Streaming Tiles: Flexible Implementation of Convolution Neural Networks Inference on Manycore Architectures
Autor: | Madhura Purnaprajna, Zain Ul-Abdin, Nesma M. Rezk |
---|---|
Rok vydání: | 2018 |
Předmět: |
Artificial neural network
Computer science business.industry Computation Deep learning Inference 020206 networking & telecommunications 02 engineering and technology 010501 environmental sciences 01 natural sciences Memory management Kernel (image processing) Computer engineering 0202 electrical engineering electronic engineering information engineering System on a chip Artificial intelligence business 0105 earth and related environmental sciences |
Zdroj: | IPDPS Workshops |
Popis: | Convolution neural networks (CNN) are extensively used for deep learning applications such as image recognition and computer vision. The convolution module of these networks is highly compute-intensive. Having an efficient implementation of the convolution module enables realizing the inference part of the neural network on embedded platforms. Low precision parameters require less memory, less computation time, and less power consumption while achieving high classification accuracy. Furthermore, streaming the data over parallelized processing units saves a considerable amount of memory, which is a key concern in memory constrained embedded platforms. In this paper, we explore the design space for streamed CNN on Epiphany manycore architecture using varying precisions for weights (ranging from binary to 32-bit). Both AlexNet and GoogleNet are explored for two different memory sizes of Epiphany cores. We are able to achieve competitive performance for both Alexnet and GoogleNet with respect to emerging manycores. Furthermore, the effects of different design choices in terms of precision, memory size, and the number of cores are evaluated by applying the proposed method. |
Databáze: | OpenAIRE |
Externí odkaz: |