Results 1  10
of
14
New strategies for assigning realtime tasks to multiprocessor systems
 IEEE TRANSACTIONS ON COMPUTERS
, 1995
"... Optimal scheduling of realtime tasks on multiprocessor systems is known to be computationally intractable for large task sets. Any practical scheduling algorithm for assigning realtime tasks to a multiprocessor system presents a tradeoff between its computational complexity and its performance. In ..."
Abstract

Cited by 83 (0 self)
 Add to MetaCart
Optimal scheduling of realtime tasks on multiprocessor systems is known to be computationally intractable for large task sets. Any practical scheduling algorithm for assigning realtime tasks to a multiprocessor system presents a tradeoff between its computational complexity and its performance. In this study, new schedulability conditions are presented for homogeneous multiprocessor systems where individual processors execute the ratemonotonic scheduling algorithm. The conditions are used to develop new strategies for assigning realtime tasks to processors. The performance of the new strategies is shown to be significantly better than suggested by the existing literature. Under the realistic assumption that the load of each realtime task is small compared to the processing speed of each processor, it is shown that the processors can be almost fully utilized.
Vmalloc: A General and Efficient Memory Allocator
, 1996
"... Introduction Dynamic memory allocation is an integral part of programming. Programs in C and C++ (via constructors and destructors) routinely allocate memory using the familiar ANSIC standard interface malloc established around 1979 by Doug McIlroy. Malloc manipulates heap memory using the functi ..."
Abstract

Cited by 47 (7 self)
 Add to MetaCart
Introduction Dynamic memory allocation is an integral part of programming. Programs in C and C++ (via constructors and destructors) routinely allocate memory using the familiar ANSIC standard interface malloc established around 1979 by Doug McIlroy. Malloc manipulates heap memory using the functions malloc(s) to allocate a block of size s, free(b) to free a previously allocated block b, and realloc(b,s) to resize a block b to size s. No optimal solution to dynamic memory allocation exists [1, 2, 3] so, over the years, many malloc implementations were proposed with different tradeoffs in time and space efficiency. A study by David Korn and Phong Vo in 1985 presented and compared 11 malloc versions. Only a few of these survived the test of time. The first widely used malloc was written by McIlroy and became part of many Bell Labs Research and System V versions of the UNIX system. This malloc is based on a firstfit strategy and can be significantly slow in large memories. C. King
Assigning RealTime Tasks to Homogeneous Multiprocessor Systems
, 1994
"... Optimal scheduling of realtime tasks on multiprocessor systems is known to be computationally intractable for large task sets. Any practical scheduling algorithm for assigning realtime tasks to a multiprocessor system presents a tradeoff between its computational complexity and its performance. T ..."
Abstract

Cited by 27 (5 self)
 Add to MetaCart
Optimal scheduling of realtime tasks on multiprocessor systems is known to be computationally intractable for large task sets. Any practical scheduling algorithm for assigning realtime tasks to a multiprocessor system presents a tradeoff between its computational complexity and its performance. The performance of a scheduling algorithm is measured in terms of the additional number of processors required to arrive at a schedule without deadline violations as compared to an optimal algorithm. In this study, new schedulability conditions are presented for homogeneous multiprocessor systems where individual processors execute the ratemonotonic scheduling algorithm. The conditions are used to develop new strategies for assigning realtime tasks to processors. The performance of the new strategies is shown to be significantly better than suggested by the existing literature. Under the (realistic) assumption that the load of each realtime task is small compared to the processing speed of...
Biased Random Walks, Lyapunov Functions, and Stochastic Analysis of Best Fit Bin Packing
, 1995
"... We study the Best Fit algorithm for online bin packing under the distribution in which the item sizes are uniformly distributed in the discrete range f1=k � 2=k�:::�j=kg. Our main result is that, in the case j = k; 2, the asymptotic expected waste remains bounded. This settles an open problem of Co ..."
Abstract

