Co-scheduling algorithms for high-throughput workload execution
From MaRDI portal
Abstract: This paper investigates co-scheduling algorithms for processing a set of parallel applications. Instead of executing each application one by one, using a maximum degree of parallelism for each of them, we aim at scheduling several applications concurrently. We partition the original application set into a series of packs, which are executed one by one. A pack comprises several applications, each of them with an assigned number of processors, with the constraint that the total number of processors assigned within a pack does not exceed the maximum number of available processors. The objective is to determine a partition into packs, and an assignment of processors to applications, that minimize the sum of the execution times of the packs. We thoroughly study the complexity of this optimization problem, and propose several heuristics that exhibit very good performance on a variety of workloads, whose application execution times model profiles of parallel scientific codes. We show that co-scheduling leads to to faster workload completion time and to faster response times on average (hence increasing system throughput and saving energy), for significant benefits over traditional scheduling from both the user and system perspectives.
Recommendations
- Speedup-aware co-schedules for efficient workload management
- Models and algorithms for coscheduling compute-intensive tasks on a network of workstations
- On scheduling coflows
- On scheduling coflows (extended abstract)
- Scheduling and optimizing algorithm for parallel tasks in heterogeneous distributed computing systems
- scientific article; zbMATH DE number 2080857
- Multi-cluster co-allocation scheduling algorithms in virtual computing environments
Cites work
- scientific article; zbMATH DE number 3639144 (Why is no real title available?)
- scientific article; zbMATH DE number 1003241 (Why is no real title available?)
- A stochastic batching and scheduling problem
- Efficient scheduling algorithms for a single batch processing machine
- Fast parallel algorithms for short-range molecular dynamics
- Introduction to algorithms.
- Optimal batch schedules for parallel machines
- Optimal control of batch service queues
- Performance Bounds for Level-Oriented Two-Dimensional Packing Algorithms
- ScaLAPACK Users' Guide
- Scheduling a batching machine
- Scheduling with batching: A review
- Speedup-aware co-schedules for efficient workload management
- Two-dimensional packing problems: a survey
Cited in
(9)- On scheduling coflows (extended abstract)
- An algorithm for coalescing operations with precedence constraints in real-time systems
- Optimizing latency and throughput of application workflows on clusters
- Novel fairness-aware co-scheduling for shared cache contention game on chip multiprocessors
- A graph based approach for co-scheduling jobs on multi-core computers
- Loosely coordinated coscheduling in the context of other approaches for dynamic job scheduling: a survey
- Euro-Par 2004 Parallel Processing
- Core allocation to minimize total flow time in a multicore system in the presence of a processing time constraint
- Speedup-aware co-schedules for efficient workload management
This page was built for publication: Co-scheduling algorithms for high-throughput workload execution
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1702725)
