Rainer Leupers – författare

Customizable processors have been described as the next natural step in the evolution of the microprocessor business: a step in the life of a new technology where top performance alone is no longer sufficient to guarantee market success. Other factors become fundamental, such as time to market, convenience, energy efficiency, and ease of customization. This book is the first to explore comprehensively one of the most fundamental trends which emerged in the last decade: to treat processors not as rigid, fixed entities, which designers include "as is� in their products; but rather, to build sound methodologies to tailor-fit processors to the specific needs of such products. This book addresses the goal of maintaining a very large family of processors, with a wide range of features, at a cost comparable to that of maintaining a single processor. First book to present comprehensively the major ASIP design methodologies and tools without any particular bias Written by most of the pioneers and top international experts of this young domain Unique mix of management perspective, technical detail, research outlook, and practical implementation

It is well known that embedded systems have to be implemented efficiently. This requires that processors optimized for certain application domains are used in embedded systems. Such an optimization requires a careful exploration of the design space, including a detailed study of cost/performance tradeoffs. In order to avoid time-consuming assembly language programming during design space exploration, compilers are needed. In order to analyze the effect of various software or hardware configurations on the performance, retargetable compilers are needed that can generate code for numerous different potential hardware configurations. This book provides a comprehensive and up-to-date overview of the fast developing area of retargetable compilers for embedded systems. It describes a large set important tools as well as applications of retargetable compilers at different levels in the design flow. Retargetable Compiler Technology for Embedded Systems is mostly self-contained and requires only fundamental knowledge in software and compiler design. It is intended to be a key reference for researchers and designers working on software, compilers, and processor optimization for embedded systems.

The building blocks of today's and future embedded systems are complex intellectual property components, or cores, many of which are programmable processors. Traditionally, these embedded processors mostly have been pro­ grammed in assembly languages due to efficiency reasons. This implies time­ consuming programming, extensive debugging, and low code portability. The requirements of short time-to-market and dependability of embedded systems are obviously much better met by using high-level language (e.g. C) compil­ ers instead of assembly. However, the use of C compilers frequently incurs a code quality overhead as compared to manually written assembly programs. Due to the need for efficient embedded systems, this overhead must be very low in order to make compilers useful in practice. In turn, this requires new compiler techniques that take the specific constraints in embedded system de­ sign into account. An example are the specialized architectures of recent DSP and multimedia processors, which are not yet sufficiently exploited by existing compilers.

The market for consumer electronics is characterized by rapidly growing complexities of applications and decreasing market window opportunities. A key concept for coping with such requirements is the reuse of system components. Embedding programmable processors into VLSI systems facilitates reuse and offers a high degree of flexibility. The use of embedded processors, however, poses challenges for software compilers, because real-time constraints and limited silicon area for program memories demand extremely efficient machine code. Additionally there is a need for flexible, retargetable compilers which explore the mutual dependence between processor architectures and program execution speed. Current compiler technology does not meet these demands, particularly the area of DSP where application-specific processors are predominant. As a consequence, the largest part of DSP software is still developed manually at assembly language level. Recent research efforts, located at the intersection of software and hardware design, aim at eliminating this bottleneck.Retargetable Code Generation for Digital Signal Processors outlines the new role of compilers in hardware/software codesign of embedded systems, and it describes the state-of-the-art in the area of retargetable code generation and optimization for embedded DSPs. It presents concepts and algorithmic solutions, which achieve both retargetability and high code quality. In contrast to approaches taken in classical compiler construction, emphasis is put on effective code optimization instead of high compilation speed. The usefulness of the proposed techniques is demonstrated for real-life architectures. This volume presents an integrated solution for retargetable DSP compilers. It covers the whole compilation process, including target processor modelling, intermediate code generation, code selection, register allocation, scheduling and optimization for parallelism. It should be of interest to researchers, senior design engineers and CAD managers both in academia and industry.

