Open Access Open Access  Restricted Access Subscription Access

Combining Deep Learning Accelerators and Graphics Processing Unit for Efficient Computing

Agbaje, M.O, Daniel O, Mosinmiloluwa, O

Abstract


Hardware used in implementing artificial neural networks is vital as it has a major role to play in the speed and efficiency of the whole system. It is also a stated fact that the artificial intelligence industry is at crossroads for which processor (Deep Learning Accelerators and Graphics Processing Unit) best fits the portfolio for the most powerful tool for deep learning. In this article, we conducted a comparative study on the two processors by highlighting their selling points and lapses and made a case for the two processors to work together in a system, where one processor covers the lapse of the other one to enhance efficient computing.

Full Text:

PDF

References


Nurvitadhi, E., Venkatesh, G., Sim, J., Marr, D., Huang, R., Ong Gee Hock, J., ... & Boudoukh, G. (2017, February). Can FPGAs beat GPUs in accelerating next-generation deep neural networks?. In Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (pp. 5-14).

Bolz, J., Farmer, I., Grinspun, E., & Schröder, P. (2003). Sparse matrix solvers on the GPU: conjugate gradients and multigrid. ACM transactions on graphics (TOG), 22(3), 917-924.

Harris, M. J., Baxter, W. V., Scheuermann, T., & Lastra, A. (2003, July). Simulation of cloud dynamics on graphics hardware. In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware (pp. 92-101).

Krüger, J., & Westermann, R. (2005). Linear algebra operators for GPU implementation of numerical algorithms. In ACM SIGGRAPH 2005 Courses (pp. 234-es).

"nvidiateslamicroarchitecture"(http://people.cs.umass.edu/~emery/classes/cmpsci691st/readings/Arch/gpu.pdf) (PDF).

"nvidia introduces supercomputer for self driving cars" (http://gas2.org/2016/01/06/nvidia-introduces-supercomputer-for-self-driving-cars/).

"imagenet classification with deep convolutional neural networks" (https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf) (PDF).

"how the gpu came to be used for general computation"(http://igoro.com/archive/how-gpu-came-to-be-used-for-general computation/).

"google developing AI processors" (http://www.eetimes.com/document.asp?doc_id=1329715).google using its own AI accelerators.

"FPGA Based Deep Learning Accelerators Take on ASICs" (http://www.nextplatform.com/2016/08/23/fpga-based-deep-learning-accelerators-take-asics/). The Next Platform. 2016-08-23. Retrieved 2016-09-07.


Refbacks

  • There are currently no refbacks.