Towards the automatic derivation of computer performance models from the real time and embedded systems design

Real Time and Embedded systems always have performance constraints either on response time or on throughput or on device utilisation rate. With conventional design methods these constraints are verified until the testing phase. No estimation of the variables on which the designer has specified some performance constraint is available before.In the frame of the Esprit II project COMPLEMENT, whose aim is to detect and fulfil the gaps between the different methods and tools that cover the whole design process of a real time and embedded system, an important effort is invested in including the use of performance modelling techniques very early in the development life-cycle in order to compute estimations of the performance criteria.The goal of this paper is to present some of the results obtained around the integration of performance evaluation modelling within design methods: the taxonomy of performance requirements to classify the types of performance constraints. the performance information model to bridge the gap between the design entities and the performance models, by introducing annotations to be able to run the derived models in order to provide the efficiency estimation of the system.

Heterogeneous-ISA multi-core architectures have emerged as a promising design paradigm given the ever-increasing demands on single threaded performance. Such architectures comprise multiple cores that differ not just in micro-architectural parameters (e.g., fetch width, ROB size) but also in their Instruction Set Architectures (ISAs). These architectures extract previously latent performance gains by executing different phases of the program on the core (and ISA) best suited to it, as opposed to executing the entire program on a single ISA. In such a computing paradigm, maximum performance is only extracted when we ensure that at every point in the program’s execution, the program runs on the core best suited to it. In this work, we propose a migration framework that practically and accurately decides when to migrate the program across different cores (and ISAs) to extract maximum performance gains. Under the covers, this framework combines a regression based performance modelling technique with a greedy scheduling algorithm. Our performance modelling technique leverages hardware performance counters prevalent in all major processors today to accurately estimate the performance of the program on different ISAs to within an error of 6%. Putting it together with our greedy scheduler enables our framework to achieve single thread performance speedups of 29.6% with respect to a baseline single ISA heterogeneous architecture.

Water jet machining (WJM) systems are quickly gaining wide industrial acceptance for cutting metallic and non-metallic materials in complex shapes. However, WJM systems are not used extensively by small-scale and medium-scale industries due to their high cost. There is no commercially available WJM system to meet the requirements of small-scale industries. In order to satisfy their demand, a low-cost first alpha-prototype WJM system has been previously developed using conventional design techniques. The intensifier, which is the key component of a WJM, is mainly responsible for the high cost. Therefore, this study concentrates on the redesign of the intensifier used in the prototype. Technical and economical requirements, as well as the main principle used on the double-acting intensifiers, constitute strong design constraints that do not permit drastic modifications using conventional design techniques. A novel redesign methodology, developed by Otto and Wood, provides systematic approach for the product development that matches customer needs. Therefore this methodology has been modified and used to improve the existing prototype. The methodology consists of a 10-step process with four primary phases. Most of the design enhancements on the components of the prototype WJM system have been achieved through the use of the redesign methodology compared with conventional design methodology.

Tightly-coupled (TC) fusion of Inertial Measurement Units (IMUs) with Global Navigation Satellite Systems (GNSSs) is a common technique that provides high-rate positioning even under GNSS interruptions. In order to provide accurate positioning, errors of IMU and GNSS must be modelled and estimated by filtering techniques such as Extended Kalman Filter (EKF). Due to nonlinearity and stochastic characteristics of IMU and GNSS system and measurement models, robust filter design has been a challenge. Conventional design techniques use mission-specific fixed models and trial-and-error noise parameter tuning to design IMU/GNSS filters. These conventional techniques are inflexible and do not always lead to accurate designs as there are no ways to verify the filter ability to estimate sensors errors accurately. To address this challenge, this paper presents a flexible design framework and a systematic procedure for TC IMU/GNSS fusion. The framework utilizes symbolic engines to represent and linearize system and measurement models. Symbolic engines are flexible in new models and fusion algorithms development. In order to evaluate the estimation of sensors errors, an Inverse-Kinematics module is developed to generate error-free sensors measurements which can be contaminated by known errors. The filter parameters are tuned using Genetic Algorithms and the performance is evaluated based on the accuracy of estimating all states including the added known errors. The framework has been used to develop a quaternion-based EKF design and verified on real raw IMU/GNSS data. The results showed that the developed framework greatly reduces efforts to design robust and accurate fusion systems for TC IMU/GNSS integration.

