SST + gem5 = a scalable simulation infrastructure for high performance computing

Authors:
Mingyu Hsieh;Kevin Pedretti;Jie Meng;Ayse Coskun;Michael Levenhagen;Arun Rodrigues
Affiliations:
Sandia National Labs, Albuquerque, NM;Sandia National Labs, Albuquerque, NM;Boston University, Boston, MA;Boston University, Boston, MA;Sandia National Labs, Albuquerque, NM;Sandia National Labs, Albuquerque, NM
Venue:
Proceedings of the 5th International ICST Conference on Simulation Tools and Techniques
Year:
2012

Citing 14
Cited 1

The SimpleScalar tool set, version 2.0

ACM SIGARCH Computer Architecture News
Wattch: a framework for architectural-level power analysis and optimizations

Proceedings of the 27th annual international symposium on Computer architecture
Exploiting Structural Duplication for Lifetime Reliability Enhancement

Proceedings of the 32nd annual international symposium on Computer Architecture
Fast switching of threads between cores

ACM SIGOPS Operating Systems Review
Managing contention for shared resources on multicore processors

Communications of the ACM
McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures

Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
Resource-conscious scheduling for energy efficiency on multicore processors

Proceedings of the 5th European conference on Computer systems
ORION 2.0: a fast and accurate NoC power and area model for early-stage design space exploration

Proceedings of the Conference on Design, Automation and Test in Europe
Experiences with a Lightweight Supercomputer Kernel: Lessons Learned from Blue Gene's CNK

Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis
The structural simulation toolkit

ACM SIGMETRICS Performance Evaluation Review - Special issue on the 1st international workshop on performance modeling, benchmarking and simulation of high performance computing systems (PMBS 10)
A framework for architecture-level power, area, and thermal simulation and its application to network-on-chip design exploration

ACM SIGMETRICS Performance Evaluation Review - Special issue on the 1st international workshop on performance modeling, benchmarking and simulation of high performance computing systems (PMBS 10)
Scalable, accurate multicore simulation in the 1000-core era

ISPASS '11 Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software
The gem5 simulator

ACM SIGARCH Computer Architecture News
A scalable simulation framework for evaluating thermal management techniques and the lifetime reliability of multithreaded multicore systems

IGCC '11 Proceedings of the 2011 International Green Computing Conference and Workshops

VarEMU: an emulation testbed for variability-aware software

Proceedings of the Ninth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis

Quantified Score

Hi-index	0.00

Visualization

Abstract

High Performance Computing (HPC) faces new challenges in scalability, performance, reliability, and power consumption. Solving these challenges will require radically new hardware and software approaches. It is impractical to explore this vast design space without detailed system-level simulations. However, most of the existing simulators are either not sufficiently detailed, not scalable, or cannot evaluate key system characteristics such as energy consumption or reliability. To address this problem, we integrate the highly detailed gem5 performance simulator into the parallel Structural Simulation Toolkit (SST). We add the fast-forwarding capability in the SST/gem5 and port the lightweight Kitten operating system on gem5. In addition, we improve the reliability model in SST with a comprehensive analysis of system reliability. Utilizing the simulation framework, we evaluate the impact of two energy-efficient resource-conscious scheduling policies on system reliability. Our results show that the effectiveness of scheduling policies differ according to the composition of workload and system topology.