Autotuning in High-Performance Computing Applications

Balaprakash, Prasanna; Dongarra, Jack; Gamblin, Todd; Hall, Mary; Hollingsworth, Jeffrey K.; Norris, Boyana; Vuduc, Richard

doi:10.1109/jproc.2018.2841200

Cited by 89 publications

(66 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However from the end-user point of view, a manual selection of the application configuration it is a non-trivial task. Application autotuning [5] is a wellknown field in literature and there are several available tools [16], [17], [18] that can select the most suitable configuration according to application requirements. In this section, we explain how tuning can be automatically done by the application itself according to an execution time budget allocated by the end-user.…”

Section: Application Autotuningmentioning

confidence: 99%

“…Application autotuning. Autotuning in HPC is a wellknown research area [5] where several libraries and tools exist to support the automatic optimization of software knobs. Among the libraries that are tailored to specific tasks some examples are ATLAS [45] for matrix multiplication routines, FTTW [46] for FFT operations, OSKI [47] for sparse matrix kernels, and SPIRAL [48] for digital signal processing.…”

Section: Related Workmentioning

confidence: 99%

“…The main goal of the proposed approach is to provide tunable approximations to explore performance-accuracy tradeoffs during the docking task, and autotuning [5] to support the optimization phase. In this paper, tradeoffs are enabled enhancing GeoDock-MA by exposing five tunable software knobs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

et al. 2020

View full text Add to dashboard Cite

The drug discovery process involves several tasks to be performed in vivo, in vitro and in silico. Molecular docking is a task typically performed in silico. It aims at finding the three-dimensional pose of a given molecule when it interacts with the target protein binding site. This task is often done for virtual screening a huge set of molecules to find the most promising ones, which will be forwarded to the later stages of the drug discovery process. Given the huge complexity of the problem, molecular docking cannot be solved by exploring the entire space of the ligand poses. State-of-the-art approaches face the problem by sampling the space of the ligand poses to generate results in a reasonable time budget. In this work, we improve the geometric approach to molecular docking by introducing tunable approximations. In particular, we analyzed and enriched the original implementation with tunable software knobs to explore and control the performance-accuracy tradeoffs. We modeled time-to-solution of the virtual screening task as a function of software knobs, input data features, and available computational resources. Therefore, the application can autotune its configuration according to a user-defined time budget. We used a Mini-App derived by LiGenDock -a state-of-the-art molecular docking application -to validate the proposed approach. We run the enhanced Mini-App on an HPC system by using a very large database of pockets and ligands. The proposed approach exposes a time-to-solution interval spanning more than one order of magnitude with accuracy degradation up to 30%, more in general providing different accuracy levels according to the needs of the virtual screening campaign.

show abstract

Section: Application Autotuningmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A tighter integration into applications has been recently identified as one of the main challenges in autotuning [6]. Kernel Tuning Toolkit was designed to simplify the integration process.…”

Section: Introductionmentioning

confidence: 99%

“…The search for efficient tuning configurations may be challenging due to the discrete and non-linear nature of tuning spaces [6]. Therefore, large tuning spaces are usu- 1 We adopt the nomenclature from [6]. ally impossible to explore during application runtime.…”

Section: Introductionmentioning

confidence: 99%

A benchmark set of highly-efficient CUDA and OpenCL kernels and its dynamic autotuning with Kernel Tuning Toolkit

Petrovič

Střelák

Hozzová

et al. 2020

Future Generation Computer Systems

View full text Add to dashboard Cite

In recent years, the heterogeneity of both commodity and supercomputers hardware has increased sharply. Accelerators, such as GPUs or Intel Xeon Phi co-processors, are often key to improving speed and energy efficiency of highly-parallel codes. However, due to the complexity of heterogeneous architectures, optimization of codes for a certain type of architecture as well as porting codes across different architectures, while maintaining a comparable level of performance, can be extremely challenging. Addressing the challenges associated with performance optimization and performance portability, autotuning has gained a lot of interest. Autotuning of performance-relevant source-code parameters allows to automatically tune applications without hard coding optimizations and thus helps with keeping the performance portable. In this paper, we introduce a benchmark set of ten autotunable kernels for important computational problems implemented in OpenCL or CUDA. Using our Kernel Tuning Toolkit, we show that with autotuning most of the kernels reach near-peak performance on various GPUs and outperform baseline implementations on CPUs and Xeon Phis. Our evaluation also demonstrates that autotuning is key to performance portability. In addition to offline tuning, we also introduce dynamic autotuning of code optimization parameters during application runtime. With dynamic tuning, the Kernel Tuning Toolkit enables applications to re-tune performance-critical kernels at runtime whenever needed, for example, when input data changes. Although it is generally believed that autotuning spaces tend to be too large to be searched during application runtime, we show that it is not necessarily the case when tuning spaces are designed rationally. Many of our kernels reach near peak-performance with moderately sized tuning spaces that can be searched at runtime with acceptable overhead. Finally we demonstrate, how dynamic performance tuning can be integrated into a real-world application from cryo-electron microscopy domain.

show abstract

Future Trends

2023

Multiscale Modelling in Biomedical Engineering

View full text Add to dashboard Cite

Autotuning in High-Performance Computing Applications

Cited by 89 publications

References 59 publications

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

A benchmark set of highly-efficient CUDA and OpenCL kernels and its dynamic autotuning with Kernel Tuning Toolkit

Future Trends

Contact Info

Product

Resources

About