The situation of telecommunications systems is rapidly evolving towards a state characterized by the presence of a multitude of services integrated in a single network structure. In order to ease their integration, it is important to provide an unambiguous description of the organization, of the functionality, and of the relationships existing among services. Since it is not possible to completely foresee the situation of services in the future, the description should be modular, so that the task of adding new services to an existing environment is simplified. Formal description techniques are languages designed to handle such descriptions. Their goal is to produce correct and unambiguous specifications, understanding and modeling the system and the domain within which it operates. Their input is a set of required statements and a conceptual overview of the system. Their output is a formal representation that captures the functional behavior. On the other hand, the throughput of physical networks is constantly growing, reaching the order of Gbit/s. In the meantime, services needing high throughput, like multimedia conferencing systems are being designed, creating a need for flexible, high performance communication systems. An important feature of new high speed services is their increased need for guarantees. Therefore, the use of powerful performance modeling techniques becomes of prime importance. Their goal is to obtain some notion of how the system will perform under a given set of conditions. Performance evaluation theorists have long been using system specifications to make a heuristic model of the system and then an analysis of the model. When system specifications exist, the question arises whether a more direct path to performance analysis can be found. Our scope is to provide a methodology that fully and consistently integrates formal specification and performance evaluation. A problem is that many of the bottlenecks and impediments to smooth data flow have to do with implementation issues not directly dealt within the system specification itself. Therefore, prior to generating a performance model, the formal specification should be enhanced with the relevant non-functional information. It is essential to assure a smooth specification of the non-functional information. Thus, it is necessary to consistently add this information to the formal specification. Besides, the extended formal method should focus on conserving the semantics of the original one, and on providing a coherent extension of the semantics and syntax for the new concepts. Since all relevant required information is integrated within the formal extended representation, we provide a mapping technique that translates the extended formal representation into a performance modeling conserving the properties of the formal model. In parallel to the development of a performance model, the formal model can be validated and verified, and their implementation can be tested for conformance towards the original formal model. Finally, the performance modelling is implemented in a programming language, and then simulated. The results from simulation can be reused as inputs for the optimization of the formal specification (functional optimization) or the extended formal model (design optimization). To sum up, the goal of this work is to: Define extensions to current formal methods that allow to enhance the formal specification with performance modeling related information. Develop a method to translate the extended formal specification into a performance modeling. Develop rules and guidelines to automatically implement the performance modeling for the purpose of a performance evaluation (we use the commercial tool Opnet). Develop a consistent and coherent methodology for the integration of performance modeling and formal specification.

Resource Virtualization and Load Balancing are main objectives to reduce the power consumption and to improve the performance of large data centers (DC). The management of Cloud Data Centers (CDC) requires an accurate planning and an efficient use of system resources in order to save energy consumption (greening), to provide Quality of Service (QoS), and to meet negotiated Service Level Agreements (SLA). This contribution addresses the question of modeling and the development of generic queuing models for energy-efficient use of resources for dynamic load balancing in virtualized CDCs. Performance models are developed for energy efficiency through automatic Server Consolidation, Dynamic Voltage and Frequency Scaling (DVFS) under Static Load Balancing; Dynamic Load Balancing can be achieved through Virtual Machine (VM) migrations. The analysis of such models provides quantitative performance figures upon which the system operation can be optimized with respect to guaranteed real-time performance and energy efficiency under prescribed SLAs.

Organic materials hold considerable promise for thermoelectric applications, particularly in flexible devices, due to their pliable and lightweight nature. Recent progress in this domain has been fueled by enhancements in organic thermoelectric materials and more efficient device designs. This review offers a comprehensive overview of these advancements. It begins by detailing the evolution and performance optimization of high-efficiency organic thermoelectric materials, emphasizing both chemical and physical modifications. The review also delves into innovative design strategies for flexible devices, covering new structural approaches, performance modeling, and thermal management techniques. Moreover, it examines advanced manufacturing processes like 3D printing and thin-film deposition. To highlight global trends and challenges, the review integrates findings from top research institutions. The review projects future breakthroughs in material development, characterization techniques, and device optimization, particularly focusing on advances in materials such as PEDOT:PSS and PANI. It underscores strategies to boost conductivity and the Seebeck coefficient. Remarkably, innovative device designs have substantially enhanced energy conversion efficiency, while numerical simulations have improved output voltage and power density. Furthermore, cutting-edge manufacturing technologies like 3D printing and solution processing have facilitated the scalable production of intricate structures. In summary, these collective advancements drive high-performance, cost-effective, and sustainable thermoelectric technologies for diverse applications, including wearable electronics, energy harvesting, and thermal management.

