Auto-tuning of fast fourier transform on graphics processors

Dotsenko, Yuri; Baghsorkhi, Sara S.; Lloyd, Brandon; Govindaraju, Naga K.

doi:10.1145/1941553.1941589

Cited by 53 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous works on fast Fourier transform for the GPU such as [17] includes transposition to improve locality for global memory accesses; the authors did not specify whether the transposition is in-place or not, but we believe it is an out-of-place one. We also believe that their work can be enhanced by employing an in-place transposition algorithm like ours to increase the maximum size of dataset allowed for GPU offloading.…”

Section: In-place and Out-of-place Transposition For Gpusmentioning

confidence: 98%

In-Place Matrix Transposition on GPUs

Gómez-Luna

Sung²,

Chang

et al. 2016

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Matrix transposition is an important algorithmic building block for many numeric algorithms such as FFT. With more and more algebra libraries offloading to GPUs, a high performance in-place transposition becomes necessary. Intuitively, in-place transposition should be a good fit for GPU architectures due to limited available on-board memory capacity and high throughput. However, direct application of CPU in-place transposition algorithms lacks the amount of parallelism and locality required by GPU to achieve good performance. In this paper we present our in-place matrix transposition approach for GPUs that is performed using elementary tile-wise transpositions. We propose low-level optimizations for the elementary transpositions, and find the best performing configurations for them. Then, we compare all sequences of transpositions that achieve full transposition, and detect which is the most favorable for each matrix. We present an heuristic to guide the selection of tile sizes, and compare them to brute-force search. We diagnose the drawback of our approach, and propose a solution using minimal padding. With fast padding and unpadding kernels, the overall throughput is significantly increased. Finally, we compare our method to another recent implementation.

show abstract

Section: In-place and Out-of-place Transposition For Gpusmentioning

confidence: 98%

In-Place Matrix Transposition on GPUs

Gómez-Luna

Sung²,

Chang

et al. 2016

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…Hardware architectures can be dynamically adjusted to target execution speed and much more [18][19][20]. In High Performance Computing it is common to adapt a running application; e.g., tuning FFTs for graphics processing units [21]. Considerable effort has been devoted to MapReduce, which exposes many configurable parameters [22][23][24].…”

Section: Related Workmentioning

confidence: 99%

Automated multi-objective control for self-adaptive software design

Filieri

Hoffmann

Maggio

2015

Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering

View full text Add to dashboard Cite

While software is becoming more complex everyday, the requirements on its behavior are not getting any easier to satisfy. An application should offer a certain quality of service, adapt to the current environmental conditions and withstand runtime variations that were simply unpredictable during the design phase. To tackle this complexity, control theory has been proposed as a technique for managing software's dynamic behavior, obviating the need for human intervention. Control-theoretical solutions, however, are either tailored for the specific application or do not handle the complexity of multiple interacting components and multiple goals. In this paper, we develop an automated control synthesis methodology that takes, as input, the configurable software components (or knobs) and the goals to be achieved. Our approach automatically constructs a control system that manages the specified knobs and guarantees the goals are met. These claims are backed up by experimental studies on three different software applications, where we show how the proposed automated approach handles the complexity of multiple knobs and objectives.

show abstract

“…There has been a rich body of work on optimizations and tuning of GPGPU applications [24,34,68,76,84]. Ryoo et al [84] introduced two metrics to prune optimization space by calculating the utilization and efficiency of GPGPU applications.…”

Section: Other Gpgpu Performance Modeling Techniquesmentioning

confidence: 99%