ZTE achieves a record–beyond a thousand images per second in facial recognition–known as “theoretical high accuracy” for its custom topology.
Deep learning technology is very important as it can enable perception in mobile edge computing systems. Hence, ZTE has collaborated with Intel to reach a benchmark in deep learning and convolutional neural networks (CNN). The technology is what many companies in Internet search and AI are trying to advance, and includes picture search and matching, as one example.
The test took place in Nanjing City, China, where ZTE’s engineers used Intel’s midrange Arria 10 FPGA for a cloud inferencing application using a CNN algorithm.
ZTE has achieved a record–beyond a thousand images per second in facial recognition–known as “theoretical high accuracy” for its’ custom topology. Intel’s Arria 10 FPGA accelerated the raw design performance more than 10 times while maintaining the accuracy.
The Arria 10 FPGA provides up to 1.5TFLOPs single precision floating-point processing performance, 1.15 million logic elements and more than a terabit-per-second high-speed connectivity.
Such deep learning designs can be seamlessly migrated from the Arria 10 FPGA family to the high-end Intel Stratix 10 FPGA family and users can expect up to nine times performance boost.
Besides the impressive increase in performance, the team at the ZTE Wireless Institute also managed to speed up design time with the use of the OpenCL programming language.
“With the Intel reference design and using the Intel SDK for OpenCL to program the FPGA, our development time was greatly shortened,” said Xiong Xiankui, chief engineer, ZTE Wireless Institute.