Evaluating the effect of replacing CNK with linux on the compute-nodes of blue gene/l

Shmueli, Edi; Almási, George; Brunheroto, José R.; Castaños, José G.; Dózsa, Gábor; Kumar, Sameer; Lieber, Derek

doi:10.1145/1375527.1375554

Cited by 27 publications

(24 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows it to run existing kernels without any porting, including lightweight kernels [27] like Kitten, Catamount, Cray CNL [17], and IBM's CNK [29].…”

Section: Palacios As a Hpc Vmmmentioning

confidence: 99%

“…Since a full Linux distribution is not used, this approach suffers many of the same functionality weaknesses as the non-Linux approaches, while not providing the performance advantages. Other examples of this approach are the efforts to port Linux to the IBM BlueGene/L and BlueGene/P systems [30,3]. These projects have encountered performance issues due to the mismatch between the platform's memory management hardware and the Linux memory management subsystem.…”

Section: Chapter 7 Related Workmentioning

confidence: 99%

“…The desire to preserve the benefits of a lightweight environment but provide support a richer feature set has also led other lightweight kernel developers to explore more full-featured alternatives [29]. We have also explored other means of providing a more full-featured set of system services [34], but the complexity of building a framework for application-specific OSes is significantly greater than simply using an existing full-featured virtualized OS, especially if the performance impact is minimal.…”

Section: Chapter 7 Related Workmentioning

confidence: 99%

“…Kitten's simple memory model enables high performance communication and data sharing, and it has a low noise profile in massively multiprocessor environments. Kitten has been developed in the spirit of lightweight kernels [27], such as Sandia's Catamount [18] and IBM's CNK [29], that are well known to perform better than commodity kernels for HPC.…”

Section: Chapter 1 Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Palacios and Kitten : high performance operating systems for scalable virtualized and native supercomputing.

Widener¹,

Jaconette²,

Bridges³

et al. 2009

View full text Add to dashboard Cite

Palacios and Kitten are new open source tools that enable applications, whether ported or not, to achieve scalable high performance on large machines. They provide a thin layer over the hardware to support both full-featured virtualized environments and native code bases. Kitten is an OS under development at Sandia that implements a lightweight kernel architecture to provide predictable behavior and increased flexibility on large machines, while also providing Linux binary compatibility. Palacios is a VMM that is under development at Northwestern University and the University of New Mexico. Palacios, which can be embedded into Kitten and other OSes, supports existing, unmodified applications and operating systems by using virtualization that leverages hardware technologies. We describe the design and implementation of both Kitten and Palacios. Our benchmarks show that they provide near native, scalable performance. Palacios and Kitten provide an incremental path to using supercomputer resources that is not performance-compromised.3 Acknowledgment

show abstract

“…This allows it to run existing kernels without any porting, including lightweight kernels [27] like Kitten, Catamount, Cray CNL [17], and IBM's CNK [29].…”

Section: Palacios As a Hpc Vmmmentioning

confidence: 99%

Section: Chapter 7 Related Workmentioning

confidence: 99%

Section: Chapter 7 Related Workmentioning

confidence: 99%

Section: Chapter 1 Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Palacios and Kitten : high performance operating systems for scalable virtualized and native supercomputing.

Widener¹,

Jaconette²,

Bridges³

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Since maximizing the amount of computation power delivered to running parallel applications is critical to achieving high performance and scalability, many commercial systems already use Lightweight Kernels (LWKs) with static scheduling, such as CNK [50] in BlueGene HPC systems, and Netra DPS [2] which is mainly used in networking.…”

Section: Introductionmentioning

confidence: 99%

Thread Assignment in Multicore/Multithreaded Processors: A Statistical Approach

Radojković

Carpenter

Moretó

et al. 2016

IEEE Trans. Comput.

View full text Add to dashboard Cite

Abstract-The introduction of multicore/multithreaded processors, comprised of a large number of hardware contexts (virtual CPUs) that share resources at multiple levels, has made process scheduling, in particular assignment of running threads to available hardware contexts, an important aspect of system performance. Nevertheless, thread assignment of applications running on state-of-the art processors is an NP-complete problem. Over the years, numerous studies have proposed heuristic-based algorithms for thread assignment. Since the thread assignment problem is intractable, it is in general impossible to know the performance of the optimal assignment, so the room for improvement of a given algorithm is also unknown. It is therefore hard to decide whether to invest more effort and time to improve an algorithm that may already be close to optimal. In this paper, we present a statistical approach to the thread assignment problem. First, we present a method that predicts the performance of the optimal thread assignment, based on the observed performance of each thread assignment in a random sample. The method is based on Extreme Value Theory (EVT), a branch of statistics that analyses extreme deviations from the population mean. We also propose sample pruning, a method that significantly reduces the time required to apply the statistical method by reducing the number of candidate solutions that need to be measured. Finally, we show that, if no suitable heuristicbased algorithm is available, a sample of several thousand random thread assignments is enough to obtain, with high confidence, an assignment with performance close to optimal. The presented approach is architecture and application independent, and it can be used to address the thread assignment problem in various domains. It is especially well suited for systems in which the workload seldom changes. An example is network systems, which typically provide a constant set of services that are known in advance, with network applications performing a similar processing algorithm for each packet in the system. In this paper, we validate our methods with an industrial case study for a set of multithreaded network applications on an UltraSPARC T2 processor. This article is an extension of our previous work [44], which was published in

show abstract