skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Evaluation of the Single-precision Floatingpoint Vector Add Kernel Using the Intel FPGA SDK for OpenCL

Abstract

Open Computing Language (OpenCL) is a high-level language that enables software programmers to explore Field Programmable Gate Arrays (FPGAs) for application acceleration. The Intel FPGA software development kit (SDK) for OpenCL allows a user to specify applications at a high level and explore the performance of low-level hardware acceleration. In this report, we present the FPGA performance and power consumption results of the single-precision floating-point vector add OpenCL kernel using the Intel FPGA SDK for OpenCL on the Nallatech 385A FPGA board. The board features an Arria 10 FPGA. We evaluate the FPGA implementations using the compute unit duplication and kernel vectorization optimization techniques. On the Nallatech 385A FPGA board, the maximum compute kernel bandwidth we achieve is 25.8 GB/s, approximately 76% of the peak memory bandwidth. The power consumption of the FPGA device when running the kernels ranges from 29W to 42W.

Authors:
 [1];  [1];  [1];  [1]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1357902
Report Number(s):
ANL/ALCF-17/2
135203
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; OpenCL; FPGA; vector add

Citation Formats

Jin, Zheming, Yoshii, Kazutomo, Finkel, Hal, and Cappello, Franck. Evaluation of the Single-precision Floatingpoint Vector Add Kernel Using the Intel FPGA SDK for OpenCL. United States: N. p., 2017. Web. doi:10.2172/1357902.
Jin, Zheming, Yoshii, Kazutomo, Finkel, Hal, & Cappello, Franck. Evaluation of the Single-precision Floatingpoint Vector Add Kernel Using the Intel FPGA SDK for OpenCL. United States. doi:10.2172/1357902.
Jin, Zheming, Yoshii, Kazutomo, Finkel, Hal, and Cappello, Franck. Thu . "Evaluation of the Single-precision Floatingpoint Vector Add Kernel Using the Intel FPGA SDK for OpenCL". United States. doi:10.2172/1357902. https://www.osti.gov/servlets/purl/1357902.
@article{osti_1357902,
title = {Evaluation of the Single-precision Floatingpoint Vector Add Kernel Using the Intel FPGA SDK for OpenCL},
author = {Jin, Zheming and Yoshii, Kazutomo and Finkel, Hal and Cappello, Franck},
abstractNote = {Open Computing Language (OpenCL) is a high-level language that enables software programmers to explore Field Programmable Gate Arrays (FPGAs) for application acceleration. The Intel FPGA software development kit (SDK) for OpenCL allows a user to specify applications at a high level and explore the performance of low-level hardware acceleration. In this report, we present the FPGA performance and power consumption results of the single-precision floating-point vector add OpenCL kernel using the Intel FPGA SDK for OpenCL on the Nallatech 385A FPGA board. The board features an Arria 10 FPGA. We evaluate the FPGA implementations using the compute unit duplication and kernel vectorization optimization techniques. On the Nallatech 385A FPGA board, the maximum compute kernel bandwidth we achieve is 25.8 GB/s, approximately 76% of the peak memory bandwidth. The power consumption of the FPGA device when running the kernels ranges from 29W to 42W.},
doi = {10.2172/1357902},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Apr 20 00:00:00 EDT 2017},
month = {Thu Apr 20 00:00:00 EDT 2017}
}

Technical Report:

Save / Share: