Exploration and Design of Power-Efficient Networked Many-Core Systems

Multiprocessing is a promising solution to meet the requirements of near future applications. To get full benefit from parallel processing, a manycore system needs efficient, on-chip communication architecture. Networkon- Chip (NoC) is a general purpose communication concept that offers highthroughput, reduced power consumption, and keeps complexity in check by a regular composition of basic building blocks. This thesis presents power efficient communication approaches for networked many-core systems. We address a range of issues being important for designing power-efficient manycore systems at two different levels: the network-level and the router-level. From the network-level point of view, exploiting state-of-the-art concepts such as Globally Asynchronous Locally Synchronous (GALS), Voltage/ Frequency Island (VFI), and 3D Networks-on-Chip approaches may be a solution to the excessive power consumption demanded by today’s and future many-core systems. To this end, a low-cost 3D NoC architecture, based on high-speed GALS-based vertical channels, is proposed to mitigate high peak temperatures, power densities, and area footprints of vertical interconnects in 3D ICs. To further exploit the beneficial feature of a negligible inter-layer distance of 3D ICs, we propose a novel hybridization scheme for inter-layer communication. In addition, an efficient adaptive routing algorithm is presented which enables congestion-aware and reliable communication for the hybridized NoC architecture. An integrated monitoring and management platform on top of this architecture is also developed in order to implement more scalable power optimization techniques. From the router-level perspective, four design styles for implementing power-efficient reconfigurable interfaces in VFI-based NoC systems are proposed. To enhance the utilization of virtual channel buffers and to manage their power consumption, a partial virtual channel sharing method for NoC routers is devised and implemented. Extensive experiments with synthetic and real benchmarks show significant power savings and mitigated hotspots with similar performance compared to latest NoC architectures. The thesis concludes that careful codesigned elements from different network levels enable considerable power savings for many-core systems.

Adaptive Routing Approaches for Networked Many-Core Systems

Through advances in technology, System-on-Chip design is moving towards integrating tens to hundreds of intellectual property blocks into a single chip. In such a many-core system, on-chip communication becomes a performance bottleneck for high performance designs. Network-on-Chip (NoC) has emerged as a viable solution for the communication challenges in highly complex chips. The NoC architecture paradigm, based on a modular packet-switched mechanism, can address many of the on-chip communication challenges such as wiring complexity, communication latency, and bandwidth. Furthermore, the combined benefits of 3D IC and NoC schemes provide the possibility of designing a high performance system in a limited chip area. The major advantages of 3D NoCs are the considerable reductions in average latency and power consumption. There are several factors degrading the performance of NoCs. In this thesis, we investigate three main performance-limiting factors: network congestion, faults, and the lack of efficient multicast support. We address these issues by the means of routing algorithms. Congestion of data packets may lead to increased network latency and power consumption. Thus, we propose three different approaches for alleviating such congestion in the network. The first approach is based on measuring the congestion information in different regions of the network, distributing the information over the network, and utilizing this information when making a routing decision. The second approach employs a learning method to dynamically find the less congested routes according to the underlying traffic. The third approach is based on a fuzzy-logic technique to perform better routing decisions when traffic information of different routes is available. Faults affect performance significantly, as then packets should take longer paths in order to be routed around the faults, which in turn increases congestion around the faulty regions. We propose four methods to tolerate faults at the link and switch level by using only the shortest paths as long as such path exists. The unique characteristic among these methods is the toleration of faults while also maintaining the performance of NoCs. To the best of our knowledge, these algorithms are the first approaches to bypassing faults prior to reaching them while avoiding unnecessary misrouting of packets. Current implementations of multicast communication result in a significant performance loss for unicast traffic. This is due to the fact that the routing rules of multicast packets limit the adaptivity of unicast packets. We present an approach in which both unicast and multicast packets can be efficiently routed within the network. While suggesting a more efficient multicast support, the proposed approach does not affect the performance of unicast routing at all. In addition, in order to reduce the overall path length of multicast packets, we present several partitioning methods along with their analytical models for latency measurement. This approach is discussed in the context of 3D mesh networks.

