Leakage temperature dependency aware real-time scheduling for power and thermal optimization

Catering to society's demand for high performance computing, billions of transistors are now integrated on IC chips to deliver unprecedented performances. With increasing transistor density, the power consumption/density is growing exponentially. The increasing power consumption directly translates to the high chip temperature, which not only raises the packaging/cooling costs, but also degrades the performance/reliability and life span of the computing systems. Moreover, high chip temperature also greatly increases the leakage power consumption, which is becoming more and more significant with the continuous scaling of the transistor size. As the semiconductor industry continues to evolve, power and thermal challenges have become the most critical challenges in the design of new generations of computing systems. ^ In this dissertation, we addressed the power/thermal issues from the system-level perspective. Specifically, we sought to employ real-time scheduling methods to optimize the power/thermal efficiency of the real-time computing systems, with leakage/ temperature dependency taken into consideration. In our research, we first explored the fundamental principles on how to employ dynamic voltage scaling (DVS) techniques to reduce the peak operating temperature when running a real-time application on a single core platform. We further proposed a novel real-time scheduling method, “M-Oscillations” to reduce the peak temperature when scheduling a hard real-time periodic task set. We also developed three checking methods to guarantee the feasibility of a periodic real-time schedule under peak temperature constraint. We further extended our research from single core platform to multi-core platform. We investigated the energy estimation problem on the multi-core platforms and developed a light weight and accurate method to calculate the energy consumption for a given voltage schedule on a multi-core platform. Finally, we concluded the dissertation with elaborated discussions of future extensions of our research. ^

Real-time scheduling of embedded applications on multi-core platforms

For the past several decades, we have experienced the tremendous growth, in both scale and scope, of real-time embedded systems, thanks largely to the advances in IC technology. However, the traditional approach to get performance boost by increasing CPU frequency has been a way of past. Researchers from both industry and academia are turning their focus to multi-core architectures for continuous improvement of computing performance. In our research, we seek to develop efficient scheduling algorithms and analysis methods in the design of real-time embedded systems on multi-core platforms. Real-time systems are the ones with the response time as critical as the logical correctness of computational results. In addition, a variety of stringent constraints such as power/energy consumption, peak temperature and reliability are also imposed to these systems. Therefore, real-time scheduling plays a critical role in design of such computing systems at the system level. We started our research by addressing timing constraints for real-time applications on multi-core platforms, and developed both partitioned and semi-partitioned scheduling algorithms to schedule fixed priority, periodic, and hard real-time tasks on multi-core platforms. Then we extended our research by taking temperature constraints into consideration. We developed a closed-form solution to capture temperature dynamics for a given periodic voltage schedule on multi-core platforms, and also developed three methods to check the feasibility of a periodic real-time schedule under peak temperature constraint. We further extended our research by incorporating the power/energy constraint with thermal awareness into our research problem. We investigated the energy estimation problem on multi-core platforms, and developed a computation efficient method to calculate the energy consumption for a given voltage schedule on a multi-core platform. In this dissertation, we present our research in details and demonstrate the effectiveness and efficiency of our approaches with extensive experimental results.

Leakage Temperature Dependency Aware Real-Time Scheduling for Power and Thermal Optimization

Catering to society’s demand for high performance computing, billions of transistors are now integrated on IC chips to deliver unprecedented performances. With increasing transistor density, the power consumption/density is growing exponentially. The increasing power consumption directly translates to the high chip temperature, which not only raises the packaging/cooling costs, but also degrades the performance/reliability and life span of the computing systems. Moreover, high chip temperature also greatly increases the leakage power consumption, which is becoming more and more significant with the continuous scaling of the transistor size. As the semiconductor industry continues to evolve, power and thermal challenges have become the most critical challenges in the design of new generations of computing systems. In this dissertation, we addressed the power/thermal issues from the system-level perspective. Specifically, we sought to employ real-time scheduling methods to optimize the power/thermal efficiency of the real-time computing systems, with leakage/ temperature dependency taken into consideration. In our research, we first explored the fundamental principles on how to employ dynamic voltage scaling (DVS) techniques to reduce the peak operating temperature when running a real-time application on a single core platform. We further proposed a novel real-time scheduling method, “M-Oscillations” to reduce the peak temperature when scheduling a hard real-time periodic task set. We also developed three checking methods to guarantee the feasibility of a periodic real-time schedule under peak temperature constraint. We further extended our research from single core platform to multi-core platform. We investigated the energy estimation problem on the multi-core platforms and developed a light weight and accurate method to calculate the energy consumption for a given voltage schedule on a multi-core platform. Finally, we concluded the dissertation with elaborated discussions of future extensions of our research.

