in solid electrolytes (SE) and electrochemical redox reactions in order to form metallic electrodeposits. When a positive bias is applied to an anode opposite to a cathode, atoms at the anode are oxidized to ions and dissolve into the SE. Under the influence of the electric field, the ions move to the cathode and become reduced to form the electrodeposits. These electrodeposits are filamentary in nature and persistent, and since they are metallic can alter the physical characteristics of the material on which they are formed. PMCs can be used as next generation memories, radio frequency (RF) switches and physical unclonable functions (PUFs).

The morphology of the filaments is impacted by the biasing conditions. Under a relatively high applied electric field, they form as dendritic elements with a low fractal dimension (FD), whereas a low electric field leads to high FD features. Ion depletion effects in the SE due to low ion diffusivity/mobility also influences the morphology by limiting the ion supply into the growing electrodeposit.

Ion transport in SE is due to hopping transitions driven by drift and diffusion force. A physical model of ion hopping with Brownian motion has been proposed, in which the ion transitions are random when time window is larger than characteristic time. The random growth process of filaments in PMC adds entropy to the electrodeposition, which leads to random features in the dendritic patterns. Such patterns has extremely high information capacity due to the fractal nature of the electrodeposits.

In this project, lateral-growth PMCs were fabricated, whose LRS resistance is less than 10Ω, which can be used as RF switches. Also, an array of radial-growth PMCs was fabricated, on which multiple dendrites, all with different shapes, could be grown simultaneously. Those patterns can be used as secure keys in PUFs and authentication can be performed by optical scanning.

A kinetic Monte Carlo (KMC) model is developed to simulate the ion transportation in SE under electric field. The simulation results matched experimental data well that validated the ion hopping model.

As persistent non-volatile memory solutions become integrated in the computing ecosystem and landscape, traditional commodity file systems architected and developed for traditional block I/O based memory solutions must be reevaluated. A majority of commodity file systems have been architected and designed with the goal of managing data on non-volatile storage devices such as hard disk drives (HDDs) and solid state drives (SSDs). HDDs and SSDs are attached to a computing system via a controller or I/O hub, often referred to as the southbridge. The point of HDD and SSD attachment creates multiple levels of translation for any data managed by the CPU that must be stored in non-volatile memory (NVM) on an HDD or SSD. Storage Class Memory (SCM) devices provide the ability to store data at the CPU and DRAM level of a computing system. A novel set of modifications to the ext2 and ext4 commodity file systems to address the needs of SCM will be presented and discussed. An in-depth analysis of many existing file systems, from multiple sources, will be presented along with an analysis to identify key modifications and extensions that would be necessary to execute file system on SCM devices. From this analysis, modifications and extensions have been applied to the FAT commodity file system for key functional tests that will be presented to demonstrate the operation and execution of the file system extensions.

The availability of a wide range of general purpose as well as accelerator cores on

modern smartphones means that a significant number of applications can be executed

on a smartphone simultaneously, resulting in an ever increasing demand on the memory

subsystem. While the increased computation capability is intended for improving

user experience, memory requests from each concurrent application exhibit unique

memory access patterns as well as specific timing constraints. If not considered, this

could lead to significant memory contention and result in lowered user experience.

This work first analyzes the impact of memory degradation caused by the interference

at the memory system for a broad range of commonly-used smartphone applications.

The real system characterization results show that smartphone applications,

such as web browsing and media playback, suffer significant performance degradation.

This is caused by shared resource contention at the application processor’s last-level

cache, the communication fabric, and the main memory.

Based on the detailed characterization results, rest of this thesis focuses on the

design of an effective memory interference mitigation technique. Since web browsing,

being one of the most commonly-used smartphone applications and represents many

html-based smartphone applications, my thesis focuses on meeting the performance

requirement of a web browser on a smartphone in the presence of background processes

and co-scheduled applications. My thesis proposes a light-weight user space frequency

governor to mitigate the degradation caused by interfering applications, by predicting

the performance and power consumption of web browsing. The governor selects an

optimal energy-efficient frequency setting periodically by using the statically-trained

performance and power models with dynamically-varying architecture and system

conditions, such as the memory access intensity of background processes and/or coscheduled applications, and temperature of cores. The governor has been extensively evaluated on a Nexus 5 smartphone over a diverse range of mobile workloads. By

operating at the most energy-efficient frequency setting in the presence of interference,

energy efficiency is improved by as much as 35% and with an average of 18% compared

to the existing interactive governor, while maintaining the satisfactory performance

of web page loading under 3 seconds.

Cyber-physical systems and hard real-time systems have strict timing constraints that specify deadlines until which tasks must finish their execution. Missing a deadline can cause unexpected outcome or endanger human lives in safety-critical applications, such as automotive or aeronautical systems. It is, therefore, of utmost importance to obtain and optimize a safe upper bound of each task’s execution time or the worst-case execution time (WCET), to guarantee the absence of any missed deadline. Unfortunately, conventional microarchitectural components, such as caches and branch predictors, are only optimized for average-case performance and often make WCET analysis complicated and pessimistic. Caches especially have a large impact on the worst-case performance due to expensive off- chip memory accesses involved in cache miss handling. In this regard, software-controlled scratchpad memories (SPMs) have become a promising alternative to caches. An SPM is a raw SRAM, controlled only by executing data movement instructions explicitly at runtime, and such explicit control facilitates static analyses to obtain safe and tight upper bounds of WCETs. SPM management techniques, used in compilers targeting an SPM-based processor, determine how to use a given SPM space by deciding where to insert data movement instructions and what operations to perform at those program locations. This dissertation presents several management techniques for program code and stack data, which aim to optimize the WCETs of a given program. The proposed code management techniques include optimal allocation algorithms and a polynomial-time heuristic for allocating functions to the SPM space, with or without the use of abstraction of SPM regions, and a heuristic for splitting functions into smaller partitions. The proposed stack data management technique, on the other hand, finds an optimal set of program locations to evict and restore stack frames to avoid stack overflows, when the call stack resides in a size-limited SPM. In the evaluation, the WCETs of various benchmarks including real-world automotive applications are statically calculated for SPMs and caches in several different memory configurations.

Software Managed Manycore (SMM) architectures - in which each core has only a scratch pad memory (instead of caches), - are a promising solution for scaling memory hierarchy to hundreds of cores. However, in these architectures, the code and data of the tasks mapped to the cores must be explicitly managed in the software by the compiler. State-of-the-art compiler techniques for SMM architectures require inter-procedural information and analysis. A call graph of the program does not have enough information, and Global CFG, i.e., combining all the control flow graphs of the program has too much information, and becomes too big. As a result, most new techniques have informally defined and used GCCFG (Global Call Control Flow Graph) - a whole program representation which captures the control-flow as well as function call information in a succinct way - to perform inter-procedural analysis. However, how to construct it has not been shown yet. We find that for several simple call and control flow graphs, constructing GCCFG is relatively straightforward, but there are several cases in common applications where unique graph transformation is needed in order to formally and correctly construct the GCCFG. This paper fills this gap, and develops graph transformations to allow the construction of GCCFG in (almost) all cases. Our experiments show that by using succinct representation (GCCFG) rather than elaborate representation (GlobalCFG), the compilation time of state-of-the-art code management technique [4] can be improved by an average of 5X, and that of stack management [20] can be improved by an average of 4X.