Exploring Adaptive Implementation of On-Chip Networks

As technology geometries have shrunk to the deep submicron regime, the communication delay and power consumption of global interconnections in high performance Multi- Processor Systems-on-Chip (MPSoCs) are becoming a major bottleneck. The Network-on- Chip (NoC) architecture paradigm, based on a modular packet-switched mechanism, can address many of the on-chip communication issues such as performance limitations of long interconnects and integration of large number of Processing Elements (PEs) on a chip. The choice of routing protocol and NoC structure can have a significant impact on performance and power consumption in on-chip networks. In addition, building a high performance, area and energy efficient on-chip network for multicore architectures requires a novel on-chip router allowing a larger network to be integrated on a single die with reduced power consumption. On top of that, network interfaces are employed to decouple computation resources from communication resources, to provide the synchronization between them, and to achieve backward compatibility with existing IP cores. Three adaptive routing algorithms are presented as a part of this thesis. The first presented routing protocol is a congestion-aware adaptive routing algorithm for 2D mesh NoCs which does not support multicast (one-to-many) traffic while the other two protocols are adaptive routing models supporting both unicast (one-to-one) and multicast traffic. A streamlined on-chip router architecture is also presented for avoiding congested areas in 2D mesh NoCs via employing efficient input and output selection. The output selection utilizes an adaptive routing algorithm based on the congestion condition of neighboring routers while the input selection allows packets to be serviced from each input port according to its congestion level. Moreover, in order to increase memory parallelism and bring compatibility with existing IP cores in network-based multiprocessor architectures, adaptive network interface architectures are presented to use multiple SDRAMs which can be accessed simultaneously. In addition, a smart memory controller is integrated in the adaptive network interface to improve the memory utilization and reduce both memory and network latencies. Three Dimensional Integrated Circuits (3D ICs) have been emerging as a viable candidate to achieve better performance and package density as compared to traditional 2D ICs. In addition, combining the benefits of 3D IC and NoC schemes provides a significant performance gain for 3D architectures. In recent years, inter-layer communication across multiple stacked layers (vertical channel) has attracted a lot of interest. In this thesis, a novel adaptive pipeline bus structure is proposed for inter-layer communication to improve the performance by reducing the delay and complexity of traditional bus arbitration. In addition, two mesh-based topologies for 3D architectures are also introduced to mitigate the inter-layer footprint and power dissipation on each layer with a small performance penalty.

On Dynamic Monitoring Methods for Networks-on-Chip

Rapid ongoing evolution of multiprocessors will lead to systems with hundreds of processing cores integrated in a single chip. An emerging challenge is the implementation of reliable and efficient interconnection between these cores as well as other components in the systems. Network-on-Chip is an interconnection approach which is intended to solve the performance bottleneck caused by traditional, poorly scalable communication structures such as buses. However, a large on-chip network involves issues related to congestion problems and system control, for instance. Additionally, faults can cause problems in multiprocessor systems. These faults can be transient faults, permanent manufacturing faults, or they can appear due to aging. To solve the emerging traffic management, controllability issues and to maintain system operation regardless of faults a monitoring system is needed. The monitoring system should be dynamically applicable to various purposes and it should fully cover the system under observation. In a large multiprocessor the distances between components can be relatively long. Therefore, the system should be designed so that the amount of energy-inefficient long-distance communication is minimized. This thesis presents a dynamically clustered distributed monitoring structure. The monitoring is distributed so that no centralized control is required for basic tasks such as traffic management and task mapping. To enable extensive analysis of different Network-on-Chip architectures, an in-house SystemC based simulation environment was implemented. It allows transaction level analysis without time consuming circuit level implementations during early design phases of novel architectures and features. The presented analysis shows that the dynamically clustered monitoring structure can be efficiently utilized for traffic management in faulty and congested Network-on-Chip-based multiprocessor systems. The monitoring structure can be also successfully applied for task mapping purposes. Furthermore, the analysis shows that the presented in-house simulation environment is flexible and practical tool for extensive Network-on-Chip architecture analysis.

On Energy Efficient Computing Platforms

In accordance with the Moore's law, the increasing number of on-chip integrated transistors has enabled modern computing platforms with not only higher processing power but also more affordable prices. As a result, these platforms, including portable devices, work stations and data centres, are becoming an inevitable part of the human society. However, with the demand for portability and raising cost of power, energy efficiency has emerged to be a major concern for modern computing platforms. As the complexity of on-chip systems increases, Network-on-Chip (NoC) has been proved as an efficient communication architecture which can further improve system performances and scalability while reducing the design cost. Therefore, in this thesis, we study and propose energy optimization approaches based on NoC architecture, with special focuses on the following aspects. As the architectural trend of future computing platforms, 3D systems have many bene ts including higher integration density, smaller footprint, heterogeneous integration, etc. Moreover, 3D technology can signi cantly improve the network communication and effectively avoid long wirings, and therefore, provide higher system performance and energy efficiency. With the dynamic nature of on-chip communication in large scale NoC based systems, run-time system optimization is of crucial importance in order to achieve higher system reliability and essentially energy efficiency. In this thesis, we propose an agent based system design approach where agents are on-chip components which monitor and control system parameters such as supply voltage, operating frequency, etc. With this approach, we have analysed the implementation alternatives for dynamic voltage and frequency scaling and power gating techniques at different granularity, which reduce both dynamic and leakage energy consumption. Topologies, being one of the key factors for NoCs, are also explored for energy saving purpose. A Honeycomb NoC architecture is proposed in this thesis with turn-model based deadlock-free routing algorithms. Our analysis and simulation based evaluation show that Honeycomb NoCs outperform their Mesh based counterparts in terms of network cost, system performance as well as energy efficiency.

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.

Design Space Exploration for MPSoC Architectures

Multiprocessor system-on-chip (MPSoC) designs utilize the available technology and communication architectures to meet the requirements of the upcoming applications. In MPSoC, the communication platform is both the key enabler, as well as the key differentiator for realizing efficient MPSoCs. It provides product differentiation to meet a diverse, multi-dimensional set of design constraints, including performance, power, energy, reconfigurability, scalability, cost, reliability and time-to-market. The communication resources of a single interconnection platform cannot be fully utilized by all kind of applications, such as the availability of higher communication bandwidth for computation but not data intensive applications is often unfeasible in the practical implementation. This thesis aims to perform the architecture-level design space exploration towards efficient and scalable resource utilization for MPSoC communication architecture. In order to meet the performance requirements within the design constraints, careful selection of MPSoC communication platform, resource aware partitioning and mapping of the application play important role. To enhance the utilization of communication resources, variety of techniques such as resource sharing, multicast to avoid re-transmission of identical data, and adaptive routing can be used. For implementation, these techniques should be customized according to the platform architecture. To address the resource utilization of MPSoC communication platforms, variety of architectures with different design parameters and performance levels, namely Segmented bus (SegBus), Network-on-Chip (NoC) and Three-Dimensional NoC (3D-NoC), are selected. Average packet latency and power consumption are the evaluation parameters for the proposed techniques. In conventional computing architectures, fault on a component makes the connected fault-free components inoperative. Resource sharing approach can utilize the fault-free components to retain the system performance by reducing the impact of faults. Design space exploration also guides to narrow down the selection of MPSoC architecture, which can meet the performance requirements with design constraints.

On Fault Tolerance Methods for Networks-on-Chip

Technology scaling has proceeded into dimensions in which the reliability of manufactured devices is becoming endangered. The reliability decrease is a consequence of physical limitations, relative increase of variations, and decreasing noise margins, among others. A promising solution for bringing the reliability of circuits back to a desired level is the use of design methods which introduce tolerance against possible faults in an integrated circuit. This thesis studies and presents fault tolerance methods for network-onchip (NoC) which is a design paradigm targeted for very large systems-onchip. In a NoC resources, such as processors and memories, are connected to a communication network; comparable to the Internet. Fault tolerance in such a system can be achieved at many abstraction levels. The thesis studies the origin of faults in modern technologies and explains the classification to transient, intermittent and permanent faults. A survey of fault tolerance methods is presented to demonstrate the diversity of available methods. Networks-on-chip are approached by exploring their main design choices: the selection of a topology, routing protocol, and flow control method. Fault tolerance methods for NoCs are studied at different layers of the OSI reference model. The data link layer provides a reliable communication link over a physical channel. Error control coding is an efficient fault tolerance method especially against transient faults at this abstraction level. Error control coding methods suitable for on-chip communication are studied and their implementations presented. Error control coding loses its effectiveness in the presence of intermittent and permanent faults. Therefore, other solutions against them are presented. The introduction of spare wires and split transmissions are shown to provide good tolerance against intermittent and permanent errors and their combination to error control coding is illustrated. At the network layer positioned above the data link layer, fault tolerance can be achieved with the design of fault tolerant network topologies and routing algorithms. Both of these approaches are presented in the thesis together with realizations in the both categories. The thesis concludes that an optimal fault tolerance solution contains carefully co-designed elements from different abstraction levels