We are presently observing a paradigm change in designing complex SoC as it occurs roughly every twelve years due to the exponentially increasing number of transistors on a chip. This design discontinuity, as all previous ones, is characterized by a move to a higher level of abstraction. This is required to cope with the rapidly increasing design costs. While the present paradigm change shares the move to a higher level of abstraction with all previous ones, there exists also a key difference. For the ?rst time shrinking geometries do not leadtoacorrespondingincreaseofperformance. InarecenttalkLisaSuofIBM pointed out that in 65nm technology only about 25% of performance increase can be attributed to scaling geometries while the lion share is due to innovative processor architecture [1]. We believe that this fact will revolutionize the entire semiconductor industry. What is the reason for the end of the traditional view of Moore’s law? It is instructive to look at the major drivers of the semiconductor industry: wireless communications and multimedia. Both areas are characterized by a rapidly increasingdemandofcomputationalpowerinordertoprocessthesophisticated algorithmsnecessarytooptimallyutilizethepreciousresourcebandwidth. The computational power cannot be provided by traditional processor architectures and shared bus type of interconnects. The simple reason for this fact is energy ef?ciency: there exist orders of magnitude between the energy ef?ciency of an algorithm implemented as a ?xed functionality computational element and of a software implementation on a processor.

New software tools and a sophisticated methodology above RTL are required to answer the challenges of designing an optimized application specific processor (ASIP). This book offers an automated and fully integrated implementation flow and compares it to common implementation practice. Case-studies emphasise that neither the architectural advantages nor the design space of ASIPs are sacrificed for an automated implementation. Realizing a building block which fulfils the requirements on programmability and computational power is now efficiently possible for the first time.Optimized ASIP Synthesis from Architecture Description Language Models inspires hardware designers as well as application engineers to design powerful ASIPs that will make their SoC designs unique.

Today more than 90 per cent of all programmable processors are employed in embedded systems. This number is actually not surprising, contemplating that in a typical home you might find one or two PCs equipped with high-performance standard processors, and probably dozens of embedded systems, including electronic entertainment, household, and telecom devices, each of them equipped with one or more embedded processors. The question arises why programmable processors are so popular in embedded system design. The answer lies in the fact that they help to narrow the gap between chip capacity and designer productivity. Embedded processors cores are nothing but one step further towards improved design reuse, just along the lines of standard cells in logic synthesis and macrocells in RTL synthesis in earlier times of IC design. Additionally, programmable processors permit to migrate functionality from hardware to software, resulting in an even improved reuse factor as well as greatly increased flexibility.The LISA processor design platform (LPDP) presented in Architecture Exploration for Embedded Processors with LISA addresses recent design challenges and results in highly satisfactory solutions. The LPDP covers all major high-level phases of embedded processor design and is capable of automatically generating almost all required software development tools from processor models in the LISA language. It supports a profiling-based, stepwise refinement of processor models down to cycle-accurate and even RTL synthesis models. Moreover, it elegantly avoids model inconsistencies otherwise omnipresent in traditional design flows.

Computerarchitecturepresentlyfacesanunprecedentedrevolution: Thestep from monolithic processors towards multi-core ICs, motivated by the ever - creasingneedforpowerandenergyef ciencyinnanoelectronics. Whetheryou prefer to call it MPSoC (multi-processor system-on-chip) or CMP (chip mul- processor), no doubt this revolution affects large domains of both computer science and electronics, and it poses many new interdisciplinary challenges. For instance, ef cient programming models and tools for MPSoC are largely an open issue: "Multi-core platforms are a reality - but where is the software support" (R. Lauwereins, IMEC). Solving it will require enormous research efforts as well as the education of a whole new breed of software engineers that bring the results from universities into industrial practice. Atthesametime,thedesignofcomplexMPSoCarchitecturesisanextremely time-consuming task, particularly in the wireless and multimedia application domains, where heterogeneous architectures are predominant.Due to the - ploding NRE and mask costs most companies are now following a platform approach: Invest a large (but one-time) design effort into a proper core - chitecture, and create easy-to-design derivatives for new standards or product features. Needless to say, only the most ef cient MPSoC platforms have a real chance to enjoy a multi-year lifetime on the highly competitive semiconductor market for embedded systems.

Increasing complexity of modern embedded systems demands system designers to ramp up their design productivity without compromising performance goals. This is promoted by modern Electronic System Level (ESL) techniques. Language-driven Exploration and Implementation of Partially Re-configurable ASIPs addresses an important segment of the ESL area by modeling partially re-configurable processors via high-level Architecture Description Language (ADL). This approach also hints an imminent evolution in the area of re-configurable system design.

1. 1 Motivation Digital information technology has revolutionized the world during the last few decades. Todayabout98%ofprogrammabledigitaldevicesareactuallyembedded [132]. Theseembeddedsystemshavebecomethemainapplicationareaofinfor- tiontechnologyhardwareandarethebasistodeliverthesophisticatedfunctionality of today's technical devices. As shown in Fig. 1. 1(a), current forecasts predict a worldwideembeddedsystemmarketof$88billionin2009. Millions of Gates 40 25% 300 2004 35 Available Gates 2009 250 20% Used Gates AAGR% 30 200 Design Productivity Gap 25 15% Design Productivity Gap 20 150 10% 15 100 10 5% 50 32 55 25 50 5 20 47 43 10 8 123 0,8 0 0 0% 1993 1995 1997 1999 2001 2003 2005 America Europe Japan Asia-Pacific (a) Global embedded systems revenue and (b) Crisis of complexity [217] average annual growth rate(AAGR) [103] Fig. 1. 1 Embeddedsystemdesign Overthepastfewyears,theever-increasingcomplexityandperformancerequi- mentsofnewwirelesscommunications,automotiveandconsumerelectronicsapp- cations are changing the way embedded systems are designed and implemented today. InconformitywithMoore'slaw[99],onedrivingforceistherapidprogress in deep-submicron process technologies.Chip designers and manufacturers have constantly pushed the envelope of technological and physical constraints. In fact, designers have more gates at their disposal than ever before. However, current M. Hohenauer,R. Leupers, C Compilers for ASIPs, 1 DOI10. 1007/978-1-4419-1176-6 1, C SpringerScience+BusinessMedia,LLC2010 $Billions 2 1 Introduction mainstream-embeddedsystemdesignsarenotusingatleast50%ofthesiliconarea availabletothem(Fig. 1. 1(b)). Thegrowthindesigncomplexitythreatenstooutpace thedesigner'sproductivity,onaccountofunmanageabledesignsizesandtheneed formoredesigniterationsduetodeep-submicroneffects. Thisphenomenonisalso referredtoas crisis of complexity[103]andcomesalongwithexponentiallygr- ing non-recurring engineering (NRE) costs (Fig. 1. 2) to design and manufacture chips. Understandably,thesecostsonlyamortizeforverylargevolumesorhigh-end products. $100. 000. 000. 000,00 $10. 000. 000. 000,00 $1. 000. 000. 000,00 $100. 000. 000,00 RTL Methodology Future Improvements $10. 000. 000,00 1990 1995 2000 2005 2010 2015 Fig. 1.

It is well known that embedded systems have to be implemented efficiently. This requires that processors optimized for certain application domains are used in embedded systems. Such an optimization requires a careful exploration of the design space, including a detailed study of cost/performance tradeoffs. In order to avoid time-consuming assembly language programming during design space exploration, compilers are needed. In order to analyze the effect of various software or hardware configurations on the performance, retargetable compilers are needed that can generate code for numerous different potential hardware configurations. This book provides a comprehensive and up-to-date overview of the fast developing area of retargetable compilers for embedded systems. It describes a large set important tools as well as applications of retargetable compilers at different levels in the design flow. Retargetable Compiler Technology for Embedded Systems is mostly self-contained and requires only fundamental knowledge in software and compiler design. It is intended to be a key reference for researchers and designers working on software, compilers, and processor optimization for embedded systems.

The building blocks of today's and future embedded systems are complex intellectual property components, or cores, many of which are programmable processors. Traditionally, these embedded processors mostly have been pro­ grammed in assembly languages due to efficiency reasons. This implies time­ consuming programming, extensive debugging, and low code portability. The requirements of short time-to-market and dependability of embedded systems are obviously much better met by using high-level language (e.g. C) compil­ ers instead of assembly. However, the use of C compilers frequently incurs a code quality overhead as compared to manually written assembly programs. Due to the need for efficient embedded systems, this overhead must be very low in order to make compilers useful in practice. In turn, this requires new compiler techniques that take the specific constraints in embedded system de­ sign into account. An example are the specialized architectures of recent DSP and multimedia processors, which are not yet sufficiently exploited by existing compilers.

