Adaptive optimization for OpenCL programs on embedded heterogeneous systems

Taylor, Benjamin M.; Marco, Vicent Sanz; Wang, Zheng

doi:10.1145/3078633.3081040

Cited by 39 publications

(36 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach avoids the pitfall by automatically learning how to best schedule rendering process. There are also works use statistical modeling or control theories to optimize energy efficiency on mobiles [16], [17], [18], [19], [20], [21]. While not specific to web browsing, these studies demonstrate the advantages and needs for adaptive systemlevel optimizations.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Web Browsing on Mobile Heterogeneous Multi-cores

Ren¹,

Wang²,

Fang³

et al. 2024

IEEE Comput. Arch. Lett.

Self Cite

View full text Add to dashboard Cite

Web browsing is an important application domain, but it imposes a significant power burden on mobile devices. While heterogeneous multi-cores offer the potential for energy-efficient computing, existing web browsers fail to exploit the hardware to optimize mobile web browsing. Our work aims to offer a better way to optimize web browsing on heterogeneous mobile devices. We achieve this by developing a machine learning based approach to predict the optimal processor setting for rendering the web content. The prediction is based on the web content, the network status and the optimization goal. We evaluate our approach by applying it to the Chromium browser and testing it on a representative big.LITTLE mobile platform. We apply our approach to the top 1,000 hottest websites across seven typical networking environments. Our approach achieves over 80% of the performance delivered by a perfect predictor. Our approach achieves over 30%, 50%, and 60% improvement respectively for load time, energy consumption and the energy delay product when compared to two state-of-the-art approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive Web Browsing on Mobile Heterogeneous Multi-cores

Ren¹,

Wang²,

Fang³

et al. 2024

IEEE Comput. Arch. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning has been employed for various optimization tasks [40], including code optimization [7,12,29,30,37,39,41,42,43,44,45,46,51], task scheduling [9,10,11,33,34], model selection [38], etc.…”

Section: Related Workmentioning

confidence: 99%

Optimizing Sparse Matrix–Vector Multiplications on an ARMv8-based Many-Core Architecture

Chen

Fang

Chen

et al. 2019

Int J Parallel Prog

Self Cite

View full text Add to dashboard Cite

Sparse matrix-vector multiplications (SpMV) are common in scientific and HPC applications but are hard to be optimized. While the ARMv8based processor IP is emerging as an alternative to the traditional x64 HPC processor design, there is little study on SpMV performance on such new many-cores. To design efficient HPC software and hardware, we need to understand how well SpMV performs. This work develops a quantitative approach to characterize SpMV performance on a recent ARMv8-based many-core architecture, Phytium FT-2000 Plus (FTP). We perform extensive experiments involved over 9,500 distinct profiling runs on 956 sparse datasets and five mainstream sparse matrix storage formats, and compare FTP against the Intel Knights Landing many-core. We experimentally show that picking the optimal sparse matrix storage format and parameters is non-trivial as the correct decision requires expert knowledge of the input matrix and the hardware. We address the problem by proposing a machine learning based model that predicts the best storage format and parameters using input matrix features. The model automatically specializes to the many-core architectures we considered. The experimental results show that our approach achieves on average 93% of the best-available performance without incurring runtime profiling overhead.

show abstract

“…At compile time, we augment the application with a runtime decision that enables offloading, and at runtime, we dynamically select the best strategy based on the different criteria. Taylor et al [59] use machine learning techniques to help select the optimal computing device for OpenCL programs on embedded heterogeneous systems (big.LITTLE with Mali GPU). The predictive model is trained offline with features extracted from LLVM bitcode.…”

Section: Transparent Accelerationmentioning

confidence: 99%

Transparent Acceleration for Heterogeneous Platforms With Compilation to OpenCL

Riebler

Vaz

Kenter

et al. 2019

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

Multi-accelerator platforms combine CPUs and different accelerator architectures within a single compute node. Such systems are capable of processing parallel workloads very efficiently while being more energy efficient than regular systems consisting of CPUs only. However, the architectures of such systems are diverse, forcing developers to port applications to each accelerator using different programming languages, models, tools, and compilers. Developers not only require domain-specific knowledge but also need to understand the low-level accelerator details, leading to an increase in the design effort and costs.To tackle this challenge, we propose a compilation approach and a practical realization called HTrOP that is completely transparent to the user. HTrOP is able to automatically analyze a sequential CPU application, detect computational hotspots, and generate parallel OpenCL host and kernel code. The potential of HTrOP is demonstrated by offloading hotspots to different OpenCL-enabled resources (currently the CPU, the generalpurpose GPU, and the manycore Intel Xeon Phi) for a broad set of benchmark applications. We present an in-depth evaluation of our approach in terms of performance gains and energy savings, taking into account all static and dynamic overheads. We are able to achieve speedups and energy savings of up to two orders of magnitude, if an application has sufficient computational intensity, when compared to a natively compiled application.This article is an extension of a conference paper/poster at PPoPP'18 [49]. Prior work only outlined the tool flow and the parallelization mechanism. Evaluation is entirely new, including energy measurements and trends over several data points per application.

show abstract

Adaptive optimization for OpenCL programs on embedded heterogeneous systems

Cited by 39 publications

References 41 publications

Adaptive Web Browsing on Mobile Heterogeneous Multi-cores

Adaptive Web Browsing on Mobile Heterogeneous Multi-cores

Optimizing Sparse Matrix–Vector Multiplications on an ARMv8-based Many-Core Architecture

Transparent Acceleration for Heterogeneous Platforms With Compilation to OpenCL

Contact Info

Product

Resources

About