Serverless computing brings another revolution to cloud computing as function-as-a-service (FaaS) where the applications are abstracted as a group of functions. Serverless applications are cost-effective and manage resources efficiently but the lack of performance modeling and energy optimization affects the potential users' broad adoption of serverless computing. Performance enhancement and energy optimization are necessary to guarantee the serverless applications' service level agreement (SLA). This review paper presents various performance metrics in serverless computing, including cost, scalability, latency, energy consumption, resource utilization, fault tolerance, and response time. Based on these metrics, various performance modeling and energy optimization techniques have been explored to reduce energy consumption and improve system efficiency. Furthermore, the review investigates software platforms for implementing serverless computing, including AWS Lambda, Apache OpenWhisk, Azure Functions, and Google Cloud Functions, highlighting key findings and limitations. This comprehensive review serves as a guide for researchers, directing them toward new and promising research directions in the field.

To support the portability of efficiency when bringing an application from scientific computing to a new HPC system, autotuning techniques are promising approaches. Ideally, these approaches are able to derive an efficient implementation for a specific HPC system by applying suitable program transformations. Often, a large number of implementations results, and the most efficient of these variants should be selected. In this article, we investigate performance modelling and prediction techniques which can support the selection process. These techniques may significantly reduce the selection effort, compared to extensive runtime tests. We apply the execution-cache-memory (ECM) performance model to numerical solution methods for ordinary differential equations (ODEs). In particular, we consider the question whether it is possible to obtain a performance prediction for the resulting implementation variants to support the variant selection. We investigate the accuracy of the prediction for different ODEs and different hardware platforms and show that the prediction is able to reliably select a set of fast variants and, thus, to limit the search space for possible later empirical tuning.

PurposeThe generic design environment for a flexible printed‐circuit board assemblies (PCBA) remanufacturing cell contains four interrelated complex design domains. Mechanical design domains are really complex and the use of well‐proven mechanical product design methodologies does not help the designer. Hence, this paper aims to develop a generic systematic design methodology for a flexible PCBA remanufacturing cell.Design/methodology/approachThe study investigates the use of conventional mechanical product design techniques for the design of a flexible PCBA rework (remanufacturing) cell. It indicates problems and the weaknesses when conventional product design techniques are used for the development of flexible manufacturing systems (FMS). It then provides a new systematic mechanical design methodology for designing a flexible PCBA rework (remanufacturing) cell. The design methodology is intended to be generic in order to apply successfully to any FMS design.FindingsConventional product design methodology cannot be used directly for the design of a flexible PCBA remanufacturing cell. Hence, two design methodologies were developed: the generic FMS mechanical design methodology and a specific FMS design methodology for a PCBA rework cell. The first one was developed based on the tasks of the conventional product design process integrated with new design tools. The generic design methodology was then extended to obtain the second methodology for a PCBA rework cell design. Both of the methodologies were applied to a flexible PCBA rework cell design problem. Both design methodologies eliminated unusable design solutions at the early design stages of the conceptual design process and made the design process easier.Practical implicationsThe generic and specific design methodologies provide a better design environment, even for less specialized FMS designers.Originality/valueThe design methodologies may help for the commercialization of a flexible PCBA remanufacturing cell that may be used for SM rework and assembly.

Statecharts are a graphical representation to model reactive systems that respond to external or internal stimuli by changing the state of a given system. Statecharts can be seen as an extension of state-transition diagrams that allows modeling hierarchy, orthogonality, and interdependence. Due to their features to represent reactive systems, Statecharts have been adapted to represent and deal analytically with performance models (reactive systems whose performance is to be evaluated). An interesting feature present in Statecharts is to record the system's state, which cannot be represented in Markov models in a straightforward manner due to its "memory-less" property. The contributions of this paper are: show that Statecharts are a feasible alternative to specify a reactive system so that its performance can be evaluated by both analytical and simulation techniques; show that the inclusion of the memory representation in the Statecharts specification can indeed be made by both analytical and simulation techniques. The results of a case study of a manufacturing system show that the objectives are achieved.

Shrinking feature sizes, reduced voltages, and higher transistor count of nano-scale silicon chips challenge designers in terms of performance, power consumption, and reliability. This paper investigates the effect of simultaneous use of dynamic voltage and frequency scaling (DVFS) and body biasing (BB) on power consumption, reliability, and performance. An analytical model of reliability as a function of body bias voltage, supply voltage, and frequency is proposed. We derive a three dimensional optimization problem by exploiting proposed reliability model in conjunction with power consumption and performance model. The resulting problem is solved using widely-used geometric optimization to identify optimal supply voltage and body bias voltage and then is validated using accurate simulation. Afterwards, it is demonstrated how joint energy-performance-reliability space optimization method can be used in an adaptive reliability-aware power management systems. Finally, we show that combined soft error aware BB and DVFS is capable of improving power consumption about 30% in comparison to reliability-aware DVFS only for the same level of reliability and performance constraints.

Optimizing processors for specific application(s) can substantially improve energy-efficiency. With the end of Dennard scaling, and the corresponding reduction in energyefficiency gains from technology scaling, such approaches may become increasingly important. However, designing applicationspecific processors require fast design space exploration tools to optimize for the targeted application(s). Analytical models can be a good fit for such design space exploration as they provide fast performance estimations and insight into the interaction between an application's characteristics and the micro-architecture of a processor. Unfortunately, current analytical models require some microarchitecture dependent inputs, such as cache miss rates, branch miss rates and memory-level parallelism. This requires profiling the applications for each cache and branch predictor configuration, which is far more time-consuming than evaluating the actual performance models. In this work we present a micro-architecture independent profiler and associated analytical models that allow us to produce performance and power estimates across a large design space almost instantaneously. We show that using a micro-architecture independent profile leads to a speedup of 25× for our evaluated design space, compared to an analytical model that uses micro-architecture dependent profiles. Over a large design space, the model has a 13% error for performance and a 7% error for power, compared to cycle-level simulation. The model is able to accurately determine the optimal processor configuration for different applications under power or performance constraints, and it can provide insight into performance through cycle stacks.

ABSTRACTBuilding envelope has a pivotal role in adequate thermal comfort of occupants in the indoor environment. Recent research has been focused on innovative techniques to enhance building performance. Among them, the integration of phase change materials (PCMs) in building envelopes has proven to be promising. Phase change materials have the potential to tune the temperature around their melting point. In addition, the latent heat of phase transition provides high storage capacity compared to plain envelope structures. The current paper provides a comprehensive review on PCM inclusion in building walls, roofs, and floors. It highlights the main governing performance parameters, incorporation methods, modeling techniques, and thermal performance assessment of the systems. Detailed analysis of the results is presented. It includes the effect of PCM inclusion on cooling/heating load reduction, indoor thermal comfort conditions, and energy saving. PCM inclusion was found to reduce building loads by up to 30%. They have also shown a potential of maintaining indoor temperature fluctuation within as low as 2°C. The listed papers cover the recent few decades and span through locations with different climate conditions. The majority of reported work was in Europe and Asia as they are leading in their sustainability goals. In adverse climates like North America, scarce research was reported as the large temperature variation is not favorable for PCM integration. The paper is intended to be a guide for researchers working in the field of PCM integration in building applications. It covers the most recent advances, potentials, and challenges of different integration techniques.

Summary Steam-assisted gravity drainage is the method of choice to extract bitumen from Athabasca oil-sand reservoirs in Western Canada. Under reservoir conditions, bitumen is immobile because of high viscosity, and its typically high level of saturation limits the injectivity of steam. In current industry practice, steam is circulated within injection and production wells. Operators keep the steam circulating until mobile bitumen breaks through the producer and communication is established between the injector and the producer. The “startup” phase is a time-consuming process taking three or more months with no oil production. A variety of processes could be used to minimize the length of the startup phase, such as electromagnetic (EM) heating in either the induction (medium frequency) or radio-frequency ranges. Knowledge of the size of the hot zone formed by steam circulation and of the benefits of simultaneous EM-heating techniques increases understanding of the startup process and helps to minimize startup duration. The aim of the present work is to introduce an analytical model to predict startup duration for steam circulation with and without EM heating. Results reveal that resistive (electrothermal) heating with/without brine injection cannot be a preferable method for mobilizing the bitumen in startup phase. Induction slightly decreases startup time at frequencies smaller than 10 kHz, and at 100 kHz it can reduce startup time to less than two months.