poster

ViennaCL++: Enable TensorFlow/Eigen via ViennaCL with OpenCL C++ Flow

Authors:

Tai-Liang Chen,

Shih-Huan Chien,

Jenq-Kuen LeeAuthors Info & Claims

IWOCL '18: Proceedings of the International Workshop on OpenCL

Article No.: 28, Pages 1 - 2

https://doi.org/10.1145/3204919.3207894

Published: 14 May 2018 Publication History

Get Access

Abstract

This paper presents the ViennaCL++, an OpenCL C++ kernel library for Vienna Computing Library (ViennaCL) combined with TensorFlow/Eigen library to enable acceleration and optimization of linear algebraic computing. Previously, TensorFlow would invoke Eigen for solvers. To enable OpenCL flow, one can invoke Eigen via ViennaCL to generate kernel programs for GPU computation. In order to support the features of the latest specification, the linear algebraic kernel library is migrated to OpenCL C++ with C++ features in ViennaCL++ to construct the OpenCL flow for TensorFlow and its underlying computational library Eigen. The software flow is based on the state-of-the-art specification of OpenCL and OpenCL C++ kernel langauge, as well as SPIR-V binary intermediate representation. The experimental results of ViennaCL++ which includes C++ class and SPIR-V flow are achieving 8 times and 49 times speedup for BLAS2 and BLAS3 operations compared to Eigen library on the x86_64 of Intel hardware. Overall, these results indicate that the performance of ViennaCL++ runtime execution with OpenCL C++ and SPIR-V flow is similar to traditional OpenCL C flow. Note that the Intel OpenCL 2.1 compiler is equipped with most Khronos OpenCL 2.2 (OpenCL C++) linguistic to support the experiment.

References

[1]

OpenCL Overview. 2018. https://www.khronos.org/opencl/.

Google Scholar

[2]

Karl Rupp, Philippe Tillet, Florian Rudolf, Josef Weinbub, Andreas Morhammer, Tibor Grasser, Ansgar JuÌĹngel, and Siegfried Selberherr. 2016. ViennaCL---Linear Algebra Library for Multi-and Many-Core Architectures. SIAM Journal on Scientific Computing 38, 5 (2016), S412--S439.

Digital Library

Google Scholar

[3]

Shao-Chung Wang, Li-Chen Kan, Yuan-Shin Hwang, and Jenq-Kuen Lee. 2016. Energy efficient affine register file for GPU microarchitecture. In Parallel Processing Workshops (ICPPW), 2016 45th International Conference on. IEEE, 52--58.

Crossref

Google Scholar

[4]

Shao-Chung Wang, Li-Chen Kan, Chao-Lin Lee, Yuan-Shin Hwang, and Jenq-Kuen Lee. 2017. Architecture and Compiler Support for GPUs Using Energy-Efficient Affine Register Files. ACM Transactions on Design Automation of Electronic Systems (TODAES) 23, 2 (2017), 18.

Digital Library

Google Scholar

[5]

Chun-Chieh Yang, Shao-Chung Wang, Min-Yi Hsu, Yuan-Ming Chang, Yuan-Shin Hwang, and Jenq-Kuen Lee. 2017. OpenCL 2.0 Compiler Adaptation on LLVM for PTX Simulators. In Parallel Processing Workshops (ICPPW), 2017 46th International Conference on. IEEE, 53--58.

Crossref

Google Scholar

Cited By

View all

Fumero JRethy GStratikopoulos AFoutris NKotselidis CRosà AHenz M(2023)Beehive SPIR-V Toolkit: A Composable and Functional API for Runtime SPIR-V Code GenerationProceedings of the 15th ACM SIGPLAN International Workshop on Virtual Machines and Intermediate Languages10.1145/3623507.3623555(61-72)Online publication date: 18-Oct-2023
https://dl.acm.org/doi/10.1145/3623507.3623555
Chang PChen THuang YYu MLee J(2022)C++OpenCL4TVM: Support C++OpenCL Kernel for TVM NN OperatorsProceedings of the 10th International Workshop on OpenCL10.1145/3529538.3530001(1-2)Online publication date: 10-May-2022
https://dl.acm.org/doi/10.1145/3529538.3530001
Chang PChen TLee J(2021)Enabling the Use of C++20 Unseq Execution Policy for OpenCLProceedings of the 9th International Workshop on OpenCL10.1145/3456669.3456674(1-2)Online publication date: 27-Apr-2021
https://dl.acm.org/doi/10.1145/3456669.3456674
Show More Cited By

Index Terms

ViennaCL++: Enable TensorFlow/Eigen via ViennaCL with OpenCL C++ Flow
1. Software and its engineering
  1. Software notations and tools
    1. Context specific languages
      1. Specialized application languages
    2. Development frameworks and environments
      1. Application specific development environments

Recommendations

C++OpenCL4TVM: Support C++OpenCL Kernel for TVM NN Operators
IWOCL '22: Proceedings of the 10th International Workshop on OpenCL

In an era of artificial intelligence (AI), OpenCL serves as one of the AI frameworks’ back-ends, notably, the tensor virtual machine (TVM), which focuses on the inference side of neural networks. After optimizing a computational graph, TVM traverses the ...
Automatic performance optimization in ViennaCL for GPUs
POOSC '10: Proceedings of the 9th Workshop on Parallel/High-Performance Object-Oriented Scientific Computing

Highly parallel computing architectures such as graphics processing units (GPUs) pose several new challenges for scientific computing, which have been absent on single core CPUs. However, a transition from existing serial code to parallel code for GPUs ...
HIPCL: Tool for Porting CUDA Applications to Advanced OpenCL Platforms Through HIP
IWOCL '20: Proceedings of the International Workshop on OpenCL

Heterogeneous-compute Interface for Portability (HIP), is an open-source C++ runtime API and a kernel language. It is designed to be compatible with CUDA and to deliver close to native performance on CUDA platforms while exposing additional low-level ...

Comments

Information & Contributors

Information

Published In

IWOCL '18: Proceedings of the International Workshop on OpenCL

May 2018

108 pages

ISBN:9781450364393

DOI:10.1145/3204919

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

In-Cooperation

Huawei Technologies Co. Ltd.: Huawei Technologies Co. Ltd.
Khronos: Khronos Group
Xilinx: Xilinx Inc.
Codeplay: Codeplay Software Ltd.
Intel: Intel
The University of Bristol: The University of Bristol

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 May 2018

Check for updates

Author Tags

Qualifiers

Poster
Research
Refereed limited

Funding Sources

This work was supported in part by the Ministry of Science and Technology of Taiwan

Conference

IWOCL '18

IWOCL '18: International Workshop on OpenCL

May 14 - 16, 2018

Oxford, United Kingdom

Acceptance Rates

IWOCL '18 Paper Acceptance Rate 16 of 33 submissions, 48%;

Overall Acceptance Rate 84 of 152 submissions, 55%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
170
Total Downloads

Downloads (Last 12 months)8
Downloads (Last 6 weeks)1

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Fumero JRethy GStratikopoulos AFoutris NKotselidis CRosà AHenz M(2023)Beehive SPIR-V Toolkit: A Composable and Functional API for Runtime SPIR-V Code GenerationProceedings of the 15th ACM SIGPLAN International Workshop on Virtual Machines and Intermediate Languages10.1145/3623507.3623555(61-72)Online publication date: 18-Oct-2023
https://dl.acm.org/doi/10.1145/3623507.3623555
Chang PChen THuang YYu MLee J(2022)C++OpenCL4TVM: Support C++OpenCL Kernel for TVM NN OperatorsProceedings of the 10th International Workshop on OpenCL10.1145/3529538.3530001(1-2)Online publication date: 10-May-2022
https://dl.acm.org/doi/10.1145/3529538.3530001
Chang PChen TLee J(2021)Enabling the Use of C++20 Unseq Execution Policy for OpenCLProceedings of the 9th International Workshop on OpenCL10.1145/3456669.3456674(1-2)Online publication date: 27-Apr-2021
https://dl.acm.org/doi/10.1145/3456669.3456674
Yu MChen TLee J(2020)Accelerating NNEF Framework on OpenCL Devices Using clDNNProceedings of the International Workshop on OpenCL10.1145/3388333.3388655(1-2)Online publication date: 27-Apr-2020
https://dl.acm.org/doi/10.1145/3388333.3388655
Liao WChang YWang SYang CLee JHwang Y(2018)Scheduling Methods to Optimize Dependent Programs for GPU ArchitectureWorkshop Proceedings of the 47th International Conference on Parallel Processing10.1145/3229710.3229723(1-8)Online publication date: 13-Aug-2018
https://dl.acm.org/doi/10.1145/3229710.3229723

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

References

Cited By

Index Terms

Recommendations

C++OpenCL4TVM: Support C++OpenCL Kernel for TVM NN Operators

Automatic performance optimization in ViennaCL for GPUs

HIPCL: Tool for Porting CUDA Applications to Advanced OpenCL Platforms Through HIP

Comments

Information

Published In

In-Cooperation

Publisher

Publication History

Check for updates

Author Tags

Qualifiers

Funding Sources

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations