Understanding Performance Differences of FPGAs and GPUs

Proceedings - 26th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2018

Volumn , Issue , 2018, Pages 93-96

  Cong, Jason ^a   Fang, Zhenman ^a,b   Lo, Michael ^a   Wang, Hanrui ^a   Xu, Jingxian ^a   Zhang, Shaochong ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b XILINX INC   (United States)

Author keywords

Analytical model; FPGA; GPU; Performance comparison

Indexed keywords

ANALYTICAL MODELS; BANDWIDTH; BENCHMARKING; COMPUTERS; GRAPHICS PROCESSING UNIT; PROGRAM PROCESSORS;

BENCHMARK SUITES; CLOCK FREQUENCY; DEEP PIPELINES; MEMORY BANDWIDTHS; OFF-CHIP MEMORY; PERFORMANCE COMPARISON; RODINIA;

FIELD PROGRAMMABLE GATE ARRAYS (FPGA);

EID: 85057754695     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/FCCM.2018.00023     Document Type: Conference Paper

References (9)

1. S. Che et al., "Rodinia: A benchmark suite for heterogeneous computing, " in IISWC'2009, pp. 44-54. [Online]. Available: http://www. cs. virginia. edu/-skadron/wiki/rodinia/index. php
2. J. Cong et al., "High-level synthesis for fpgas: From prototyping to deployment, " TCAD'2011, vol. 30, no. 4, pp. 473-491.
3. "Amazon EC2 F1 Instances, " https://aws. amazon. com/ec2/instance-types/f1/, accessed: 2018-01-21.
4. G. Singh et al., "Xilinx 16nm datacenter device family with in-package hbm and ccix interconnect, " in HotChips'2017.
5. J. Cong et al., "An optimal microarchitecture for stencil computation acceleration based on non-uniform partitioning of data reuse buffers, " in DAC'2014, pp. 1-6.
6. C. Zhang et al., "Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks, " in ICCAD'2016, pp. 1-8.
7. S. Che et al., "Accelerating compute-intensive applications with GPUs and fpgas, " in SASP'2008, pp. 101-107.
8. K. Krommydas et al., "On the characterization of OpenCL dwarfs on fixed and reconfigurable platforms, " in ASAP'2014, pp. 153-160.
9. H. R. Zohouri et al., "Evaluating and optimizing OpenCL kernels for high performance computing with fpgas, " in SC'2016, pp. 35: 1-35: 12.