Solution of aerospace problems using structured and unstructured strategies

Products developed at industries, institutes and research centers are expected to have high level of quality and performance, having a minimum waste, which require efficient and robust tools to numerically simulate stringent project conditions with great reliability. In this context, Computational Fluid Dynamics (CFD) plays an important role and the present work shows two numerical algorithms that are used in the CFD community to solve the Euler and Navier-Stokes equations applied to typical aerospace and aeronautical problems. Particularly, unstructured discretization of the spatial domain has gained special attention by the international community due to its ease in discretizing complex spatial domains. This work has the main objective of illustrating some advantages and disadvantages of numerical algorithms using structured and unstructured spatial discretization of the flow governing equations. Numerical methods include a finite volume formulation and the Euler and Navier-Stokes equations are applied to solve a transonic nozzle problem, a low supersonic airfoil problem and a hypersonic inlet problem. In a structured context, these problems are solved using MacCormack’s implicit algorithm with Steger and Warming’s flux vector splitting technique, while, in an unstructured context, Jameson and Mavriplis’ explicit algorithm is used. Convergence acceleration is obtained using a spatially variable time stepping procedure.

Control of Structures with Cubic and Quadratic Non-Linearities with Time Delay Consideration

This paper studies the effect of time delay on the active non-linear control of dynamically loaded flexible structures. The behavior of non-linear systems under state feedback control, considering a fixed time delay for the control force, is investigated. A control method based on non-linear optimal control, using a tensorial formulation and state feedback control is used. The state equations and the control forces are expressed in polynomial form and a performance index, quadratic in both state vector and control forces, is used. General polynomial representations of the non-linear control law are obtained and implemented for control algorithms up to the fifth order. This methodology is applied to systems with quadratic and cubic non-linearities. Strongly non-linear systems are tested and the effectiveness of the control system including a delay for the application of control forces is discussed. Numerical results indicate that the adopted control algorithm can be efficient for non-linear systems, chiefly in the presence of strong non-linearities but increasing time delay reduces the efficiency of the control system. Numerical results emphasize the importance of considering time delay in the project of active structural control systems.

Energy-efficient control strategies for variable speed driven parallel pumping systems based on pump operation point monitoring with frequency converters

The pumping processes requiring wide range of flow are often equipped with parallelconnected centrifugal pumps. In parallel pumping systems, the use of variable speed control allows that the required output for the process can be delivered with a varying number of operated pump units and selected rotational speed references. However, the optimization of the parallel-connected rotational speed controlled pump units often requires adaptive modelling of both parallel pump characteristics and the surrounding system in varying operation conditions. The available information required for the system modelling in typical parallel pumping applications such as waste water treatment and various cooling and water delivery pumping tasks can be limited, and the lack of real-time operation point monitoring often sets limits for accurate energy efficiency optimization. Hence, alternatives for easily implementable control strategies which can be adopted with minimum system data are necessary. This doctoral thesis concentrates on the methods that allow the energy efficient use of variable speed controlled parallel pumps in system scenarios in which the parallel pump units consist of a centrifugal pump, an electric motor, and a frequency converter. Firstly, the suitable operation conditions for variable speed controlled parallel pumps are studied. Secondly, methods for determining the output of each parallel pump unit using characteristic curve-based operation point estimation with frequency converter are discussed. Thirdly, the implementation of the control strategy based on real-time pump operation point estimation and sub-optimization of each parallel pump unit is studied. The findings of the thesis support the idea that the energy efficiency of the pumping can be increased without the installation of new, more efficient components in the systems by simply adopting suitable control strategies. An easily implementable and adaptive control strategy for variable speed controlled parallel pumping systems can be created by utilizing the pump operation point estimation available in modern frequency converters. Hence, additional real-time flow metering, start-up measurements, and detailed system model are unnecessary, and the pumping task can be fulfilled by determining a speed reference for each parallel-pump unit which suggests the energy efficient operation of the pumping system.

Scalable algorithms for height field illumination

Global illumination algorithms are at the center of realistic image synthesis and account for non-trivial light transport and occlusion within scenes, such as indirect illumination, ambient occlusion, and environment lighting. Their computationally most difficult part is determining light source visibility at each visible scene point. Height fields, on the other hand, constitute an important special case of geometry and are mainly used to describe certain types of objects such as terrains and to map detailed geometry onto object surfaces. The geometry of an entire scene can also be approximated by treating the distance values of its camera projection as a screen-space height field. In order to shadow height fields from environment lights a horizon map is usually used to occlude incident light. We reduce the per-receiver time complexity of generating the horizon map on N N height fields from O(N) of the previous work to O(1) by using an algorithm that incrementally traverses the height field and reuses the information already gathered along the path of traversal. We also propose an accurate method to integrate the incident light within the limits given by the horizon map. Indirect illumination in height fields requires information about which other points are visible to each height field point. We present an algorithm to determine this intervisibility in a time complexity that matches the space complexity of the produced visibility information, which is in contrast to previous methods which scale in the height field size. As a result the amount of computation is reduced by two orders of magnitude in common use cases. Screen-space ambient obscurance methods approximate ambient obscurance from the depth bu er geometry and have been widely adopted by contemporary real-time applications. They work by sampling the screen-space geometry around each receiver point but have been previously limited to near- field effects because sampling a large radius quickly exceeds the render time budget. We present an algorithm that reduces the quadratic per-pixel complexity of previous methods to a linear complexity by line sweeping over the depth bu er and maintaining an internal representation of the processed geometry from which occluders can be efficiently queried. Another algorithm is presented to determine ambient obscurance from the entire depth bu er at each screen pixel. The algorithm scans the depth bu er in a quick pre-pass and locates important features in it, which are then used to evaluate the ambient obscurance integral accurately. We also propose an evaluation of the integral such that results within a few percent of the ray traced screen-space reference are obtained at real-time render times.

Ensuring the efficient utilization of Business Intelligence

In recent years, chief information officers (CIOs) around the world have identified Business Intelligence (BI) as their top priority and as the best way to enhance their enterprises competitiveness. Yet, many enterprises are struggling to realize the business value that BI promises. This discrepancy causes important questions, for example: what are the critical success factors of Business Intelligence and, more importantly, how it can be ensured that a Business Intelligence program enhances enterprises competitiveness. The main objective of the study is to find out how it can be ensured that a BI program meets its goals in providing competitive advantage to an enterprise. The objective is approached with a literature review and a qualitative case study. For the literature review the main objective populates three research questions (RQs); RQ1: What is Business Intelligence and why is it important for modern enterprises? RQ2: What are the critical success factors of Business Intelligence programs? RQ3: How it can be ensured that CSFs are met? The qualitative case study covers the BI program of a Finnish global manufacturer company. The research questions for the case study are as follows; RQ4: What is the current state of the case company’s BI program and what are the key areas for improvement? RQ5: In what ways the case company’s Business Intelligence program could be improved? The case company’s BI program is researched using the following methods; action research, semi-structured interviews, maturity assessment and benchmarking. The literature review shows that Business Intelligence is a technology-based information process that contains a series of systematic activities, which are driven by the specific information needs of decision-makers. The objective of BI is to provide accurate, timely, fact-based information, which enables taking actions that lead to achieving competitive advantage. There are many reasons for the importance of Business Intelligence, two of the most important being; 1) It helps to bridge the gap between an enterprise’s current and its desired performance, and 2) It helps enterprises to be in alignment with key performance indicators meaning it helps an enterprise to align towards its key objectives. The literature review also shows that there are known critical success factors (CSFs) for Business Intelligence programs which have to be met if the above mentioned value is wanted to be achieved, for example; committed management support and sponsorship, business-driven development approach and sustainable data quality. The literature review shows that the most common challenges are related to these CSFs and, more importantly, that overcoming these challenges requires a more comprehensive form of BI, called Enterprise Performance Management (EPM). EPM links measurement to strategy by focusing on what is measured and why. The case study shows that many of the challenges faced in the case company’s BI program are related to the above-mentioned CSFs. The main challenges are; lack of support and sponsorship from business, lack of visibility to overall business performance, lack of rigid BI development process, lack of clear purpose for the BI program and poor data quality. To overcome these challenges the case company should define and design an enterprise metrics framework, make sure that BI development requirements are gathered and prioritized by business, focus on data quality and ownership, and finally define clear goals for the BI program and then support and sponsor these goals.

