Recognition of convolutional neural network based on CUDA Technology

For the problem whether Graphic Processing Unit(GPU),the stream processor with high performance of floating— point computing is applicable to neural networks, this paper proposes the parallel recognition algorithm of Convolutional Neural Networks(CNNs).It adopts Compute Unified Device Architecture(CUDA)technology, definite the parallel data structures, and describes the mapping mechanism for computing tasks on CUDA.It compares the parallel recognition algorithm achieved on GPU of GTX200 hardware architecture with the serial algorithm on CPU.It improves speed by nearly 60 times.Result shows that GPU based the stream processor architecture ate more applicable to some related applications about neural networks than CPU. Key wordsstream processor;Single—Instruction Multiple—Thread(SIMT);GTX200 hardware architecture;Compute Unified Device Architecture (CUDA)technology;Convolutional Neural Networks (CNNs) The recognition algorithm of Convolutional Neural Networks (CNNs) is widely used in many research areas, but the implementation involves high arithmetic intensity. Use a new emerging paradigm, the streaming model [1] of Graphic Processing Unit (GPU), which has more transistor for data processing and many-core (hundreds of cores) compared with CPU. Significant application-level speedup over uniprocessor execution, easy entrance, numerical precision and accuracy, wide availability to end users and strong scalability, these programmable features of GPU make it a new hotspot.