SMO: An Integrated Approach to Intra-array and Inter-array Storage Optimization

The polyhedral model provides an expressive intermediate representation that is convenient for the analysis and subsequent transformation of affine loop nests. Several heuristics exist for achieving complex program transformations in this model. However, there is also considerable scope to utilize this model to tackle the problem of automatic memory footprint optimization. In this paper, we present a new automatic storage optimization technique which can be used to achieve both intra-array as well as inter-array storage reuse with a pre-determined schedule for the computation. Our approach works by finding statement-wise storage partitioning hyper planes that partition a unified global array space so that values with overlapping live ranges are not mapped to the same partition. Our heuristic is driven by a fourfold objective function which not only minimizes the dimensionality and storage requirements of arrays required for each high-level statement, but also maximizes inter statement storage reuse. The storage mappings obtained using our heuristic can be asymptotically better than those obtained by any existing technique. We implement our technique and demonstrate its practical impact by evaluating its effectiveness on several benchmarks chosen from the domains of image processing, stencil computations, and high-performance computing.

Direct Computation of 3D Shape Invariants and the Focus of Expansion

Structure from motion often refers to the computation of 3D structure from a matched sequence of images. However, a depth map of a surface is difficult to compute and may not be a good representation for storage and recognition. Given matched images, I will first show that the sign of the normal curvature in a given direction at a given point in the image can be computed from a simple difference of slopes of line-segments in one image. Using this result, local surface patches can be classified as convex, concave, parabolic (cylindrical), hyperbolic (saddle point) or planar. At the same time the translational component of the optical flow is obtained, from which the focus of expansion can be computed.

Classical computation with quantum systems

As semiconductor electronic devices scale to the nanometer range and quantum structures (molecules, fullerenes, quantum dots, nanotubes) are investigated for use in information processing and storage, it, becomes useful to explore the limits imposed by quantum mechanics on classical computing. To formulate the problem of a quantum mechanical description of classical computing, electronic device and logic gates are described as quantum sub-systems with inputs treated as boundary conditions, outputs expressed.is operator expectation values, and transfer characteristics and logic operations expressed through the sub-system Hamiltonian. with constraints appropriate to the boundary conditions. This approach, naturally, leads to a description of the subsystem.,, in terms of density matrices. Application of the maximum entropy principle subject to the boundary conditions (inputs) allows for the determination of the density matrix (logic operation), and for calculation of expectation values of operators over a finite region (outputs). The method allows for in analysis of the static properties of quantum sub-systems.

Enabling Robust and Efficient Distributed Computation in Dynamic Peer-to-Peer Networks

Motivated by the need for designing efficient and robust fully-distributed computation in highly dynamic networks such as Peer-to-Peer (P2P) networks, we study distributed protocols for constructing and maintaining dynamic network topologies with good expansion properties. Our goal is to maintain a sparse (bounded degree) expander topology despite heavy {\em churn} (i.e., nodes joining and leaving the network continuously over time). We assume that the churn is controlled by an adversary that has complete knowledge and control of what nodes join and leave and at what time and has unlimited computational power, but is oblivious to the random choices made by the algorithm. Our main contribution is a randomized distributed protocol that guarantees with high probability the maintenance of a {\em constant} degree graph with {\em high expansion} even under {\em continuous high adversarial} churn. Our protocol can tolerate a churn rate of up to $O(n/\poly\log(n))$ per round (where $n$ is the stable network size). Our protocol is efficient, lightweight, and scalable, and it incurs only $O(\poly\log(n))$ overhead for topology maintenance: only polylogarithmic (in $n$) bits needs to be processed and sent by each node per round and any node's computation cost per round is also polylogarithmic. The given protocol is a fundamental ingredient that is needed for the design of efficient fully-distributed algorithms for solving fundamental distributed computing problems such as agreement, leader election, search, and storage in highly dynamic P2P networks and enables fast and scalable algorithms for these problems that can tolerate a large amount of churn.