Comparison between dSPACE and NI systems based on real-time intelligent control of a teleoperated hydraulic servo system

The Laboratory of Intelligent Machine researches and develops energy-efficient power transmissions and automation for mobile construction machines and industrial processes. The laboratory's particular areas of expertise include mechatronic machine design using virtual technologies and simulators and demanding industrial robotics. The laboratory has collaborated extensively with industrial actors and it has participated in significant international research projects, particularly in the field of robotics. For years, dSPACE tools were the lonely hardware which was used in the lab to develop different control algorithms in real-time. dSPACE's hardware systems are in widespread use in the automotive industry and are also employed in drives, aerospace, and industrial automation. But new competitors are developing new sophisticated systems and their features convinced the laboratory to test new products. One of these competitors is National Instrument (NI). In order to get to know the specifications and capabilities of NI tools, an agreement was made to test a NI evolutionary system. This system is used to control a 1-D hydraulic slider. The objective of this research project is to develop a control scheme for the teleoperation of a hydraulically driven manipulator, and to implement a control algorithm between human and machine interaction, and machine and task environment interaction both on NI and dSPACE systems simultaneously and to compare the results.

Cost-efficient virtual machine management : provisioning, admission control, and consolidation

One of the main challenges in Software Engineering is to cope with the transition from an industry based on software as a product to software as a service. The field of Software Engineering should provide the necessary methods and tools to develop and deploy new cost-efficient and scalable digital services. In this thesis, we focus on deployment platforms to ensure cost-efficient scalability of multi-tier web applications and on-demand video transcoding service for different types of load conditions. Infrastructure as a Service (IaaS) clouds provide Virtual Machines (VMs) under the pay-per-use business model. Dynamically provisioning VMs on demand allows service providers to cope with fluctuations on the number of service users. However, VM provisioning must be done carefully, because over-provisioning results in an increased operational cost, while underprovisioning leads to a subpar service. Therefore, our main focus in this thesis is on cost-efficient VM provisioning for multi-tier web applications and on-demand video transcoding. Moreover, to prevent provisioned VMs from becoming overloaded, we augment VM provisioning with an admission control mechanism. Similarly, to ensure efficient use of provisioned VMs, web applications on the under-utilized VMs are consolidated periodically. Thus, the main problem that we address is cost-efficient VM provisioning augmented with server consolidation and admission control on the provisioned VMs. We seek solutions for two types of applications: multi-tier web applications that follow the request-response paradigm and on-demand video transcoding that is based on video streams with soft realtime constraints. Our first contribution is a cost-efficient VM provisioning approach for multi-tier web applications. The proposed approach comprises two subapproaches: a reactive VM provisioning approach called ARVUE and a hybrid reactive-proactive VM provisioning approach called Cost-efficient Resource Allocation for Multiple web applications with Proactive scaling. Our second contribution is a prediction-based VM provisioning approach for on-demand video transcoding in the cloud. Moreover, to prevent virtualized servers from becoming overloaded, the proposed VM provisioning approaches are augmented with admission control approaches. Therefore, our third contribution is a session-based admission control approach for multi-tier web applications called adaptive Admission Control for Virtualized Application Servers. Similarly, the fourth contribution in this thesis is a stream-based admission control and scheduling approach for on-demand video transcoding called Stream-Based Admission Control and Scheduling. Our fifth contribution is a computation and storage trade-o strategy for cost-efficient video transcoding in cloud computing. Finally, the sixth and the last contribution is a web application consolidation approach, which uses Ant Colony System to minimize the under-utilization of the virtualized application servers.