The market for consumer electronics is characterized by rapidly growing complexities of applications and decreasing market window opportunities. A key concept for coping with such requirements is the reuse of system components. Embedding programmable processors into VLSI systems facilitates reuse and offers a high degree of flexibility. The use of embedded processors, however, poses challenges for software compilers, because real-time constraints and limited silicon area for program memories demand extremely efficient machine code. Additionally there is a need for flexible, retargetable compilers which explore the mutual dependence between processor architectures and program execution speed. Current compiler technology does not meet these demands, particularly the area of DSP where application-specific processors are predominant. As a consequence, the largest part of DSP software is still developed manually at assembly language level. Recent research efforts, located at the intersection of software and hardware design, aim at eliminating this bottleneck.Retargetable Code Generation for Digital Signal Processors outlines the new role of compilers in hardware/software codesign of embedded systems, and it describes the state-of-the-art in the area of retargetable code generation and optimization for embedded DSPs. It presents novel concepts and algorithmic solutions, which achieve both retargetability and high code quality. In contrast to approaches taken in classical compiler construction, emphasis is put on effective code optimization instead of high compilation speed. The usefulness of the proposed techniques is demonstrated for real-life architectures. Retargetable Code Generation for Digital Signal Processors, with a foreword by Peter Marwedel, is the first contribution to this area, that presents an integrated solution for retargetable DSP compilers. It covers the whole compilation process, including target processor modelling, intermediate code generation, code selection, register allocation, scheduling and optimization for parallelism. It will be of interest to researchers, senior design engineers and CAD managers both in academia and industry.

Already today more than 90% of all programmable processors are employed in embedded systems. This number is actually not surprising, contemplating that in a typical home you might find one or two PCs equipped with high­ of embedded systems, performance standard processors, but probably dozens including electronic entertainment, household, and telecom devices, each of them equipped with one or more embedded processors. Moreover, the elec­ tronic components of upper-class cars incorporate easily over one hundred pro­ cessors. Hence, efficient embedded processor design is certainly an area worth looking at. The question arises why programmable processors are so popular in embed­ ded system design. The answer lies in the fact that they help to narrow the gap between chip capacity and designer productivity. Embedded processors cores are nothing but one step further towards improved design reuse, just along the lines of standard cells in logic synthesis and macrocells in RTL synthesis in earlier times of IC design. Additionally, programmable processors permit to migrate functionality from hardware to software, resulting in an even improved reuse factor as well as greatly increased flexibility.

Simulation of computer architectures has made rapid progress recently. The primary application areas are hardware/software performance estimation and optimization as well as functional and timing verification. Recent, innovative technologies such as retargetable simulator generation, dynamic binary translation, or sampling simulation have enabled widespread use of processor and system-on-chip (SoC) simulation tools in the semiconductor and embedded system industries. Simultaneously, processor and SoC simulation is still a very active research area, e.g. what amounts to higher simulation speed, flexibility, and accuracy/speed trade-offs. This book presents and discusses the principle technologies and state-of-the-art in high-level hardware architecture simulation, both at the processor and the system-on-chip level.

It gives me immense pleasure to introduce this timely handbook to the research/- velopment communities in the ?eld of signal processing systems (SPS). This is the ?rst of its kind and represents state-of-the-arts coverage of research in this ?eld. The driving force behind information technologies (IT) hinges critically upon the major advances in both component integration and system integration. The major breakthrough for the former is undoubtedly the invention of IC in the 50’s by Jack S. Kilby, the Nobel Prize Laureate in Physics 2000. In an integrated circuit, all components were made of the same semiconductor material. Beginning with the pocket calculator in 1964, there have been many increasingly complex applications followed. In fact, processing gates and memory storage on a chip have since then grown at an exponential rate, following Moore’s Law. (Moore himself admitted that Moore’s Law had turned out to be more accurate, longer lasting and deeper in impact than he ever imagined. ) With greater device integration, various signal processing systems have been realized for many killer IT applications. Further breakthroughs in computer sciences and Internet technologies have also catalyzed large-scale system integration. All these have led to today’s IT revolution which has profound impacts on our lifestyle and overall prospect of humanity. (It is hard to imagine life today without mobiles or Internets!) The success of SPS requires a well-concerted integrated approach from mul- ple disciplines, such as device, design, and application.