Efficient biometric and password based mutual authentication for consumer USB mass storage devices

A Universal Serial Bus (USB) Mass Storage Device (MSD), often termed a USB flash drive, is ubiquitously used to store important information in unencrypted binary format. This low cost consumer device is incredibly popular due to its size, large storage capacity and relatively high transfer speed. However, if the device is lost or stolen an unauthorized person can easily retrieve all the information. Therefore, it is advantageous in many applications to provide security protection so that only authorized users can access the stored information. In order to provide security protection for a USB MSD, this paper proposes a session key agreement protocol after secure user authentication. The main aim of this protocol is to establish session key negotiation through which all the information retrieved, stored and transferred to the USB MSD is encrypted. This paper not only contributes an efficient protocol, but also does not suffer from the forgery attack and the password guessing attack as compared to other protocols in the literature. This paper analyses the security of the proposed protocol through a formal analysis which proves that the information is stored confidentially and is protected offering strong resilience to relevant security attacks. The computational cost and communication cost of the proposed scheme is analyzed and compared to related work to show that the proposed scheme has an improved tradeoff for computational cost, communication cost and security.

Effectiveness-ntu computation with a mathematical model for cross-flow heat exchangers

Due to the wide range of design possibilities, simple manufactured, low maintenance and low cost, cross-flow heat exchangers are extensively used in the petroleum, petrochemical, air conditioning, food storage, and others industries. In this paper a mathematical model for cross-flow heat exchangers with complex flow arrangements for determining epsilon -NTU relations is presented. The model is based on the tube element approach, according to which the heat exchanger outlet temperatures are obtained by discretizing the coil along the tube fluid path. In each cross section of the element, tube-side fluid temperature is assumed to be constant because the heat capacity rate ratio C*=Cmin/Cmax tends toward zero in the element. Thus temperature is controlled by effectiveness of a local element corresponding to an evaporator or a condenser-type element. The model is validated through comparison with theoretical algebraic relations for single-pass cross-flow arrangements with one or more rows. Very small relative errors are obtained showing the accuracy of the present model. epsilon -NTU curves for several complex circuit arrangements are presented. The model developed represents a useful research tool for theoretical and experimental studies on heat exchangers performance.

Interconnection systems for highly integrated computation devices

The sustained demand for faster,more powerful chips has beenmet by the availability of chip manufacturing processes allowing for the integration of increasing numbers of computation units onto a single die. The resulting outcome, especially in the embedded domain, has often been called SYSTEM-ON-CHIP (SOC) or MULTI-PROCESSOR SYSTEM-ON-CHIP (MPSOC). MPSoC design brings to the foreground a large number of challenges, one of the most prominent of which is the design of the chip interconnection. With a number of on-chip blocks presently ranging in the tens, and quickly approaching the hundreds, the novel issue of how to best provide on-chip communication resources is clearly felt. NETWORKS-ON-CHIPS (NOCS) are the most comprehensive and scalable answer to this design concern. By bringing large-scale networking concepts to the on-chip domain, they guarantee a structured answer to present and future communication requirements. The point-to-point connection and packet switching paradigms they involve are also of great help in minimizing wiring overhead and physical routing issues. However, as with any technology of recent inception, NoC design is still an evolving discipline. Several main areas of interest require deep investigation for NoCs to become viable solutions: • The design of the NoC architecture needs to strike the best tradeoff among performance, features and the tight area and power constraints of the on-chip domain. • Simulation and verification infrastructure must be put in place to explore, validate and optimize the NoC performance. • NoCs offer a huge design space, thanks to their extreme customizability in terms of topology and architectural parameters. Design tools are needed to prune this space and pick the best solutions. • Even more so given their global, distributed nature, it is essential to evaluate the physical implementation of NoCs to evaluate their suitability for next-generation designs and their area and power costs. This dissertation focuses on all of the above points, by describing a NoC architectural implementation called ×pipes; a NoC simulation environment within a cycle-accurate MPSoC emulator called MPARM; a NoC design flow consisting of a front-end tool for optimal NoC instantiation, called SunFloor, and a set of back-end facilities for the study of NoC physical implementations. This dissertation proves the viability of NoCs for current and upcoming designs, by outlining their advantages (alongwith a fewtradeoffs) and by providing a full NoC implementation framework. It also presents some examples of additional extensions of NoCs, allowing e.g. for increased fault tolerance, and outlines where NoCsmay find further application scenarios, such as in stacked chips.

