We developed a Virtual Power Management (VPM) simulation methodology for pre-silicon design and validation of power management hardware and firmware. VPM integrates a realistic hardware interface with high-level workload and power models to achieve fast and effective system-wide simulation. VPM models are used independently for algorithmic and architectural exploration, and in conjunction with the Simics simulation environment to execute real firmware for verification. In this paper, we present an overview of the VPM architecture and results from two studies using the simulation framework.

Dynamic power management features are now an integral part of processor chip and system design. Dynamic voltage and frequency scaling (DVFS), core folding and per-core power gating (PCPG) are power control actuators (or "knobs") that are available in modern multi-core systems. However, figuring out the actuation protocol for such knobs in order to achieve maximum efficiency has so far remained an open research problem. In the context of specific system utilization dynamics, the desirable order of applying these knobs is not easy to determine.

Real-time systems are an important class of process control systems that need to respond to events under time constraints, or deadlines. Such systems may also be required to deliver service in spite of hardware or software faults in their components. This fault-tolerant characteristic is especially critical in systems whose failure can cause economic disaster and/or loss of lives. This paper reports recent research in the area of analytical modeling of the three major characteristics of real-time systems: timeliness, dependability, and external environmental dependencies. The paper starts with a brief introduction to analytical modeling frameworks such as Markov models and stochastic petri nets. This is followed by an examination of advances in modeling response-time distributions, reliability, distributed messaging services, and software fault-tolerance in real-time systems.

Messaging services are a useful component in distributed systems that require scalable dissemination of messages (events) from suppliers to consumers. These services decouple suppliers and consumers, and take care of client registration and message propagation, thus relieving the burden on the supplier Recently performance models for the configurable delivery and discard policies found in messaging services have been developed, that can be used to predict response time distributions and discard probabilities under failure-free conditions. However, these messaging service models do not include the effect of failures. In a distributed system, supplier, consumer and messaging services can fail independently leading to different consequences. In this paper we consider the expected loss rate associated with messaging services as a performability measure and derive approximate closed-form expressions for three different quality of service settings. These measures provide a quantitative framework that allows different messaging service configurations to be compared and design trade-off decisions to be made.

As CORBA (Common Object Request Broker Architecture) gains popularity as a standard for portable, distributed, object-oriented computing, the need for a CORBA messaging solution is being increasingly felt. This led the Object Management Group (OMQ) to specify a Notification Service that aims to provide a more flexible and robust messaging solution than the earlier Event Service. The Notification Service provides several configurable quality of service (QoS) and administrative settings that deal with issues such as reliability, event (message) delivery order and discard policies. Unlike in conventional queuing systems, some Notification Service QoS configurations can lead to discards from within the internal queues, requiring careful analysis and configuration if such discards are to be avoided or minimized. This paper presents stochastic models (based on continuous time Markov chains and queuing theory) to analyze the Notification Service delivery and discard policies in detail.

The event service is the earliest CORBA solution to the message queue model of communication in distributed systems. Typical implementations, however, suffer from the lack of event delivery guarantees. The loss of messages is aggravated by the presence of burstiness in the input to the event service, and occurrences of isolated bursts of traffic could also have serious effects. In this paper, we develop stochastic reward net (SRN) models that can aid in the study and configuration of the event service to conform to design specifications. To capture burstiness in the input, a Markov-modulated Poisson process (MMPP) is used as the input source. Erlang distributed event consumption times are used in the models to accommodate more general distributions and a wider range of variances. The models also take into consideration the FIFO discard policy adopted in many event service implementations. The SRN models are solved using the tool SPNP (Stochastic Petri Net Package). The applicability of the models to the CORBA notification service is also briefly discussed.