Q. Qiu, Qing Wu, and M. Pedram, "Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets", Proc. the Design Automation Conference, Jun. 2000.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....a voltage scaling scheme for system level communication pipelines [38, 39, 40] it can reduce energy consumption compared to shutting down idle component while satisfying all QoS requirement. Qiu, Wu and Pedram proposed generalized stochastic Petri nets (GSPN) as a model for communication systems [35, 34, 36, 37]. They derived power consumption from a set of QoS constraints such as delay and jitter, and proposed a linear programming solution to finding the optimal power management policy. Although these techniques manage power for the entire communication system, they have a few limitations that cannot ....

Q. Qiu, Q. Wu, and M. Pedram. Dynamic power management of complex systems using generalized stochastic petri nets. In Proc. Design Automation Conference, pages 352--356, June 2000.

....the above techniques are effective to reduce system power consumption, they do not treat power or timing as hard constraints, but as costs or penalties. Most of DPM techniques assume single resource scenarios and therefore did not consider inter resource dependency. Qiu, Qu and Pedram in [16] model multiple service providers and their Generalized Stochastic Petri Net (GSPN) model can potentially model dependencyamong resources. However, only one server is needed to process an incoming request, and their GSPN model is mainly for the request dispatch behavior of servers rather than ....

Q. Qiu, Q. Wu, and M. Pedram. Dynamic power management of complex systems using generalized stochastic petri nets. In Proc. 2000.

....such as solar whose maximum output can vary, they must be strictly satisfied. This becomes especially important as we increase the dynamic range of power by increasing parallelism. Second, they have not considered inter component dependency in a system, with the exception of Qiu, Qu and Pedram in [35], which models multiple service providers and their Generalized DPM DVS MS [45, 16] 3, 34] 13, 38, 39, 36] 26, 28] Timing as constraint N N Y Y Y Power as constraint N N N N Y Timing overhead Y Y N N Y Power overhead Y Y N N Y Multiple resources N Y N Y Y Figure 3: Comparison of dynamic ....

Q. Qiu, Q. Wu, and M. Pedram. Dynamic power management of complex systems using generalized stochastic petri nets. In Proc. 2000.

....Command, USAF, under cooperative agreement FC 3060200 2 0525 as part of the Power Aware Communication and Computation (PACC) program. into two categories [14] dynamic and static. Dynamic techniques are generally easy to implement and applied during run time. Examples of such techniques include [1, 4, 8, 11, 15, 16, 17]. Due to its inherent uncertainty and lack of complete knowledge about the timing constraints, no strong optimality results have been proven with these techniques. In [4] several dynamic voltage scheduling algorithms are proposed for real time systems containing both periodic tasks and sporadic ....

Q. Qiu, Q. Wu, and M.Pedram. Dynamic power management of complex system using generalized stochastic petri nets. DAC, pages 352--356, 2000.

....cost of mode changes on the processor is often reasonably neglected [6, 9, 10] In dynamic power management techniques, researchers concentrated on systems of a single device without strong timing guarantees [2, 7, 11] Tradeoffs are made between the power consumption and system performance. In [8] the authors did model multiple servers and relationships in the system. However, the modeled servers have identical behaviors (handling incoming requests) with the only difference in server parameters (handling capacity, etc. The modeled relationships of synchronization and concurrency are ....

Q. Qiu, Q. Wu, and M. Pedram. Dynamic power management of complex systems using Generalized Stochastic Petri Nets. In Proc. of DAC, pages 352--356, 2000.

....a stochastic optimization problem. These policies can explicitly trade off between power saving and performance while timeout and predictive policies cannot. Stochastic policies include discrete time and continuous time stationary models [17] 18] time indexed semi Markov models [19] Petri Nets [20], and nonstationary models [21] A common problem is that most policies require the characteristics of the workloads for off line optimization. There is no universally adopted method to adjust at run time if the workload behavior changes. 2) Low Power Scheduling for Processors: Instead of ....