Assigning real-time tasks on heterogeneous multiprocessors with two unrelated types of processors

A preliminary version of this paper appeared in Proceedings of the 31st IEEE Real-Time Systems Symposium, 2010, pp. 239–248.

Real-time communications over hybrid wired/wireless PROFIBUS-based networks

PROFIBUS is an international standard (IEC 61158) for factory-floor communications, with some hundreds of thousands of world-wide installations. However, it does not include any wireless capabilities. In this paper we propose a hybrid wired/wireless PROFIBUS solution where most of the design options are made in order to guarantee the proper real-time behaviour of the overall network. We address the timing unpredictability problems placed by the co-existence of heterogeneous transmission media in the same network. Moreover, we propose a novel solution to provide inter-cell mobility to PROFIBUS wireless nodes.

Real-time fieldbus communications using Profibus networks

This paper provides a comprehensive study on how to use Profibus fieldbus networks to support real-time industrial communications, that is, on how to ensure the transmission of real-time messages within a maximum bound time. Profibus is base on a simplified timed token (TT) protocol, which is a well-proved solution for real-time communication systems. However, Profibus differs with respect to the TT protocol, thus preventing the application of the usual TT protocol real-time analysis. In fact, real-time solutions for networks based on the TT protocol rely on the possibility of allocating specific bandwidth for the real-time traffic. This means that a minimum amount of time is always available, at each token visit, to transmit real-time messages, transversely, with the Profibus protocol, in the worst case, only one real-time message is processed per token visit. The authors propose two approaches to guarantee the real-time behavior of the Profibus protocol: (1) an unconstrained low-priority traffic profile; and (2) a constrained low-priority traffic profile. The proposed analysis shows that the first profile is a suitable approach for more responsive systems (tighter deadlines), while the second allows for increased nonreal-time traffic throughput

Scheduling real-time communications with P-NET

In this paper we address the P-NET Medium Access Control (MAC) ability to schedule traffic according to its real-time requirements, in order to support real-time distributed applications. We provide a schedulability analysis based on the P-NET standard, and propose mechanisms to overcome priority inversion problems resulting from the use of FIFO outgoing buffers

Guaranteeing real-time message deadlines in PROFIBUS networks

The paper provides a comprehensive study on how to use Profibus networks to support real time communications, that is, ensuring the transmission of the real time messages before their deadlines. Profibus is based on a simplified Timed Token (TT) protocol, which is a well proved solution for real time communication systems. However, Profibus differences from the TT protocol prevent the application of the usual TT analysis. The main reason is that, conversely to the TT protocol, in the worst case, only one high priority message is processed per token visit. The major contribution of the paper is to prove that, despite this shortcoming, it is possible to guarantee communication real time behaviour with the Profibus protocol

Supporting real-time parallel task models with work-stealing

Dynamic parallel scheduling using work-stealing has gained popularity in academia and industry for its good performance, ease of implementation and theoretical bounds on space and time. Cores treat their own double-ended queues (deques) as a stack, pushing and popping threads from the bottom, but treat the deque of another randomly selected busy core as a queue, stealing threads only from the top, whenever they are idle. However, this standard approach cannot be directly applied to real-time systems, where the importance of parallelising tasks is increasing due to the limitations of multiprocessor scheduling theory regarding parallelism. Using one deque per core is obviously a source of priority inversion since high priority tasks may eventually be enqueued after lower priority tasks, possibly leading to deadline misses as in this case the lower priority tasks are the candidates when a stealing operation occurs. Our proposal is to replace the single non-priority deque of work-stealing with ordered per-processor priority deques of ready threads. The scheduling algorithm starts with a single deque per-core, but unlike traditional work-stealing, the total number of deques in the system may now exceed the number of processors. Instead of stealing randomly, cores steal from the highest priority deque.