Algorithmic Techniques in Gene Expression Processing. From Imputation to Visualization

The amount of biological data has grown exponentially in recent decades. Modern biotechnologies, such as microarrays and next-generation sequencing, are capable to produce massive amounts of biomedical data in a single experiment. As the amount of the data is rapidly growing there is an urgent need for reliable computational methods for analyzing and visualizing it. This thesis addresses this need by studying how to efficiently and reliably analyze and visualize high-dimensional data, especially that obtained from gene expression microarray experiments. First, we will study the ways to improve the quality of microarray data by replacing (imputing) the missing data entries with the estimated values for these entries. Missing value imputation is a method which is commonly used to make the original incomplete data complete, thus making it easier to be analyzed with statistical and computational methods. Our novel approach was to use curated external biological information as a guide for the missing value imputation. Secondly, we studied the effect of missing value imputation on the downstream data analysis methods like clustering. We compared multiple recent imputation algorithms against 8 publicly available microarray data sets. It was observed that the missing value imputation indeed is a rational way to improve the quality of biological data. The research revealed differences between the clustering results obtained with different imputation methods. On most data sets, the simple and fast k-NN imputation was good enough, but there were also needs for more advanced imputation methods, such as Bayesian Principal Component Algorithm (BPCA). Finally, we studied the visualization of biological network data. Biological interaction networks are examples of the outcome of multiple biological experiments such as using the gene microarray techniques. Such networks are typically very large and highly connected, thus there is a need for fast algorithms for producing visually pleasant layouts. A computationally efficient way to produce layouts of large biological interaction networks was developed. The algorithm uses multilevel optimization within the regular force directed graph layout algorithm.

Efficient retrovirus-mediated transfer of cell-cycle control genes to transformed cells

The use of gene therapy continues to be a promising, yet elusive, alternative for the treatment of cancer. The origins of cancer must be well understood so that the therapeutic gene can be chosen with the highest chance of successful tumor regression. The gene delivery system must be tailored for optimum transfer of the therapeutic gene to the target tissue. In order to accomplish this, we study models of G1 cell-cycle control in both normal and transformed cells in order to understand the reasons for uncontrolled cellular proliferation. We then use this information to choose the gene to be delivered to the cells. We have chosen to study p16, p21, p53 and pRb gene transfer using the pCL-retrovirus. Described here are some general concepts and specific results of our work that indicate continued hope for the development of genetically based cancer treatments.

Antigenic stimulation is more efficient than LPS in inducing nitric oxide production by human mononuclear cells on the in vitro granuloma reaction in schistosomiasis

Nitric oxide (NO) is an extremely important and versatile messenger in biological systems. It has been identified as a cytotoxic factor in the immune system, presenting anti- or pro-inflammatory properties under different circumstances. In murine monocytes and macrophages, stimuli by cytokines or lipopolysaccharide (LPS) are necessary for inducing the immunologic isoform of the enzyme responsible for the high-output production of NO, nitric oxide synthase (iNOS). With respect to human cells, however, LPS seems not to stimulate NO production in the same way. Addressing this issue, we demonstrate here that peripheral blood mononuclear cells (PBMC) obtained from schistosomiasis-infected patients and cultivated with parasite antigens in the in vitro granuloma (IVG) reaction produced more nitrite in the absence of LPS. Thus, LPS-induced nitrite levels are easily detectable, although lower than those detected only with antigenic stimulation. Concomitant addition of LPS and L-N-arginine methyl ester (L-NAME) restored the ability to produce detectable levels of nitrite, which had been lost with L-NAME treatment. In addition, LPS caused a mild decrease of the IVG reaction and its association with L-NAME was responsible for reversal of the L-NAME-exacerbating effect on the IVG reaction. These results show that LPS alone is not as good an NO inducer in human cells as it is in rodent cells or cell lines. Moreover, they provide evidence for interactions between LPS and NO inhibitors that require further investigation.