A Quantitative Analysis of OS Noise

Morari, Alessandro; Gioiosa, Roberto; Wisniewski, Robert W.; Cazorla, Francisco J.; Valero, Mateo

doi:10.1109/ipdps.2011.84

Cited by 47 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, LAMMPS scales very well for the size of system under study. Finally and most importantly, LAMMPS is widely regarded as an application that is resistant to external interference [24]. Therefore, LAMMPS represents a good challenge when testing for a performance degradation due to external perturbations like RDMA traffic.…”

Section: Multimentioning

confidence: 99%

Unraveling Network-Induced Memory Contention: Deeper Insights with Machine Learning

Groves

Grant

Gonzales

et al. 2018

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Abstract-Remote Direct Memory Access (RDMA) is expected to be an integral communication mechanism for future exascale systems -enabling asynchronous data transfers, so that applications may fully utilize CPU resources while simultaneously sharing data amongst remote nodes. In this work we examine Network-induced Memory Contention (NiMC) on Infiniband networks. We expose the interactions between RDMA, main-memory and cache, when applications and out-of-band services compete for memory resources. We then explore NiMC's resulting impact on application-level performance. For a range of hardware technologies and HPC workloads, we quantify NiMC and show that NiMC's impact grows with scale resulting in up to 3X performance degradation at scales as small as 8K processes even in applications that previously have been shown to be performance resilient in the presence of noise. Additionally, this work examines the problem of predicting NiMC's impact on applications by leveraging machine learning and easily accessible performance counters. This approach provides additional insights about the root cause of NiMC and facilitates dynamic selection of potential solutions. Lastly, we evaluated three potential techniques to reduce NiMC's impact, namely hardware offloading, core reservation and software-based network throttling.

show abstract

Section: Multimentioning

confidence: 99%

Unraveling Network-Induced Memory Contention: Deeper Insights with Machine Learning

Groves

Grant

Gonzales

et al. 2018

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…HPC infrastructures frequently get their performance severely degraded by system noise or jitter, which is caused by factors like OS activity, network sharing e ects or other phenomena [24]. Although the e ects of system jitter may be negligible as long as they are kept at the local scale, parallel operations like reductions or synchronizations are known to strongly amplify its e ects by propagating jitter across the whole parallel system [20].…”

Section: Tolerance To System Noisementioning

confidence: 99%

Iteration-fusing conjugate gradient

Zhuang

Casas

2017

Proceedings of the International Conference on Supercomputing

View full text Add to dashboard Cite

This paper presents the Iteration-Fusing Conjugate Gradient (IFCG) approach which is an evolution of the Conjugate Gradient method that consists in i) letting computations from di erent iterations to overlap between them and ii) splitting linear algebra kernels into subkernels to increase concurrency and relax data-dependencies. The paper presents two ways of applying the IFCG approach: The IFCG1 algorithm, which aims at hiding the cost of parallel reductions, and the IFCG2 algorithm, which aims at reducing idle time by starting computations as soon as possible. Both IFCG1 and IFCG2 algorithms are two complementary approaches aiming at increasing parallel performance. Extensive numerical experiments are conducted to compare the IFCG1 and IFCG2 numerical stability and performance against four state-of-the-art techniques. By considering a set of representative input matrices, the paper demonstrates that IFCG1 and IFCG2 provide parallel performance improvements up to 42.9% and 41.5% respectively and average improvements of 11.8% and 7.1% with respect to the best state-of-the-art techniques while keeping similar numerical stability properties. Also, this paper provides an evaluation of the IFCG algorithms' sensitivity to system noise and it demonstrates that they run 18.0% faster on average than the best state-of-the-art technique under realistic degrees of system noise.

show abstract

“…In 2011 [13], a more quantitative analysis of noise in the Linux OS using OS-level instrumentation focused on recording the frequency and duration of individual noise sources, e.g., page fault, different interrupt types, and process preemption, and visualizing the noise trace data using Paraver [16]. The experiments targeted the Sequoia benchmarks (AMG, IRS, LAMMPS, SPHOT, UMT) [11] to break down the individual sources of OS noise for each benchmark and to identify the noise frequency and period for each source.…”

Section: Operating System Noisementioning

confidence: 99%

Investigating Operating System Noise in Extreme-Scale High-Performance Computing Systems using Simulation

Engelmann

2013

Artificial Intelligence and Applications / 794: Modelling, Identification and Control / 795: Parallel and Distributed Computing

View full text Add to dashboard Cite

Hardware/software co-design for future-generation highperformance computing (HPC) systems aims at closing the gap between the peak capabilities of the hardware and the performance realized by applications (applicationarchitecture performance gap). Performance profiling of architectures and applications is a crucial part of this iterative process. The work in this paper focuses on operating system (OS) noise as an additional factor to be considered for co-design. It represents the first step in including OS noise in HPC hardware/software co-design by adding a noise injection feature to an existing simulation-based co-design toolkit. It reuses an existing abstraction for OS noise with frequency (periodic recurrence) and period (duration of each occurrence) to enhance the processor model of the Extreme-scale Simulator (xSim) with synchronized and random OS noise simulation. The results demonstrate this capability by evaluating the impact of OS noise on MPI Bcast() and MPI Reduce() in a simulated futuregeneration HPC system with 2,097,152 compute nodes.

show abstract

A Quantitative Analysis of OS Noise

Cited by 47 publications

References 27 publications

Unraveling Network-Induced Memory Contention: Deeper Insights with Machine Learning

Unraveling Network-Induced Memory Contention: Deeper Insights with Machine Learning

Iteration-fusing conjugate gradient

Investigating Operating System Noise in Extreme-Scale High-Performance Computing Systems using Simulation

Contact Info

Product

Resources

About