OpenCL Performance on the Intel Heterogeneous Architecture Research Platform
- 22 September 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Abstract
The fundamental operation of matrix multiplication is ubiquitous across a myriad of disciplines. Yet, the identification of new optimizations for matrix multiplication remains relevant for emerging hardware architectures and heterogeneous systems. Frameworks such as OpenCL enable computation orchestration on existing systems, and its availability using the Intel High Level Synthesis compiler allows users to architect new designs for reconfigurable hardware using C/C++. Using the HARPv2 as a vehicle for exploration, we investigate the utility of several traditional matrix multiplication optimizations to better understand the performance portability of OpenCL and the implications for such optimizations on cache coherent heterogeneous architectures. Our results give targeted insights into the applicability of best practices that were designed for existing architectures when used on emerging heterogeneous systems.Keywords
Funding Information
- NSF (CNS-1763503,CNS-1814739)
This publication has 17 references indexed in Scilit:
- A survey of deep neural network architectures and their applicationsNeurocomputing, 2017
- A quantitative analysis on microarchitectures of modern CPU-FPGA platforms2016
- Exascale computing and big dataCommunications of the ACM, 2015
- FPGA accelerator for floating-point matrix multiplicationIET Computers & Digital Techniques, 2012
- Multivariate Gaussian Random Number Generation Targeting Reconfigurable HardwareACM Transactions on Reconfigurable Technology and Systems, 2008
- GPU ComputingProceedings of the IEEE, 2008
- Single-chip gigabit mixed-version IP router on Virtex-II Pro2003
- Dynamic hardware/software partitioning2003
- Garp: a MIPS processor with a reconfigurable coprocessor2002
- Efficient FPGA-based QPSK Demodulation Loops: Application to the DVB StandardLecture Notes in Computer Science, 2002