This book gives a comprehensive introduction to the design challenges of MPSoC platforms, focusing on early design space exploration. It defines an iterative methodology to increase the abstraction level so that evaluation of design decisions can be performed earlier in the design process. These techniques enable exploration on the system level before undertaking time- and cost-intensive development.

This book introduces a novel design methodology which can significantly reduce the ASIP development effort through high degrees of design automation. The key elements of this new design methodology are a powerful application profiler and an automated instruction-set customization tool which considerably lighten the burden of mapping a target application to an ASIP architecture in the initial design stages. The book includes several design case studies with real life embedded applications to demonstrate how the methodology and the tools can be used in practice for accelerating the overall ASIP design process.

This book gives a comprehensive introduction to the design challenges of MPSoC platforms, focusing on early design space exploration. It defines an iterative methodology to increase the abstraction level so that evaluation of design decisions can be performed earlier in the design process. These techniques enable exploration on the system level before undertaking time- and cost-intensive development.

1. 1 Motivation Digital information technology has revolutionized the world during the last few decades. Todayabout98%ofprogrammabledigitaldevicesareactuallyembedded [132]. Theseembeddedsystemshavebecomethemainapplicationareaofinfor- tiontechnologyhardwareandarethebasistodeliverthesophisticatedfunctionality of today's technical devices. As shown in Fig. 1. 1(a), current forecasts predict a worldwideembeddedsystemmarketof$88billionin2009. Millions of Gates 40 25% 300 2004 35 Available Gates 2009 250 20% Used Gates AAGR% 30 200 Design Productivity Gap 25 15% Design Productivity Gap 20 150 10% 15 100 10 5% 50 32 55 25 50 5 20 47 43 10 8 123 0,8 0 0 0% 1993 1995 1997 1999 2001 2003 2005 America Europe Japan Asia-Pacific (a) Global embedded systems revenue and (b) Crisis of complexity [217] average annual growth rate(AAGR) [103] Fig. 1. 1 Embeddedsystemdesign Overthepastfewyears,theever-increasingcomplexityandperformancerequi- mentsofnewwirelesscommunications,automotiveandconsumerelectronicsapp- cations are changing the way embedded systems are designed and implemented today. InconformitywithMoore'slaw[99],onedrivingforceistherapidprogress in deep-submicron process technologies.Chip designers and manufacturers have constantly pushed the envelope of technological and physical constraints. In fact, designers have more gates at their disposal than ever before. However, current M. Hohenauer,R. Leupers, C Compilers for ASIPs, 1 DOI10. 1007/978-1-4419-1176-6 1, C SpringerScience+BusinessMedia,LLC2010 $Billions 2 1 Introduction mainstream-embeddedsystemdesignsarenotusingatleast50%ofthesiliconarea availabletothem(Fig. 1. 1(b)). Thegrowthindesigncomplexitythreatenstooutpace thedesigner'sproductivity,onaccountofunmanageabledesignsizesandtheneed formoredesigniterationsduetodeep-submicroneffects. Thisphenomenonisalso referredtoas crisis of complexity[103]andcomesalongwithexponentiallygr- ing non-recurring engineering (NRE) costs (Fig. 1. 2) to design and manufacture chips. Understandably,thesecostsonlyamortizeforverylargevolumesorhigh-end products. $100. 000. 000. 000,00 $10. 000. 000. 000,00 $1. 000. 000. 000,00 $100. 000. 000,00 RTL Methodology Future Improvements $10. 000. 000,00 1990 1995 2000 2005 2010 2015 Fig. 1.

Simulation of computer architectures has made rapid progress recently. The primary application areas are hardware/software performance estimation and optimization as well as functional and timing verification. Recent, innovative technologies such as retargetable simulator generation, dynamic binary translation, or sampling simulation have enabled widespread use of processor and system-on-chip (SoC) simulation tools in the semiconductor and embedded system industries. Simultaneously, processor and SoC simulation is still a very active research area, e.g. what amounts to higher simulation speed, flexibility, and accuracy/speed trade-offs. This book presents and discusses the principle technologies and state-of-the-art in high-level hardware architecture simulation, both at the processor and the system-on-chip level.

This book introduces a novel design methodology which can significantly reduce the ASIP development effort through high degrees of design automation. The key elements of this new design methodology are a powerful application profiler and an automated instruction-set customization tool which considerably lighten the burden of mapping a target application to an ASIP architecture in the initial design stages. The book includes several design case studies with real life embedded applications to demonstrate how the methodology and the tools can be used in practice for accelerating the overall ASIP design process.

This book describes a flexible and largely automated methodology for adding the estimation of power consumption to high level simulations at the electronic system level (ESL). This method enables the inclusion of power consumption considerations from the very start of a design. This ability can help designers of electronic systems to create devices with low power consumption.  The authors also demonstrate the implementation of the method, using the popular ESL language “SystemC”. This implementation enables most existing SystemC ESL simulations for power estimation with very little manual work. Extensive case-studies of a Network on Chip communication architecture and a dual-core application processor “ARM Cortex-A9” showcase the applicability and accuracy of the method to different types of electronic devices. The evaluation compares various trade-offs regarding amount of manual work, types of ESL models, achieved estimation accuracy and impact on the simulation speed.Describes a flexible and largely automated ESL power estimation method;Shows implementation of power estimation methodology in SystemC;Uses two extensive case studies to demonstrate method introduced.

In this new edition of the Handbook of Signal Processing Systems, many of the chapters from the previous editions have been updated, and several new chapters have been added. The new contributions include chapters on signal processing methods for light field displays, throughput analysis of dataflow graphs, modeling for reconfigurable signal processing systems, fast Fourier transform architectures, deep neural networks, programmable architectures for histogram of oriented gradients processing, high dynamic range video coding, system-on-chip architectures for data analytics, analysis of finite word-length effects in fixed-point systems, and models of architecture. There are more than 700 tables and illustrations; in this edition over 300 are in color.This new edition of the handbook is organized in three parts. Part I motivates representative applications that drive and apply state-of-the art methods for design and implementation of signal processing systems; Part II discusses architectures for implementing these applications; and Part III focuses on compilers, as well as models of computation and their associated design tools and methodologies.

This book can be used as a reference for beginners and experts alike who wish to dive into the world of logic locking, thereby having a holistic view of the entire infrastructure required to design, evaluate, and deploy modern locking policies.

This book can be used as a reference for beginners and experts alike who wish to dive into the world of logic locking, thereby having a holistic view of the entire infrastructure required to design, evaluate, and deploy modern locking policies.

Eine subtile Veränderung, die zu katastrophalen Folgen führt - Hardware-Trojaner stellen zweifellos eine der größten Sicherheitsbedrohungen des modernen Zeitalters dar. Wie kann die Hardware vor diesen bösartigen Veränderungen geschützt werden? Eine mögliche Lösung verbirgt sich im Logic Locking, einer bekannten Technik zur Verschleierung von Hardware. In diesem Buch gehen wir Schritt für Schritt vor, um Logic Locking zu verstehen, von seiner grundlegenden Mechanik über die Implementierung in Software bis hin zu einer eingehenden Analyse der Sicherheitseigenschaften im Zeitalter des maschinellen Lernens. Dieses Buch kann als Nachschlagewerk sowohl für Anfänger als auch für Experten verwendet werden, die in die Welt des logischen Sperrens eintauchen wollen und dabei einen ganzheitlichen Überblick über die gesamte Infrastruktur erhalten möchten, die für den Entwurf, die Bewertung und den Einsatz moderner Sperrstrategien erforderlich ist.

This book explores the reliability and security challenges of Computing-in-Memory (CIM), a promising approach to overcoming the limitations of traditional computing. It examines the weaknesses of memristive devices, which are key to this technology, and presents practical methods to improve their stability and security. Key topics include a fault injection platform for testing reliability, the NeuroHammer attack, which exposes security risks, and the NeuroBreakoutBoard, a hardware tool for evaluating real devices. By bridging theory and practice, this book is essential for researchers, engineers, and industry professionals working on next-generation computing systems.