Application of full-system simulation in exploratory system design and development

Peterson, James L.; Bohrer, Patrick; Chen, L.; Elnozahy, E. N. Mootaz; Gheith, Ahmed; Jewell, R. H.; Kistler, Michael; Maeurer, T. R.; Malone, S.A.; Murrell, D. B.; Needel, N.; Rajamani, Karthick; Rinaldi, M. A.; Simpson, Rick; Sudeep, Kartik; Zhang, L.

doi:10.1147/rd.502.0321

Cited by 17 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mambo on its own has been verified by IBM [22] and we have verified our network model, using bandwidth and latency benchmarks, against our Cray XT-3 [24]. This leaves the question of whether the combination of these two components yields an accurate simulator.…”

Section: Validationmentioning

confidence: 85%

See 1 more Smart Citation

Instruction-level simulation of a cluster at scale

León¹,

Riesen

Maccabe

et al. 2009

Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis

View full text Add to dashboard Cite

Instruction-level simulation is necessary to evaluate new architectures. However, single-node simulation cannot predict the behavior of a parallel application on a supercomputer. We present a scalable simulator that couples a cycle-accurate node simulator with a supercomputer network model. Our simulator executes individual instances of IBM's Mambo PowerPC simulator on hundreds of cores. We integrated a NIC emulator into Mambo and model the network instead of fully simulating it. This decouples the individual node simulators and makes our design scalable.Our simulator runs unmodified parallel message-passing applications on hundreds of nodes. We can change network and detailed node parameters, inject network traffic directly into caches, and use different policies to decide when that is an advantage.This paper describes our simulator in detail, evaluates it, and demonstrates its scalability. We show its suitability for architecture research by evaluating the impact of cache injection on parallel application performance.

show abstract

Section: Validationmentioning

confidence: 85%

“…Our cluster simulator uses an augmented version of IBM's Mambo full-system simulator [22] that provides cache injection of incoming network messages [4]. Mambo is called a full-system simulator because it simulates all the components of a node: CPU, caches, memory, and the buses that connect them.…”

Section: Mambomentioning

confidence: 99%

Instruction-level simulation of a cluster at scale

León¹,

Riesen

Maccabe

et al. 2009

Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis

View full text Add to dashboard Cite

show abstract

“…The challenge here is compounded by the fact that such simulators are often slower than real processors by a factor of 10,000 or more. Even though many chip simulators (such as IBM's SystemSim simulator [5]) have the capability of fast forwarding with only a 10 fold slowdown (or so) through regions of code that do not require accurate prediction, it is often infeasible to use them to simulate large scale applications.…”

Section: B Predicting Sequential Execution Blocksmentioning

confidence: 99%

Simulating Large Scale Parallel Applications Using Statistical Models for Sequential Execution Blocks

Zheng

Gupta

Bohm

et al. 2010

2010 IEEE 16th International Conference on Parallel and Distributed Systems

View full text Add to dashboard Cite

Abstract-Predicting sequential execution blocks of a large scale parallel application is an essential part of accurate prediction of the overall performance of the application. When simulating a future machine that is not yet fabricated, or a prototype system only available at a small scale, it becomes a significant challenge. Using hardware simulators may not be feasible due to excessively slowed down execution times and insufficient resources. These challenging issues become increasingly difficult in proportion to scale of the simulation.In this paper, we propose an approach based on statistical models to accurately predict the performance of the sequential execution blocks that comprise a parallel application. We deployed these techniques in a trace-driven simulation framework to capture both the detailed behavior of the application as well as the overall predicted performance. The technique is validated using both synthetic benchmarks and the NAMD application.

show abstract

“…SimOS and IBM Mambo full-system simulator [3,13] uses a checkpointing mechanism very similar to what we propose, with explicit model state separate from the implementation state. Typical uses for checkpoints in Mambo is to save complex system setups and to switch between different implementations and different abstraction levels.…”

Section: Related Work and Alternativesmentioning

confidence: 99%

“…Checkpointing was originally developed in the mid1990s to support changing the level of abstraction in a simulation model, from a fast approximative (CPU) model to a detailed microarchitecture model [3,13]. The methodology is to use a fast simulation to position a workload at an interesting point (after booting, loading target software, etc.)…”

Section: Introductionmentioning

confidence: 99%