A Novel Approach to Carbon Dioxide Capture and Storage

The novel approach to carbon capture and storage (CCS) described in this dissertation is a significant departure from the conventional approach to CCS. The novel approach uses a sodium carbonate solution to first capture CO2 from post combustion flue gas streams. The captured CO2 is then reacted with an alkaline industrial waste material, at ambient conditions, to regenerate the carbonate solution and permanently store the CO2 in the form of an added value carbonate mineral. Conventional CCS makes use of a hazardous amine solution for CO2 capture, a costly thermal regeneration stage, and the underground storage of supercritical CO2. The objective of the present dissertation was to examine each individual stage (capture and storage) of the proposed approach to CCS. Study of the capture stage found that a 2% w/w sodium carbonate solution was optimal for CO2 absorption in the present system. The 2% solution yielded the best tradeoff between the CO2 absorption rate and the CO2 absorption capacity of the solutions tested. Examination of CO2 absorption in the presence of flue gas impurities (NOx and SOx) found that carbonate solutions possess a significant advantage over amine solutions, that they could be used for multi-pollutant capture. All the NOx and SOx fed to the carbonate solution was able to be captured. Optimization studies found that it was possible to increase the absorption rate of CO2 into the carbonate solution by adding a surfactant to the solution to chemically alter the gas bubble size. The absorption rate of CO2 was increased by as much as 14%. Three coal combustion fly ash materials were chosen as the alkaline industrial waste materials to study the storage CO2 and regeneration the absorbent. X-ray diffraction analysis on reacted fly ash samples confirmed that the captured CO2 reacts with the fly ash materials to form a carbonate mineral, specifically calcite. Studies found that after a five day reaction time, 75% utilization of the waste material for CO2 storage could be achieved, while regenerating the absorbent. The regenerated absorbent exhibited a nearly identical CO2 absorption capacity and CO2 absorption rate as a fresh Na2CO3 solution.

A model of long-term memory storage in the cerebellar cortex: A possible role for plasticity at parallel fiber synapses onto stellate/basket interneurons

By evoking changes in climbing fiber activity, movement errors are thought to modify synapses from parallel fibers onto Purkinje cells (pf*Pkj) so as to improve subsequent motor performance. Theoretical arguments suggest there is an intrinsic tradeoff, however, between motor adaptation and long-term storage. Assuming a baseline rate of motor errors is always present, then repeated performance of any learned movement will generate a series of climbing fiber-mediated corrections. By reshuffling the synaptic weights responsible for any given movement, such corrections will degrade the memories for other learned movements stored in overlapping sets of synapses. The present paper shows that long-term storage can be accomplished by a second site of plasticity at synapses from parallel fibers onto stellate/basket interneurons (pf*St/Bk). Plasticity at pf*St/Bk synapses can be insulated from ongoing fluctuations in climbing fiber activity by assuming that changes in pf*St/Bk synapses occur only after changes in pf*Pkj synapses have built up to a threshold level. Although climbing fiber-dependent plasticity at pf*Pkj synapses allows for the exploration of novel motor strategies in response to changing environmental conditions, plasticity at pf*St/Bk synapses transfers successful strategies to stable long-term storage. To quantify this hypothesis, both sites of plasticity are incorporated into a dynamical model of the cerebellar cortex and its interactions with the inferior olive. When used to simulate idealized motor conditioning trials, the model predicts that plasticity develops first at pf*Pkj synapses, but with additional training is transferred to pf*St/Bk synapses for long-term storage.

Hierarchical associative memories for parallel computation /

"This report reproduces a thesis of the same title submitted to the Department of Electrical Engineering, Massachusetts Institute of Technology, in partial fulfillment of the requirements for the degree of Doctor of Philosophy, May 1970."--p. 2

Practical, Computation Efficient High-Order Neural Network for Rotation and Shift Invariant Pattern Recognition

In this paper, a modification for the high-order neural network (HONN) is presented. Third order networks are considered for achieving translation, rotation and scale invariant pattern recognition. They require however much storage and computation power for the task. The proposed modified HONN takes into account a priori knowledge of the binary patterns that have to be learned, achieving significant gain in computation time and memory requirements. This modification enables the efficient computation of HONNs for image fields of greater that 100 × 100 pixels without any loss of pattern information.

Nanostructured Metal Oxide Coatings for Electrochemical Energy Conversion and Storage Electrodes

The realization of an energy future based on safe, clean, sustainable, and economically viable technologies is one of the grand challenges facing modern society. Electrochemical energy technologies underpin the potential success of this effort to divert energy sources away from fossil fuels, whether one considers alternative energy conversion strategies through photoelectrochemical (PEC) production of chemical fuels or fuel cells run with sustainable hydrogen, or energy storage strategies, such as in batteries and supercapacitors. This dissertation builds on recent advances in nanomaterials design, synthesis, and characterization to develop novel electrodes that can electrochemically convert and store energy.

Chapter 2 of this dissertation focuses on refining the properties of TiO2-based PEC water-splitting photoanodes used for the direct electrochemical conversion of solar energy into hydrogen fuel. The approach utilized atomic layer deposition (ALD); a growth process uniquely suited for the conformal and uniform deposition of thin films with angstrom-level thickness precision. ALD’s thickness control enabled a better understanding of how the effects of nitrogen doping via NH3 annealing treatments, used to reduce TiO2’s bandgap, can have a strong dependence on TiO2’s thickness and crystalline quality. In addition, it was found that some of the negative effects on the PEC performance typically associated with N-doped TiO2 could be mitigated if the NH3-annealing was directly preceded by an air-annealing step, especially for ultrathin (i.e., < 10 nm) TiO2 films. ALD was also used to conformally coat an ultraporous conductive fluorine-doped tin oxide nanoparticle (nanoFTO) scaffold with an ultrathin layer of TiO2. The integration of these ultrathin films and the oxide nanoparticles resulted in a heteronanostructure design with excellent PEC water oxidation photocurrents (0.7 mA/cm2 at 0 V vs. Ag/AgCl) and charge transfer efficiency.

In Chapter 3, two innovative nanoarchitectures were engineered in order to enhance the pseudocapacitive energy storage of next generation supercapacitor electrodes. The morphology and quantity of MnO2 electrodeposits was controlled by adjusting the density of graphene foliates on a novel graphenated carbon nanotube (g-CNT) scaffold. This control enabled the nanocomposite supercapacitor electrode to reach a capacitance of 640 F/g, under MnO2 specific mass loading conditions (2.3 mg/cm2) that are higher than previously reported. In the second engineered nanoarchitecture, the electrochemical energy storage properties of a transparent electrode based on a network of solution-processed Cu/Ni cores/shell nanowires (NWs) were activated by electrochemically converting the Ni metal shell into Ni(OH)2. Furthermore, an adjustment of the molar percentage of Ni plated onto the Cu NWs was found to result in a tradeoff between capacitance, transmittance, and stability of the resulting nickel hydroxide-based electrode. The nominal area capacitance and power performance results obtained for this Cu/Ni(OH)2 transparent electrode demonstrates that it has significant potential as a hybrid supercapacitor electrode for integration into cutting edge flexible and transparent electronic devices.

Towards power consumption-delay tradeoff by workload allocation in cloud-fog computing

Fog computing, characterized by extending cloud computing to the edge of the network, has recently received considerable attention. The fog is not a substitute but a powerful complement to the cloud. It is worthy of studying the interplay and cooperation between the edge (fog) and the core (cloud). To address this issue, we study the tradeoff between power consumption and delay in a cloud-fog computing system. Specifically, we first mathematically formulate the workload allocation problem. After that, we develop an approximate solution to decompose the primal problem into three subproblems of corresponding subsystems, which can be independently solved. Finally, based on extensive simulations and numerical results, we show that by sacrificing modest computation resources to save communication bandwidth and reduce transmission latency, fog computing can significantly improve the performance of cloud computing.

Enabling efficient publicly verifiable outsourcing computation for matrix multiplication

Outsourcing heavy computational tasks to remote cloud server, which accordingly significantly reduce the computational burden at the end hosts, represents an effective and practical approach towards extensive and scalable mobile applications and has drawn increasing attention in recent years. However, due to the limited processing power of the end hosts yet the keen privacy concerns on the outsourced data, it is vital to ensure both the efficiency and security of the outsourcing computation in the cloud computing. In this paper, we address the issue by developing a publicly verifiable outsourcing computation proposal. In particular, considering a large amount of applications of matrix multiplication in large datasets and image processing, we propose a publicly verifiable outsourcing computation scheme for matrix multiplication in the amortized model. Security analysis demonstrates that the proposed scheme is provable secure by blinding input and output in a simple way. By comparing the developed scheme with existing proposals, we show that our proposal is more efficient in terms of functionality, as well as the computation, communication and storage overhead.