Q. Qiu, Q. Wu, and M. Pedram, "Dynamic power management of complex systems using generalized stochastic petri nets," in Proc. Design Automation Conf., Los Angeles, CA, June 2000, pp. 352--356.

No context found.

Q. Qiu, Qing Wu, and M. Pedram, "Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets", Proc. the Design Automation Conference, Jun. 2000.

....complex system behaviors, such as concurrency, synchronization, mutual exclusion, and conflict, are present, the modeling techniques in [8] 10] become inadequate because they are effective only when constructing stochastic models of simple systems consisting of non interacting components. In [14], a technique based on controllable generalized stochastic Petri nets (GSPN) with cost is proposed that is powerful enough to compactly model a power managed system with complex behavioral characteristics. It is indeed easier for the system designer to manually specify the GSPN model than to ....

....paper, we use a simple system with a single service provider. This is because the focus of this paper is on power and QoS management, not on complex system modeling. For an example of using GSPN to model a complex power managed system with multiple interacting service providers, please refer to [14]. Figure 2 gives a simplified block diagram of our PQ managed client. Figure 2 Block diagram of a PQ managed MM client. As shown in Figure 2, the MM client consists of a service provider (SP) that may be a CPU, a DSP, or an array of hard disks. The SP provides services (e.g. computing, ....

[Article contains additional citation context not shown here]

Q. Qiu, Q. Wu, and M. Pedram, "Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets," Design Automation Conf., pp. 352-356, June 2000.

.... cases, cause timing violations [9] Furthermore, it has been shown that temperature gradients on the silicon substrate can occur due to different activities and or different sleep modes of various functional blocks in high performance microprocessor chips [10] Dynamic power management (DPM) [11] and functional block clock gating can be major sources of such thermal gradients over the substrate. Based on the cell power consumption map over the substrate, some researchers have provided techniques to derive the temperature profile along the substrate surface [12] The existence of such ....

Q.Wu, Q.Qiu, M.Pedram, "Dynamic Power Management of Complex Systems using Generalized Stochastic Petri Nets," Proc. Design Automation Conference, 2000, pp.352-356.

....and sleep modes of the functional blocks in high performance chips cause significant temperature gradients on the substrate. In [3] it has been reported that thermal gradients of 40 C exist in a high performance microprocessor design. Low power design techniques such as dynamic power management [4] and clock gating can result in such thermal gradients. With circuits moving toward GHz frequencies it is expected that the magnitude of thermal gradients in the substrate would further increase. In addition, as the minimum feature size shrinks down, the top most metal layers that carry the global ....

Q. Wu, Q. Qiu, and M. Pedram, Dynamic power management of complex systems using generalized stochastic Petri nets, Proc. Design Automation Conf., pp. 352-356, June 2000.

No context found.

Q. Qiu, Q. Wu, M. Pedram, "Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets", Proceedings of the Design Automation Conference, pp. 352-356, Jun. 2000.

No context found.

Q.Qiu, Q.Wu, and M.Pedram. Dynamic power management of complex systems using generalised stochastic petri nets. Proc. of the 37th Design Automation Conference, pages 108--119, 2000.

No context found.

Q.Qiu, Q.Wu, M.Pedram, "Dynamic Power Management of Complex Systems Using Generalised Stochastic Petri Nets", Proceedings of the 37th Design Automation Conference, June 2000, pp. 352-356.

No context found.

Q. Qiu and M. Pedram, "Dynamic power management of Complex Systems Using Generalized Stochastic Petri Nets", Design Automation Conference, pp. 352--356, 2000.

No context found.

Q. Qiu, Q. Wu, and M. Pedram, "Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets," Proc. Design Automation Conf., pp. 352-356, 2000.

No context found.

Q. Qiu and Q. Wu and M. Pedram. Dynamic power management of complex systems using generalized stochastic petri nets. In Proceedings of Design Automation Conference, pages 352-356. ACM Press, 2000.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC