Projects per year
Abstract
Increasingly prevalent asymmetric multicore processors (AMP) are necessary for delivering performance in the era of limited power budget and dark silicon. However, the software fails to use them efficiently. OS schedulers, in particular, handle asymmetry only under restricted scenarios. We have efficient symmetric schedulers, efficient asymmetric schedulers for single-threaded workloads, and efficient asymmetric schedulers for single program workloads. What we do not have is a scheduler that can handle all runtime factors affecting AMP for multi-threaded multi-programmed workloads.
This paper introduces the first general purpose asymmetry-aware scheduler for multi-threaded multi-programmed workloads. It estimates the performance of each thread on each type of core and identifies communication patterns and bottleneck threads. The scheduler then makes coordinated core assignment and thread selection decisions that still provide each application its fair share of the processor's time.
We evaluate our approach using the GEM5 simulator on four distinct big.LITTLE configurations and 26 mixed workloads composed of PARSEC and SPLASH2 benchmarks. Compared to the state-of-the art Linux CFS and AMP-aware schedulers, we demonstrate performance gains of up to 25% and 5% to 15% on average depending on the hardware setup.
This paper introduces the first general purpose asymmetry-aware scheduler for multi-threaded multi-programmed workloads. It estimates the performance of each thread on each type of core and identifies communication patterns and bottleneck threads. The scheduler then makes coordinated core assignment and thread selection decisions that still provide each application its fair share of the processor's time.
We evaluate our approach using the GEM5 simulator on four distinct big.LITTLE configurations and 26 mixed workloads composed of PARSEC and SPLASH2 benchmarks. Compared to the state-of-the art Linux CFS and AMP-aware schedulers, we demonstrate performance gains of up to 25% and 5% to 15% on average depending on the hardware setup.
Original language | English |
---|---|
Title of host publication | Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization (GCO 2020) |
Editors | Jason Mars, Lingjia Tang, Jingling Xue, Peng Wu |
Place of Publication | New York |
Publisher | ACM |
Pages | 268-279 |
ISBN (Print) | 9781450370479 |
DOIs | |
Publication status | Published - 22 Feb 2020 |
Event | International Symposium on Code Generation and Optimization (CGO 2020) - San Diego, United States Duration: 22 Feb 2020 → 26 Feb 2020 https://cgo-conference.github.io/cgo2020/ |
Publication series
Name | International Symposium on Code Generation and Optimization |
---|---|
ISSN (Print) | 1931-0544 |
ISSN (Electronic) | 2643-2838 |
Conference
Conference | International Symposium on Code Generation and Optimization (CGO 2020) |
---|---|
Abbreviated title | CGO 2020 |
Country/Territory | United States |
City | San Diego |
Period | 22/02/20 → 26/02/20 |
Internet address |
Keywords
- Asymmetric multicore processor
- OS scheduler
- Multi-threaded multi-programmed workloads
Fingerprint
Dive into the research topics of 'COLAB: a collaborative multi-factor scheduler for asymmetric multicore processors'. Together they form a unique fingerprint.Projects
- 2 Finished
-
ABC: Adaptive Brokerage for the Cloud: ABC: Adaptive Brokerage for the Cloud
Barker, A. D. (PI) & Thomson, J. D. (CoI)
1/04/18 → 30/09/22
Project: Standard
-
Discovery: Pattern Discovery and Program: Discovery: Pattern Discovery and Program Shaping for Manycore Systems
Thomson, J. D. (PI), Hammond, K. (CoI) & Sarkar, S. (CoI)
1/07/17 → 31/12/20
Project: Standard