Towards an architecture-independent analysis of parallel algorithms
STOC '88 Proceedings of the twentieth annual ACM symposium on Theory of computing
Speedup Versus Efficiency in Parallel Systems
IEEE Transactions on Computers
Process control and scheduling issues for multiprogrammed shared-memory multiprocessors
SOSP '89 Proceedings of the twelfth ACM symposium on Operating systems principles
Characterizations of parallelism in applications and their use in scheduling
SIGMETRICS '89 Proceedings of the 1989 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
A bridging model for parallel computation
Communications of the ACM
Processor scheduling in shared memory multiprocessors
SIGMETRICS '90 Proceedings of the 1990 ACM SIGMETRICS conference on Measurement and modeling of computer systems
LogP: towards a realistic model of parallel computation
PPOPP '93 Proceedings of the fourth ACM SIGPLAN symposium on Principles and practice of parallel programming
Scheduling parallelizable tasks to minimize average response time
SPAA '94 Proceedings of the sixth annual ACM symposium on Parallel algorithms and architectures
SIGMETRICS '94 Proceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A randomized parallel 3D convex hull algorithm for coarse grained multicomputers
Proceedings of the seventh annual ACM symposium on Parallel algorithms and architectures
Using parallel program characteristics in dynamic processor allocation policies
Performance Evaluation
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
SODA '93 Proceedings of the fourth annual ACM-SIAM Symposium on Discrete algorithms
Scheduling parallel tasks to minimize average response time
SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms
Preemptive Scheduling of Parallel Jobs on Multiprocessors
SIAM Journal on Computing
Multiprocessor Scheduling for High-Variability Service Time Distributions
IPPS '95 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing
Using Runtime Measured Workload Characteristics in Parallel Processor Scheduling
IPPS '96 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing
| Hi-index | 0.00 |
In this work, we study job characterization in multi-programmed multiprocessor system by taking into consideration the parallel job models. We first introduce an example to illustrate the issues involved. Then we focus on two popular system scheduling policies: round-robin for single processor systems, and equi-partition for multiprocessor systems. We analytically study effect of job parallelization on the overall performance of the system, and also present simulation results. Through these studies, we discuss scheduling policies of parallel jobs in relation to the ratio of number of jobs and the number of processors in the multiprocessor system, and propose new paradigm for parallel algorithm designs.