Towards the automatic optimal mapping of pipeline algorithms

González, Daniel Lombraña; Almeida, Francisco; Moreno, L.; Rodríguez, Casiano

doi:10.1016/s0167-8191(02)00216-8

Cited by 14 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An exact method to solve the optimal mapping problem in homogeneous systems has been presented in [12]. This is a golden-section-like method [16] that takes advantage of the convexity properties of the analytical function.…”

Section: The Enumerative Exact Methodsmentioning

confidence: 99%

Pipelines on heterogeneous systems: models and tools

Almeida

González

Moreno

et al. 2005

Concurrency Computat.: Pract. Exper.

Self Cite

View full text Add to dashboard Cite

SUMMARYWe study the performance of pipeline algorithms in heterogeneous networks. The concept of heterogeneity is not only restricted to the differences in computational power of the nodes, but also refers to the network capabilities. We develop a skeleton tool that allows us an efficient block-cyclic mapping of pipelines on heterogeneous systems. The tool supports pipelines with a number of stages much larger than the number of physical processors available. We derive an analytical formula that allows us to predict the performance of pipelines in heterogeneous systems. According to the analytical complexity formula, numerical strategies to solve the optimal mapping problem are proposed. The computational results prove the accuracy of the predictions and effectiveness of the approach.

show abstract

Section: The Enumerative Exact Methodsmentioning

confidence: 99%

Pipelines on heterogeneous systems: models and tools

Almeida

González

Moreno

et al. 2005

Concurrency Computat.: Pract. Exper.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The brute force search for finding the best mapping can be avoided by using analytical models. Previous studies [17,16,14,7] have proposed analytic models for understanding and optimizing parallel pipelines. While such models can help programmers design a pipeline, they are static and do not adapt to changes in input set and machine configuration.…”

Section: Related Workmentioning

confidence: 99%

“…Previous researchers have also proposed mechanisms to choose the number of threads per stage statically [17,16,14,7] or dynamically [10]. The static mechanisms have the shortcoming that they cannot take the input set, machine configuration, or scalability of stages into account.…”

Section: Introductionmentioning

confidence: 99%

Feedback-directed pipeline parallelism

Suleman

Qureshi

Khubaib

et al. 2010

Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques

View full text Add to dashboard Cite

Extracting high performance from Chip Multiprocessors requires that the application be parallelized. A common software technique to parallelize loops is pipeline parallelism in which the programmer/compiler splits each loop iteration into stages and each stage runs on a certain number of cores. It is important to choose the number of cores for each stage carefully because the core-to-stage allocation determines performance and power consumption. Finding the best core-to-stage allocation for an application is challenging because the number of possible allocations is large, and the best allocation depends on the input set and machine configuration.This paper proposes Feedback-Directed Pipelining (FDP), a software framework that chooses the core-to-stage allocation at run-time. FDP first maximizes the performance of the workload and then saves power by reducing the number of active cores, without impacting performance. Our evaluation on a real SMP system with two Core2Quad processors (8 cores) shows that FDP provides an average speedup of 4.2x which is significantly higher than the 2.3x speedup obtained with a practical profile-based allocation. We also show that FDP is robust to changes in machine configuration and input set.

show abstract

“…Hardware developers use them to analyse emergent architectures [13], software developers use them to tune their codes for a specific architectures [14,15], compiler developers need them to evaluate the performance of the generated code [16]. Usually is built a mathematical abstraction of the program execution to represent the target architecture, the input program and data.…”

mentioning

confidence: 99%