Mixed Model Universal Software Thread-Level Speculation

Cao, Zhen; Verbrugge, Clark

doi:10.1109/icpp.2013.79

Cited by 13 publications

(5 citation statements)

References 23 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the performance evaluation, the vital measurement is speedup, which represents the improvement of the execution speed that a task executed on two similar architectures with different resources. Usually, given the execution time of a parallelized program on N working nodes T P , and of the original sequential program T S , the absolute speedup (shown in formula ) is defined as T S / T P

Speedup = \frac{T_{s}}{T_{p}} \times 100 % .

…”

Section: Methodsmentioning

confidence: 99%

A speculative parallel simulated annealing algorithm based on Apache Spark

Wang

Zhao

Liu

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Simulated annealing (SA) is an effective method for solving unconstrained optimization problems and has been widely used in machine learning and neural network. Nowadays, in order to optimize complex problems with big data, the SA algorithm has been implemented on big data platform and obtains a certain speedup. However, the efficiency for such implementation is still limited because the conventional SA algorithm still runs with low parallelism on new platforms and the computing resource cannot be fully utilized. For these problems, this paper raised a speculative parallel SA algorithm based on Apache Spark to expand the algorithm's parallelism and enhance its efficiency. In this paper, first, the inner dependencies, which stop conventional algorithm, run in parallel, are analyzed. Then, based on the analysis, the Software Thread-Level Speculation technique is employed to help the conventional algorithm overcome the dependencies and make it run concurrently. Finally, a new parallel SA algorithm with speculation mechanism is proposed and implemented on Apache Spark. The experiments show that, for big data problems, the proposed algorithm could achieve an optimal parallelism when comparing the traditional algorithm without speculation on Apache Spark. Moreover, the execution efficiency of simulated annealing process can be markedly enhanced by the proposed algorithm. KEYWORDSApache Spark, parallel computing, simulated annealing, thread level speculation INTRODUCTIONSimulated annealing (SA) is a probabilistic technique for approximating the global optimum of a given function. Specifically, it is a metaheuristic to approximate global optimization in a large search space. 1 However, with the data growing larger, traditional SA algorithm is barely to fulfill the present speed request of data processing. This is because, for one thing, the traditional method is inefficient and poorly paralleled, for another, the computing power the present platforms could afford is not enough to support large scale processing.To solve this problem, parallel programming is frequently used in accelerating the conventional SA algorithm. Researchers have successfully implemented parallelized SA algorithm on multicore platforms and achieved certain speedup. Moreover, a good approach to process large-scale data is to make use of enormous computing power offered by modern distributed computing platforms (or called big data platforms) like ApacheHadoop 2 or Apache Spark. 3 These popular platforms adopt MapReduce, which is a specialization of the split-apply-combine strategy for data analysis, as their programming model. A standard MapReduce program is composed by pairs of Map operations (whose job is to sorting or filtering data) and Reduce operations (whose job is to do summary of the result by Map operations), and a high parallelism of a MapReduce model is obtained by marshalling the operation pairs and performing them in distributed servers in parallel. The platforms that adopt MapReduce model often split the input, turn the large scale prob...

show abstract

Speedup = \frac{T_{s}}{T_{p}} \times 100 % .

…”

Section: Methodsmentioning

confidence: 99%

A speculative parallel simulated annealing algorithm based on Apache Spark

Wang

Zhao

Liu

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Speculative parallelism creates parallel running threads, maintaining the program's chronological order while parallelizing implicit (speculative or dependent) threads. Both hardware [42][43][44] and software 45,46 architecture have been used to investigate speculative parallelism. Originally, Dang and Rauchwerger LLVM: a compilation 47 showed that it could be used to parallelize loops with distinct data access, particularly arrays.…”

Section: Automatic and Speculative Parallelizing Techniquesmentioning

confidence: 99%

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

Kumar

Singh

Aggarwal³

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

In the last few decades, technology advancements have paved the way for the creation of intelligent and autonomous systems that utilize complex calculations which are both time‐consuming and central processing unit intensive. As a consequence, parallel processing systems are gaining popularity to enhance overall computer performance. Programmers should be able to efficiently utilize available hardware resources with parallelization in an ideal world. Through the automatic parallelization of sequential code, multithreading can be executed without extra supervision. However, a wide range of software dependencies prevents this from being feasible. An architectural framework for speculative parallelization along with an efficient memory analysis and computational algorithms for the code generation are proposed that can provide optimal performance. Furthermore, a suitable support of hardware design as a runtime library to the proposed architectural framework is presented which can be used to recover misspeculated results during execution to minimize speculative parallelism overhead. The implementation makes use of the Low‐Level Virtual Machine compiler infrastructure and is tested on numerous benchmarks, thus making it highly scalable in terms of programming languages and architectures. According to our experimental results, there is significant potential for speedup increase. In comparison to the overall function speedup, that is, geomean speedup of 5.2× approximately when using the proposed architecture without hardware support, the proposed architectural framework and algorithm with hardware support give an average geomean speedup of 7.0× approximately on the given benchmark which is written in C/C++.

show abstract

“…Usually, given the execution time of a parallelized program on N cores T p , and of the original sequential program T s , the absolute speedup (shown in formula (5)) is defined as T s /T p [33]:…”

Section: Index Variable Settingmentioning

confidence: 99%

Qinling: A Parametric Model in Speculative Multithreading

Zhao

Liu

2017

Symmetry

View full text Add to dashboard Cite

Speculative multithreading (SpMT) is a thread-level automatic parallelization technique that can accelerate sequential programs, especially for irregular applications that are hard to be parallelized by conventional approaches. Thread partition plays a critical role in SpMT. Conventional machine learning-based thread partition approaches applied machine learning to offline guide partition, but could not explicitly explore the law between partition and performance. In this paper, we build a parametric model (Qinling) with a multiple regression method to discover the inherent law between thread partition and performance. The paper firstly extracts unpredictable parameters that determine the performance of thread partition in SpMT; secondly, we build a parametric model Qinling with extracted parameters and speedups, and train Qinling offline, as well as apply it to predict the theoretical speedups of unseen applications. Finally, validation is done. Prophet, which consists of an automatic parallelization compiler and a multi-core simulator, is used to obtain real speedups of the input programs. Olden and SPEC2000 benchmarks are used to train and validate the parametric model. Experiments show that Qinling delivers a good performance to predict speedups of unseen programs, and provides feedback guidance for Prophet to obtain the optimal partition parameters.

show abstract

Mixed Model Universal Software Thread-Level Speculation

Cited by 13 publications

References 23 publications

A speculative parallel simulated annealing algorithm based on Apache Spark

A speculative parallel simulated annealing algorithm based on Apache Spark

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

Qinling: A Parametric Model in Speculative Multithreading

Contact Info

Product

Resources

About