Results 1  10
of
174
Speed scaling to manage energy and temperature
 Journal of the ACM
"... We first consider online speed scaling algorithms to minimize the energy used subject to the constraint that every job finishes by its deadline. We assume that the power required to run at speed s is P s s. We provide a tight bound on the competitive ratio of the previously proposed Optimal A ..."
Abstract

Cited by 169 (17 self)
 Add to MetaCart
(Show Context)
We first consider online speed scaling algorithms to minimize the energy used subject to the constraint that every job finishes by its deadline. We assume that the power required to run at speed s is P s s. We provide a tight bound on the competitive ratio of the previously proposed Optimal Available algorithm. This improves the best known competitive ratio by a factor of . We then introduce a new online algorithm, and show that this algorithm’s competitive ratio is at most e. This competitive ratio is significantly better and is approximately e for large . Our result is essentially tight for large . In particular, as approaches infinity, we show that any algorithm must have competitive ratio e (up to lower order terms). We then turn to the problem of dynamic speed scaling to minimize the maximum temperature that the device ever reaches, again subject to the constraint that all jobs finish by their deadlines. We assume that the device cools according to Fourier’s law. We show how to solve this problem in polynomial time, within any error bound, using the Ellipsoid algorithm. 1.
Speed scaling for weighted flow times
 in Proc. ACMSIAM SODA, 2007
"... Intel’s SpeedStep and AMD’s PowerNOW technologies allow the Windows XP operating system to dynamically change the speed of the processor to prolong battery life. In this setting, the operating system must not only have a job selection policy to determine which job to run, but also a speed scaling po ..."
Abstract

Cited by 85 (19 self)
 Add to MetaCart
Intel’s SpeedStep and AMD’s PowerNOW technologies allow the Windows XP operating system to dynamically change the speed of the processor to prolong battery life. In this setting, the operating system must not only have a job selection policy to determine which job to run, but also a speed scaling policy to determine the speed at which the job will be run. We give an online speed scaling algorithm that is O(1)competitive for the objective of weighted flow time plus energy. This algorithm also allows us to efficiently construct an O(1)approximate schedule for minimizing weighted flow time subject to an energy constraint. 1
Algorithmic problems in power management
 SIGACT News
, 2005
"... We survey recent research that has appeared in the theoretical computer science literature on algorithmic ..."
Abstract

Cited by 73 (4 self)
 Add to MetaCart
(Show Context)
We survey recent research that has appeared in the theoretical computer science literature on algorithmic
Getting the Best Response for Your Erg
"... We consider the speed scaling problem of minimizing the average response time of a collection of dynamically released jobs subject to a constraint A on energy used. We propose an algorithmic approach in which an energy optimal schedule is computed for a huge A, and then the energy optimal schedule ..."
Abstract

Cited by 64 (10 self)
 Add to MetaCart
(Show Context)
We consider the speed scaling problem of minimizing the average response time of a collection of dynamically released jobs subject to a constraint A on energy used. We propose an algorithmic approach in which an energy optimal schedule is computed for a huge A, and then the energy optimal schedule is maintained as A decreases. We show that this approach yields an efficient algorithm for equiwork jobs. We note that the energy optimal schedule has the surprising feature that the job speeds are not monotone functions of the available energy. We then explain why this algorithmic approach is problematic for arbitrary work jobs. Finally, we explain how to use the algorithm for equiwork jobs to obtain an algorithm for arbitrary work jobs that is O(1)approximate with respect to average response time, given an additional factor of (1 + ffl)energy.
Static Energy Reduction Techniques for Microprocessor Caches
 IN 2001 INTERNATIONAL CONFERENCE ON COMPUTER DESIGN
, 2001
"... Microprocessor performance has been improved by increasing the capacity of onchip caches. However, the performance gain comes at the price of static energy consumption due to subthreshold leakage current in cache memory arrays. This paper compares three techniques for reducing static energy consump ..."
Abstract

Cited by 51 (5 self)
 Add to MetaCart
Microprocessor performance has been improved by increasing the capacity of onchip caches. However, the performance gain comes at the price of static energy consumption due to subthreshold leakage current in cache memory arrays. This paper compares three techniques for reducing static energy consumption in onchip level1 and level2 caches. One technique employs lowleakage transistors in the memory cell. Another technique, power supply switching, can be used to turn off memory cells and discard their contents. A third alternative is dynamic threshold modulation, which places memory cells in a standby state that preserves cell contents. In our experiments, we explore the energy and performance tradeoffs of these techniques. We also investigate the sensitivity of microprocessor performance and energy consumption to additional cache latency caused by leakagereduction techniques.
Thermal Herding: Microarchitecture Techniques for Controlling Hotspots in HighPerformance 3DIntegrated Processors
, 2007
"... 3D integration technology greatly increases transistor density while providing faster onchip communication. 3D implementations of processors can simultaneously provide both latency and power benefits due to reductions in critical wires. However, 3D stacking of active devices can potentially exacerb ..."
Abstract

Cited by 50 (5 self)
 Add to MetaCart
(Show Context)
3D integration technology greatly increases transistor density while providing faster onchip communication. 3D implementations of processors can simultaneously provide both latency and power benefits due to reductions in critical wires. However, 3D stacking of active devices can potentially exacerbate existing thermal problems. In this work, we propose a family of Thermal Herding techniques that (1) reduces 3D power density and (2) locates a majority of the power on the top die closest to the heat sink. Our 3D/thermalaware microarchitecture contributions include a significancepartitioned datapath that places the frequently switching 16bits on the top die, a 3Daware instruction scheduler allocation scheme, an address memoization approach for the load and store queues, a partial value encoding for the L1 data cache, and a branch target buffer that exploits a form of frequent partial value locality in target addresses. Compared to a conventional planar processor, our 3D processor achieves a 47.9 % frequency increase which results in a 47.0 % performance improvement (min 7%, max 77 % on individual benchmarks), while simultaneously reducing total power by 20 % (min 15%, max 30%). Without our Thermal Herding techniques, the worstcase 3D temperature increases by 17 degrees. With our Thermal Herding techniques, the temperature increase is only 12 degrees (29 % reduction in the 3D worstcase temperature increase).
Speed Scaling of Tasks with Precedence Constraints
, 2005
"... We consider the problem of speeding scaling to conserve energy in a distributedsetting where there are precedence constraints between tasks, and where the performance measure is the makespan. That is, we consider an energy bounded versionof the classic problem P  prec  Cmax. We show that, without ..."
Abstract

Cited by 47 (1 self)
 Add to MetaCart
We consider the problem of speeding scaling to conserve energy in a distributedsetting where there are precedence constraints between tasks, and where the performance measure is the makespan. That is, we consider an energy bounded versionof the classic problem P  prec  Cmax. We show that, without loss of generality,one need only consider constant power schedules. We then show how to reduce this problem to the problem Q  prec  Cmax to obtain a polylog(m)approximation algorithm.
Speed Scaling Functions for Flow Time Scheduling based on Active Job Count
"... Abstract. We study online scheduling to minimize flow time plus energy usage in the dynamic speed scaling model. We devise new speed scaling functions that depend on the number of active jobs, replacing the existing speed scaling functions in the literature that depend on the remaining work of activ ..."
Abstract

Cited by 46 (12 self)
 Add to MetaCart
(Show Context)
Abstract. We study online scheduling to minimize flow time plus energy usage in the dynamic speed scaling model. We devise new speed scaling functions that depend on the number of active jobs, replacing the existing speed scaling functions in the literature that depend on the remaining work of active jobs. The new speed functions are more stable and also more efficient. They can support better job selection strategies to improve the competitive ratios of existing algorithms [5,8], and, more importantly, to remove the requirement of extra speed. These functions further distinguish themselves from others as they can readily be used in the nonclairvoyant model (where the size of a job is only known when the job finishes). As a first step, we study the scheduling of batched jobs (i.e., jobs with the same release time) in the nonclairvoyant model and present the first competitive algorithm for minimizing flow time plus energy (as well as for weighted flow time plus energy); the performance is close to optimal. 1
Methodology For EarlyStage, MicroarchitectureLevel PowerPerformance Analysis Of Microprocessors
"... The PowerTimer toolset has been developed for use in earlystage, microarchitecturelevel powerperformance analysis of microprocessors. ..."
Abstract

Cited by 45 (23 self)
 Add to MetaCart
The PowerTimer toolset has been developed for use in earlystage, microarchitecturelevel powerperformance analysis of microprocessors.
Poweraware scheduling for makespan and flow
 In Proc. 18th Annual ACM Symp. Parallelism in Algorithms and Architectures
, 2006
"... We consider offline scheduling algorithms that incorporate speed scaling to address the bicriteria problem of minimizing energy consumption and a scheduling metric. For makespan, we give a lineartime algorithm to compute all nondominated solutions for the general uniprocessor problem and a fast a ..."
Abstract

Cited by 44 (1 self)
 Add to MetaCart
(Show Context)
We consider offline scheduling algorithms that incorporate speed scaling to address the bicriteria problem of minimizing energy consumption and a scheduling metric. For makespan, we give a lineartime algorithm to compute all nondominated solutions for the general uniprocessor problem and a fast arbitrarilygood approximation for multiprocessor problems when every job requires the same amount of work. We also show that the multiprocessor problem becomes NPhard when jobs can require different amounts of work. For total flow, we show that the optimal flow corresponding to a particular energy budget cannot be exactly computed on a machine supporting exact real arithmetic, including the extraction of roots. This hardness result holds even when scheduling equalwork jobs on a uniprocessor. We do, however, extend previous work by Pruhs et al. to give an arbitrarilygood approximation for scheduling equalwork jobs on a multiprocessor. 1