Cited by 22 (6 self)
 Add to MetaCart
We study the Best Fit algorithm for online bin packing under the distribution in which the item sizes are uniformly distributed in the discrete range f1=k � 2=k�:::�j=kg. Our main result is that, in the case j = k; 2, the asymptotic expected waste remains bounded. This settles an open problem of Co man et al [3], and involves a detailed analysis of the in nite multidimensional Markov chain underlying the algorithm.
FixedPriority Scheduling of Periodic Tasks on Multiprocessor Systems
 Department of Computer Science, University of Virginia
, 1995
"... Consider the problem of periodic task scheduling, in which we seek to minimize the total number of processors required to execute a set of tasks such that task deadlines are guaranteed by the RateMonotonic (or RM) algorithm on each processor. This problem was first investigated by Dhall and Liu, an ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
Consider the problem of periodic task scheduling, in which we seek to minimize the total number of processors required to execute a set of tasks such that task deadlines are guaranteed by the RateMonotonic (or RM) algorithm on each processor. This problem was first investigated by Dhall and Liu, and the previous lowest bound for the problem was 2.0. In this paper, an improved solution is given by designing a new algorithm for it. The algorithm, called RMFirstFitDecreasingUtilization (or RMFFDU) , is shown to have a worstcase tight bound of 5=3 = 1:66 : : :, the lowest upper bound ever derived for the scheduling problem. Simulation studies show that on the average, the new algorithm performs consistently better than those in the literature. 1 Introduction In this paper, we study the the problem of scheduling a set of periodic tasks on a multiprocessor system such that task deadlines are guaranteed on individual processors by the ratemonotonic scheduling algorithm. The problem ...
OnLine Scheduling of Scalable RealTime Tasks on Multiprocessor Systems
 J. Parallel Distrib. Comput
, 2003
"... Previous researches on realtime scheduling assume that the number of processors required to execute a task is fixed and its computation time is given based on this fixed number of processors. However, in multiprocessor systems, the computation time of scalable task varies depending on the number o ..."
Abstract

Cited by 9 (0 self)
 Add to MetaCart
Previous researches on realtime scheduling assume that the number of processors required to execute a task is fixed and its computation time is given based on this fixed number of processors. However, in multiprocessor systems, the computation time of scalable task varies depending on the number of processors allocated to it. By determining a proper number of processors to be allocated to each realtime task, more realtime tasks complete their execution before deadlines. In this paper, we propose a new online scheduling algorithm for scalable, aperiodic, nonpreemptive, and independent tasks. The proposed algorithm uses workload to represent the computational requirement of tasks and tries to reduce the total workload of all scheduled tasks so that a newly arrived task should have more feasibility to complete its execution before deadline. The algorithm works based on three rules. First, the number of processors allocated to tasks is kept as small as possible without violating deadl...
A Linear Time Online Task Assignment Scheme for Multiprocessor Systems
, 1994
"... In this study, a new online task assignment scheme is presented for multiprocessor systems where individual processors execute the ratemonotonic scheduling algorithm. The computational complexity of the task assignment scheme grows linearly with the number of tasks, and its performance is shown to ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
In this study, a new online task assignment scheme is presented for multiprocessor systems where individual processors execute the ratemonotonic scheduling algorithm. The computational complexity of the task assignment scheme grows linearly with the number of tasks, and its performance is shown to be significantly better than previously existing schemes. The superiority of our scheme is achieved by a new schedulability condition derived for the ratemonotonic scheduling discipline. 1 Introduction Ratemonotonic (RM) scheduling is becoming a viable scheduling discipline for realtime systems. Through the years, researchers have successfully applied this discipline to tackle a number of practical problems, such as task synchronization, bus scheduling, joint scheduling of periodic and aperiodic tasks, and transient overload [4, 9]. This is done through developing various scheduling algorithms to cope with situations that are not covered by the ratemonotonic algorithm. While ratemonoto...
Linear Waste of Best Fit Bin Packing on Skewed Distributions
 in Proceedings of the 41st Annual Symposium on Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA
, 2000
"... We prove that Best Fit bin packing has linear waste on the discrete distribution U{j, k} (where items are drawn uniformly from the set 2/k, , j/k}) for sufficiently large k when j = #k and 0.66 # < 2/3. Our results extend to continuous skewed distributions, where items are drawn uniform ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
We prove that Best Fit bin packing has linear waste on the discrete distribution U{j, k} (where items are drawn uniformly from the set 2/k, , j/k}) for sufficiently large k when j = #k and 0.66 # < 2/3. Our results extend to continuous skewed distributions, where items are drawn uniformly on [0, a], for 0.66 a < 2/3. This implies that the expected asymptotic performance ratio of Best Fit is strictly greater than 1 for these distributions.