Using and designing massively parallel computers for artificial neural networks
Journal of Parallel and Distributed Computing - Special issue on neural computing on massively parallel processing
The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
IR evaluation methods for retrieving highly relevant documents
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Modern Information Retrieval
Programmable Stream Processors
Computer
Learning to rank using gradient descent
ICML '05 Proceedings of the 22nd international conference on Machine learning
FPGA Implementations of Neural Networks
FPGA Implementations of Neural Networks
Learning to rank for information retrieval (LR4IR 2007)
ACM SIGIR Forum
FPGA Acceleration of RankBoost in Web Search Engines
ACM Transactions on Reconfigurable Technology and Systems (TRETS)
The Impact of Arithmetic Representation on Implementing MLP-BP on FPGAs: A Study
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In modern Web search engines, Neural Network (NN)-based learning to rank algorithms is intensively used to increase the quality of search results. LambdaRank is one such algorithm. However, it is hard to be efficiently accelerated by computer clusters or GPUs, because: (i) the cost function for the ranking problem is much more complex than that of traditional Back-Propagation(BP) NNs, and (ii) no coarse-grained parallelism exists in the algorithm. This article presents an FPGA-based accelerator solution to provide high computing performance with low power consumption. A compact deep pipeline is proposed to handle the complex computing in the batch updating. The area scales linearly with the number of hidden nodes in the algorithm. We also carefully design a data format to enable streaming consumption of the training data from the host computer. The accelerator shows up to 15.3X (with PCIe x4) and 23.9X (with PCIe x8) speedup compared with the pure software implementation on datasets from a commercial search engine.