Automatic OpenCL Device Characterization: Guiding Optimized Kernel Design

Thoman, Peter; Kofler, Klaus; Studt, Heiko; Thomson, John; Fahringer, Thomas

doi:10.1007/978-3-642-23397-5_43

Cited by 26 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is related to the weaker performance of the GPU (Ati Radeon HD5870) in mc1. Its VLIW architecture with very wide instruction width and high branch miss penalty would require specific fine-tuning of each code to perform well [33]. However, none of our test cases was tuned for a specific device.…”

Section: Analysis Of the Resultsmentioning

confidence: 99%

An automatic input-sensitive approach for heterogeneous task partitioning

Kofler

Grasso

Cosenza

et al. 2013

Proceedings of the 27th International ACM Conference on International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

Kofler, K.; Grasso, I.; Cosenza, B.; Fahringer, T.: An automatic input-sensitive approach for heterogeneous task partitioning. ABSTRACTUnleashing the full potential of heterogeneous systems, consisting of multi-core CPUs and GPUs, is a challenging task due to the difference in processing capabilities, memory availability, and communication latencies of different computational resources.In this paper we propose a novel approach that automatically optimizes task partitioning for different (input) problem sizes and different heterogeneous multi-core architectures. We use the Insieme source-to-source compiler to translate a single-device OpenCL program into a multi-device OpenCL program. The Insieme Runtime System then performs dynamic task partitioning based on an offline-generated prediction model. In order to derive the prediction model, we use a machine learning approach based on Artificial Neural Networks (ANN) that incorporates static program features as well as dynamic, input sensitive features. Principal component analysis have been used to further improve the task partitioning. Our approach has been evaluated over a suite of 23 programs and respectively achieves a performance improvement of 22% and 25% compared to an execution of the benchmarks on a single CPU and a single GPU which is equal to 87.5% of the optimal performance.

show abstract

Section: Analysis Of the Resultsmentioning

confidence: 99%

An automatic input-sensitive approach for heterogeneous task partitioning

Kofler

Grasso

Cosenza

et al. 2013

Proceedings of the 27th International ACM Conference on International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is a result of the weaker performance of the GPU in mc1. The VLIW architecture with a very wide instruction width and high branch miss penalty would require specific fine-tuning of each code to perform well [7]. However, none of our test cases was tuned for a specific device.…”

Section: Discussionmentioning

confidence: 99%

Automatic problem size sensitive task partitioning on heterogeneous parallel systems

et al. 2013

Self Cite

View full text Add to dashboard Cite

In this paper we propose a novel approach which automatizes task partitioning in heterogeneous systems. Our framework is based on the Insieme Compiler and Runtime infrastructure [1]. The compiler translates a single-device OpenCL program into a multi-device OpenCL program. The runtime system then performs dynamic task partitioning based on an offline-generated prediction model. In order to derive the prediction model, we use a machine learning approach that incorporates static program features as well as dynamic, input sensitive features. Our approach has been evaluated over a suite of 23 programs and achieves performance improvements compared to an execution of the benchmarks on a single CPU and a single GPU only.

show abstract

“…In fact, the families of OpenCL benchmarks that support multiple devices that we know of, such as the SNU NPB suite [19], use this approach to exchange data between devices. Also, the benchmarks to characterize OpenCL [22] have never compared these two possibilities as far as we know. We have found, however, that clEnqueueCopyBuffer can be in fact much slower than the two sequenced transfers possibility in some systems.…”

Section: Implementation Detailsmentioning

confidence: 99%

Developing adaptive multi-device applications with the Heterogeneous Programming Library

et al. 2015

View full text Add to dashboard Cite

The usage of heterogeneous devices presents two main problems. One is their complex programming, a problem that grows when multiple devices are used. The second issue is that even if the codes for these devices can be portable on top of OpenCL, they lack performance portability, effectively requiring specialized implementations for each device to get good performance. In this paper we extend the Heterogeneous Programming Library (HPL), which improves the usability of heterogeneous systems on top of OpenCL, to better handle both issues. First, we provide HPL with mechanisms to support the implementation of any multi-device application that requires arbitrary patterns of communication between several devices and a host memory. In a second stage HPL is improved with an adaptive scheme to optimize communications between devices depending on the execution environment. An evaluation using benchmarks with very different nature shows that HPL reduces the SLOCs and programming effort of OpenCL applications by 27 and 43 %, respectively, while improving the performance of applications that exchange data between devices by 28 % on average.

show abstract

Automatic OpenCL Device Characterization: Guiding Optimized Kernel Design

Cited by 26 publications

References 7 publications

An automatic input-sensitive approach for heterogeneous task partitioning

An automatic input-sensitive approach for heterogeneous task partitioning

Automatic problem size sensitive task partitioning on heterogeneous parallel systems

Developing adaptive multi-device applications with the Heterogeneous Programming Library

Contact Info

Product

Resources

About