Dynamic Workload Parallelization and System Calibration on Single-Chip Cloud Computer

Many-core systems are emerging from the need of more computational power and power efficiency. However there are many issues which still revolve around the many-core systems. These systems need specialized software before they can be fully utilized and the hardware itself may differ from the conventional computational systems. To gain efficiency from many-core system, programs need to be parallelized. In many-core systems the cores are small and less powerful than cores used in traditional computing, so running a conventional program is not an efficient option. Also in Network-on-Chip based processors the network might get congested and the cores might work at different speeds. In this thesis is, a dynamic load balancing method is proposed and tested on Intel 48-core Single-Chip Cloud Computer by parallelizing a fault simulator. The maximum speedup is difficult to obtain due to severe bottlenecks in the system. In order to exploit all the available parallelism of the Single-Chip Cloud Computer, a runtime approach capable of dynamically balancing the load during the fault simulation process is used. The proposed dynamic fault simulation approach on the Single-Chip Cloud Computer shows up to 45X speedup compared to a serial fault simulation approach. Many-core systems can draw enormous amounts of power, and if this power is not controlled properly, the system might get damaged. One way to manage power is to set power budget for the system. But if this power is drawn by just few cores of the many, these few cores get extremely hot and might get damaged. Due to increase in power density multiple thermal sensors are deployed on the chip area to provide realtime temperature feedback for thermal management techniques. Thermal sensor accuracy is extremely prone to intra-die process variation and aging phenomena. These factors lead to a situation where thermal sensor values drift from the nominal values. This necessitates efficient calibration techniques to be applied before the sensor values are used. In addition, in modern many-core systems cores have support for dynamic voltage and frequency scaling. Thermal sensors located on cores are sensitive to the core's current voltage level, meaning that dedicated calibration is needed for each voltage level. In this thesis a general-purpose software-based auto-calibration approach is also proposed for thermal sensors to calibrate thermal sensors on different range of voltages.

Formal Power Analysis of Systems-on-Chip

The design methods and languages targeted to modern System-on-Chip designs are facing tremendous pressure of the ever-increasing complexity, power, and speed requirements. To estimate any of these three metrics, there is a trade-off between accuracy and abstraction level of detail in which a system under design is analyzed. The more detailed the description, the more accurate the simulation will be, but, on the other hand, the more time consuming it will be. Moreover, a designer wants to make decisions as early as possible in the design flow to avoid costly design backtracking. To answer the challenges posed upon System-on-chip designs, this thesis introduces a formal, power aware framework, its development methods, and methods to constraint and analyze power consumption of the system under design. This thesis discusses on power analysis of synchronous and asynchronous systems not forgetting the communication aspects of these systems. The presented framework is built upon the Timed Action System formalism, which offer an environment to analyze and constraint the functional and temporal behavior of the system at high abstraction level. Furthermore, due to the complexity of System-on-Chip designs, the possibility to abstract unnecessary implementation details at higher abstraction levels is an essential part of the introduced design framework. With the encapsulation and abstraction techniques incorporated with the procedure based communication allows a designer to use the presented power aware framework in modeling these large scale systems. The introduced techniques also enable one to subdivide the development of communication and computation into own tasks. This property is taken into account in the power analysis part as well. Furthermore, the presented framework is developed in a way that it can be used throughout the design project. In other words, a designer is able to model and analyze systems from an abstract specification down to an implementable specification.

Modeling and Analysis of Noise and Interconnects for On-Chip Communication Link Design

This thesis considers modeling and analysis of noise and interconnects in onchip communication. Besides transistor count and speed, the capabilities of a modern design are often limited by on-chip communication links. These links typically consist of multiple interconnects that run parallel to each other for long distances between functional or memory blocks. Due to the scaling of technology, the interconnects have considerable electrical parasitics that affect their performance, power dissipation and signal integrity. Furthermore, because of electromagnetic coupling, the interconnects in the link need to be considered as an interacting group instead of as isolated signal paths. There is a need for accurate and computationally effective models in the early stages of the chip design process to assess or optimize issues affecting these interconnects. For this purpose, a set of analytical models is developed for on-chip data links in this thesis. First, a model is proposed for modeling crosstalk and intersymbol interference. The model takes into account the effects of inductance, initial states and bit sequences. Intersymbol interference is shown to affect crosstalk voltage and propagation delay depending on bus throughput and the amount of inductance. Next, a model is proposed for the switching current of a coupled bus. The model is combined with an existing model to evaluate power supply noise. The model is then applied to reduce both functional crosstalk and power supply noise caused by a bus as a trade-off with time. The proposed reduction method is shown to be effective in reducing long-range crosstalk noise. The effects of process variation on encoded signaling are then modeled. In encoded signaling, the input signals to a bus are encoded using additional signaling circuitry. The proposed model includes variation in both the signaling circuitry and in the wires to calculate the total delay variation of a bus. The model is applied to study level-encoded dual-rail and 1-of-4 signaling. In addition to regular voltage-mode and encoded voltage-mode signaling, current-mode signaling is a promising technique for global communication. A model for energy dissipation in RLC current-mode signaling is proposed in the thesis. The energy is derived separately for the driver, wire and receiver termination.

Power cycling lifetime estimation of IGBT power modules based on chip temperature modeling

In this doctoral thesis, methods to estimate the expected power cycling life of power semiconductor modules based on chip temperature modeling are developed. Frequency converters operate under dynamic loads in most electric drives. The varying loads cause thermal expansion and contraction, which stresses the internal boundaries between the material layers in the power module. Eventually, the stress wears out the semiconductor modules. The wear-out cannot be detected by traditional temperature or current measurements inside the frequency converter. Therefore, it is important to develop a method to predict the end of the converter lifetime. The thesis concentrates on power-cycling-related failures of insulated gate bipolar transistors. Two types of power modules are discussed: a direct bonded copper (DBC) sandwich structure with and without a baseplate. Most common failure mechanisms are reviewed, and methods to improve the power cycling lifetime of the power modules are presented. Power cycling curves are determined for a module with a lead-free solder by accelerated power cycling tests. A lifetime model is selected and the parameters are updated based on the power cycling test results. According to the measurements, the factor of improvement in the power cycling lifetime of modern IGBT power modules is greater than 10 during the last decade. Also, it is noticed that a 10 C increase in the chip temperature cycle amplitude decreases the lifetime by 40%. A thermal model for the chip temperature estimation is developed. The model is based on power loss estimation of the chip from the output current of the frequency converter. The model is verified with a purpose-built test equipment, which allows simultaneous measurement and simulation of the chip temperature with an arbitrary load waveform. The measurement system is shown to be convenient for studying the thermal behavior of the chip. It is found that the thermal model has a 5 C accuracy in the temperature estimation. The temperature cycles that the power semiconductor chip has experienced are counted by the rainflow algorithm. The counted cycles are compared with the experimentally verified power cycling curves to estimate the life consumption based on the mission profile of the drive. The methods are validated by the lifetime estimation of a power module in a direct-driven wind turbine. The estimated lifetime of the IGBT power module in a direct-driven wind turbine is 15 000 years, if the turbine is located in south-eastern Finland.

A Model-Based Development and Verification Framework for Distributed System-on-Chip Architecture

The capabilities and thus, design complexity of VLSI-based embedded systems have increased tremendously in recent years, riding the wave of Moore’s law. The time-to-market requirements are also shrinking, imposing challenges to the designers, which in turn, seek to adopt new design methods to increase their productivity. As an answer to these new pressures, modern day systems have moved towards on-chip multiprocessing technologies. New architectures have emerged in on-chip multiprocessing in order to utilize the tremendous advances of fabrication technology. Platform-based design is a possible solution in addressing these challenges. The principle behind the approach is to separate the functionality of an application from the organization and communication architecture of hardware platform at several levels of abstraction. The existing design methodologies pertaining to platform-based design approach don’t provide full automation at every level of the design processes, and sometimes, the co-design of platform-based systems lead to sub-optimal systems. In addition, the design productivity gap in multiprocessor systems remain a key challenge due to existing design methodologies. This thesis addresses the aforementioned challenges and discusses the creation of a development framework for a platform-based system design, in the context of the SegBus platform - a distributed communication architecture. This research aims to provide automated procedures for platform design and application mapping. Structural verification support is also featured thus ensuring correct-by-design platforms. The solution is based on a model-based process. Both the platform and the application are modeled using the Unified Modeling Language. This thesis develops a Domain Specific Language to support platform modeling based on a corresponding UML profile. Object Constraint Language constraints are used to support structurally correct platform construction. An emulator is thus introduced to allow as much as possible accurate performance estimation of the solution, at high abstraction levels. VHDL code is automatically generated, in the form of “snippets” to be employed in the arbiter modules of the platform, as required by the application. The resulting framework is applied in building an actual design solution for an MP3 stereo audio decoder application.

Reusable formal architectures for networked systems

Today's networked systems are becoming increasingly complex and diverse. The current simulation and runtime verification techniques do not provide support for developing such systems efficiently; moreover, the reliability of the simulated/verified systems is not thoroughly ensured. To address these challenges, the use of formal techniques to reason about network system development is growing, while at the same time, the mathematical background necessary for using formal techniques is a barrier for network designers to efficiently employ them. Thus, these techniques are not vastly used for developing networked systems. The objective of this thesis is to propose formal approaches for the development of reliable networked systems, by taking efficiency into account. With respect to reliability, we propose the architectural development of correct-by-construction networked system models. With respect to efficiency, we propose reusable network architectures as well as network development. At the core of our development methodology, we employ the abstraction and refinement techniques for the development and analysis of networked systems. We evaluate our proposal by employing the proposed architectures to a pervasive class of dynamic networks, i.e., wireless sensor network architectures as well as to a pervasive class of static networks, i.e., network-on-chip architectures. The ultimate goal of our research is to put forward the idea of building libraries of pre-proved rules for the efficient modelling, development, and analysis of networked systems. We take into account both qualitative and quantitative analysis of networks via varied formal tool support, using a theorem prover the Rodin platform and a statistical model checker the SMC-Uppaal.

SME internationalisation from a network perspective : an empirical study on a Finnish-Greek business network

The study examines the internationalisation process of a contemporary SME firm and explores the impact of its business network on this development. The objective of the study is to understand SME internationalisation and its dynamics from a network perspective. The purpose of this research project is to describe and explore the development process of a firm and its business network by identifying the changes, critical events and influence factors that form this development. It is a qualitative case study, which focuses on a Finnish focal firm and its respective business network as it expands into the Greek market. It is a longitudinal research process, which covers a period of time from 1994 to 2004. The empirical study concentrates on the paper trading and converting business. The study builds on the network theory and the framework provided by Johanson and Mattsson's (1988) model on network internationalisation. The incremental internationalisation theories and network theories form the theoretical focus. The research project is organised according to a process view. The focal firm evolves from a domestically-oriented small subsidiary into an internationally experienced company, which has activities in several market areas and numerous business networks in various market segments and product categories. The findings illustrate the importance of both the domestic and foreign business network context in a firm's internationalisation process. The results of the study suggest theoretical modifications on a firm's internationalisation process by broadening the perspective and incorporating the strategic context of a firm. The findings suggest that internationalisation process is a non-linear process, which does not have a deterministic order in its development. The findings emphasise the significance of relational networks, both managerial and entrepreneurial, for establishing position in foreign markets. It implies that a firm's evolution is significantly influenced by its business network and by critical events. Business networks gain coherence due to common goals and they use accumulated capabilities to exploit market opportunities. The business network sets constraints and provides opportunities, which makes the related decision making strategically important. The firm co-evolves with its business network. The research project provides an instrumental case study with a description of an SME internationalisation process. It contributes to existing knowledge by illustrating dynamics in an international business network and by pinpointing the importance of suppliers, customers, partners, ownerships and competition to the internationalisation process.

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.