SilkRoad: a multithreaded runtime system with software distributed shared memory for SMP clusters

Wong, Weng Fai; Feng, Ming-Dong; Yuen, C. K.

doi:10.1109/clustr.2000.889067

Cited by 18 publications

(13 citation statements)

References 13 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples include Brazos [40], CVM [23], SilkRoad [30] and String [21,36]. They improved upon the early DSM systems by adding threads to exploit data locality within a cluster.…”

Section: Introductionmentioning

confidence: 99%

Distributed shared arrays: A distributed virtual machine with mobility support for reconfiguration

Wims

et al. 2006

Cluster Comput

View full text Add to dashboard Cite

Distributed Shared Arrays (DSA) is a distributed virtual machine that supports Java-compliant multithreaded programming with mobility support for system reconfiguration in distributed environments. The DSA programming model allows programmers to explicitly control data distribution so as to take advantage of the deep memory hierarchy, while relieving them from error-prone orchestration of communication and synchronization at run-time. The DSA system is developed as an integral component of mobility support middleware for Grid computing so that DSA-based virtual machines can be reconfigured to adapt to the varying resource supplies or demand over the course of a computation. The DSA runtime system also features a directorybased cache coherence protocol in support of replication of user-defined sharing granularity and a communication proxy mechanism for reducing network contention. System reconfiguration is achieved by a DSA service migration mechanism, which moves the DSA service and residing computational agents between physical servers for load balancing and fault resilience. We demonstrate the programmability of the model in a number of parallel applications and evaluate its performance by application benchmark programs, in particular, the impact of the coherence granularity and service migration overhead.

show abstract

“…Examples include Brazos [40], CVM [23], SilkRoad [30] and String [21,36]. They improved upon the early DSM systems by adding threads to exploit data locality within a cluster.…”

Section: Introductionmentioning

confidence: 99%

Distributed shared arrays: A distributed virtual machine with mobility support for reconfiguration

Wims

et al. 2006

Cluster Comput

View full text Add to dashboard Cite

show abstract

“…Among them, Cilk [7] only supports sharedmemory machines, CilkNOW [6] and DCPAR [11] run on localarea, distributed-memory systems, but do not support shared data. SilkRoad [19] is a version of Cilk for distributed memory that uses a software DSM to provide shared memory to the programmer, targeting at small-scale, local-area systems. Alice [9] and Flagship [24] offer specific hardware solutions for parallel divide-andconquer programs.…”

Section: Related Workmentioning

confidence: 99%

Efficient load balancing for wide-area divide-and-conquer applications

2001

View full text Add to dashboard Cite

Divide-and-conquer programs are easily parallelized by letting the programmer annotate potential parallelism in the form of spawn and sync constructs. To achieve efficient program execution, the generated work load has to be balanced evenly among the available CPUs. For single cluster systems, Random Stealing (RS) is known to achieve optimal load balancing. However, RS is inefficient when applied to hierarchical wide-area systems where multiple clusters are connected via wide-area networks (WANs) with high latency and low bandwidth.In this paper, we experimentally compare RS with existing loadbalancing strategies that are believed to be efficient for multi-cluster systems, Random Pushing and two variants of Hierarchical Stealing. We demonstrate that, in practice, they obtain less than optimal results. We introduce a novel load-balancing algorithm, Clusteraware Random Stealing (CRS) which is highly efficient and easy to implement. CRS adapts itself to network conditions and job granularities, and does not require manually-tuned parameters. Although CRS sends more data across the WANs, it is faster than its competitors for 11 out of 12 test applications with various WAN configurations. It has at most 4% overhead in run time compared to RS on a single, large cluster, even with high wide-area latencies and low wide-area bandwidths. These strong results suggest that divideand-conquer parallelism is a useful model for writing distributed supercomputing applications on hierarchical wide-area systems.

show abstract

“…Work-stealing is a practical and provably efficient method for scheduling dynamic multithreaded computations [8,12,27,34,44]. Since work-stealing schedulers employ distributed control, the task scheduler has no direct information about the instantaneous parallelism of the job.…”

Section: Resultsmentioning

confidence: 99%

Adaptive scheduling with parallelism feedback

Agrawal

Hsu

et al. 2006

Proceedings of the Eleventh ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

View full text Add to dashboard Cite

Multiprocessor scheduling in a shared multiprogramming environment is often structured as two-level scheduling, where a kernellevel job scheduler allots processors to jobs and a user-level task scheduler schedules the work of a job on the allotted processors. In this context, the number of processors allotted to a particular job may vary during the job's execution, and the task scheduler must adapt to these changes in processor resources. For overall system efficiency, the task scheduler should also provide parallelism feedback to the job scheduler to avoid the situation where a job is allotted processors that it cannot use productively.We present an adaptive task scheduler for multitasked jobs with dependencies that provides continual parallelism feedback to the job scheduler in the form of requests for processors. Our scheduler guarantees that a job completes near optimally while utilizing at least a constant fraction of the allotted processor cycles. Our scheduler can be applied to schedule data-parallel programs, such as those written in High Performance Fortran (HPF), *Lisp, C*, NESL, and ZPL.Our analysis models the job scheduler as the task scheduler's adversary, challenging the task scheduler to be robust to the system environment and the job scheduler's administrative policies. For example, the job scheduler can make available a huge number of processors exactly when the job has little use for them. To analyze the performance of our adaptive task scheduler under this stringent adversarial assumption, we introduce a new technique called "trim analysis," which allows us to prove that our task scheduler performs poorly on at most a small number of time steps, exhibiting nearoptimal behavior on the vast majority.To be precise, suppose that a job has work T1 and critical-path length T∞ and is running on a machine with P processors. Using trim analysis, we prove that our scheduler completes the job in O(T1/ P + T∞ + L lg P ) time steps, where L is the length of a scheduling quantum and P denotes the O(T∞ + L lg P )-trimmed availability. This quantity is the average of the processor availabilThis research was supported in part by the Singapore-MIT Alliance and NSF Grant ACI-0324974. Yuxiong He is a Visiting Scholar at MIT CSAIL and a Ph.D. candidate at the National University of Singapore. Wen Jing Hsu is a Visiting Scientist at MIT CSAIL and Associate Professor at Nanyang Technological University.Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ity over all time steps excluding the O(T∞ + L lg P ) time steps with the highest processor availability. When T1/T∞ P (the job's parallelism dominates the O(T∞ + L lg P )-trimmed availability), the job ach...

show abstract

SilkRoad: a multithreaded runtime system with software distributed shared memory for SMP clusters

Cited by 18 publications

References 13 publications

Distributed shared arrays: A distributed virtual machine with mobility support for reconfiguration

Distributed shared arrays: A distributed virtual machine with mobility support for reconfiguration

Efficient load balancing for wide-area divide-and-conquer applications

Adaptive scheduling with parallelism feedback

Contact Info

Product

Resources

About