Server-based scheduling of parallel real-time tasks

Multicore platforms have transformed parallelism into a main concern. Parallel programming models are being put forward to provide a better approach for application programmers to expose the opportunities for parallelism by pointing out potentially parallel regions within tasks, leaving the actual and dynamic scheduling of these regions onto processors to be performed at runtime, exploiting the maximum amount of parallelism. It is in this context that this paper proposes a scheduling approach that combines the constant-bandwidth server abstraction with a priority-aware work-stealing load balancing scheme which, while ensuring isolation among tasks, enables parallel tasks to be executed on more than one processor at a given time instant.

Enhancing the real-time capabilities of the Linux Kernel

The mainline Linux Kernel is not designed forhard real-time systems; it only fits the requirements of soft realtimesystems. In recent years, a kernel developer communityhas been working on the PREEMPT-RT patch. This patch(that aims to get a fully preemptible kernel) adds some realtimecapabilities to the Linux kernel. However, in terms ofscheduling policies, the real-time scheduling class of Linux islimited to the First-In-First-Out (SCHED_FIFO) and Round-Robin (SCHED_RR) scheduling policies. These scheduling policiesare however quite limited in terms of realtime performance.Therefore, in this paper, we report one importantcontribution for adding more advanced real-time capabilitiesto the Linux Kernel. Specifically, we describe modificationsto the (PREEMPT-RT patched) Linux kernel to supportreal-time slot-based task-splitting scheduling algorithms. Ourpreliminary evaluation shows that our implementation exhibitsa real-time performance that is superior to the schedulingpolicies provided by the current version of PREMPT-RT. Thisis a significant add-on to a widely adopted operating system.

A pseudo-medium-wide 8-competitive interface for two-level compositional real-time scheduling of constrained- deadline sporadic tasks on a uniprocessor

Compositional real-time scheduling clearly requires that ”normal” real-time scheduling challenges are addressed but challenges intrinsic to compositionality must be addressed as well, in particular: (i) how should interfaces be described? and (ii) how should numerical values be assigned to parameters constituting the interfaces? The real-time systems community has traditionally used narrow interfaces for describing a component (for example, a utilization/bandwidthlike metric and the distribution of this bandwidth in time). In this paper, we introduce the concept of competitive ratio of an interface and show that typical narrow interfaces cause poor performance for scheduling constrained-deadline sporadic tasks (competitive ratio is infinite). Therefore, we explore more expressive interfaces; in particular a class called medium-wide interfaces. For this class, we propose an interface type and show how the parameters of the interface should be selected. We also prove that this interface is 8-competitive.

Slow down or race to halt: towards managing complexity of real-time energy management decisions

Existing work in the context of energy management for real-time systems often ignores the substantial cost of making DVFS and sleep state decisions in terms of time and energy and/or assume very simple models. Within this paper we attempt to explore the parameter space for such decisions and possible constraints faced.

A framework for the response time analysis of fixed-priority tasks with stochastic inter-arrival times

Real-time scheduling usually considers worst-case values for the parameters of task (or message stream) sets, in order to provide safe schedulability tests for hard real-time systems. However, worst-case conditions introduce a level of pessimism that is often inadequate for a certain class of (soft) real-time systems. In this paper we provide an approach for computing the stochastic response time of tasks where tasks have inter-arrival times described by discrete probabilistic distribution functions, instead of minimum inter-arrival (MIT) values.

Using NEXUS compliant debuggers for real time fault injection on microprocessors

As electronic devices get smaller and more complex, dependability assurance is becoming fundamental for many mission critical computer based systems. This paper presents a case study on the possibility of using the on-chip debug infrastructures present in most current microprocessors to execute real time fault injection campaigns. The proposed methodology is based on a debugger customized for fault injection and designed for maximum flexibility, and consists of injecting bit-flip type faults on memory elements without modifying or halting the target application. The debugger design is easily portable and applicable to different architectures, providing a flexible and efficient mechanism for verifying and validating fault tolerant components.