ABSTRACT
Semantic comparison is the basic computational task behind meaningful search techniques being deployed by most of the new search engines. This report presents performance comparison among three GPU architectures implementing semantic comparison. We have used both linear and binary search approaches along with Bloom filter while implementing semantic comparison. The Kepler, Fermi and Tesla show 250, 200 and 100 times speedup respectively compared to an Intel's i7 processor with varying workloads. We determine that binary search based Bloom filter approach reduces semantic comparison time by factor up to 100 compared to linear search based Bloom filter on real dataset.
- Gantz, J. and Reinsel D. 2011. Extracting Value from Chaos. IDC IView. DOI= http://www.emc.com/digital_universe.Google Scholar
- J. Mitchell, and M. Lapata, Vector-based models of semantic composition, Proc. ACL-08: HLT, pp. 236--244, 2008.Google Scholar
- Barroso, L. A., Dean, J. and Holzle, U. Web Search for a Planet: The Google Cluster Architecture. IEEE Micro, 23 (2). 22--28. Google ScholarDigital Library
- A. Biswas, S. Mohan, J. Panigrahy et al., Representation of Complex Concepts for Semantic Routed Network, in Proc. of the 10th International Conference on Distributed Computing and Networking, Hyderabad, India, 2009, pp. 127--138. Google ScholarDigital Library
- A. Biswas, S. Mohan, A. Tripathy, J. Panigrahy, and R. Mahapatra. 2009. Semantic Key for Meaning Based Searching. In Proc. 2009 IEEE Intl. Conf. on Semantic Computing (ICSC '09). Washington, DC, USA, 209--214. DOI=10.1109/ICSC.2009.54 Google ScholarDigital Library
- A. Tripathy, S. Mohan, and R. Mahapatra, Optimizing a Semantic Comparator Using CUDA-enabled Graphics Hardware, in 2011 IEEE 5th International Conference on Semantic Computing (ICSC2011), Palo Alto, CA, 2011, pp. 125--132 Google ScholarDigital Library
- J. C. Perez. 2009. Google joins crowd, adds semantic search capabilities, Computer World, Mar. 2009.Google Scholar
- Jeffrey Dean and Sanjay Ghemawat. 2008. MapReduce: simplified data processing on large clusters. Commun. ACM 51, 1 (January 2008), 107--113. DOI=10.1145/1327452.1327492 Google ScholarDigital Library
- Kang, U., Papalexakis, E., Harpale, A. and Faloutsos, C. GigaTensor: scaling tensor analysis up by 100 times - algorithms and discoveries Proc. of 18th ACM SIGKDD Intl. Conf. on Knowledge discovery and data mining, ACM, Beijing, China, 2012, 316--324. Google ScholarDigital Library
- Frachtenberg, E. Reducing Query Latencies in Web Search Using Fine-Grained Parallelism. World Wide Web, 12 (4). 441--460. Google ScholarDigital Library
- Lindholm, E., Nickolls, J., Oberman, S. and Montrym, J. NVIDIA Tesla: A Unified Graphics and Computing Architecture. Micro, IEEE, 28 (2). 39--55. Google ScholarDigital Library
- Nickolls, J. and Dally, W. J. The GPU Computing Era. Micro, IEEE, 30 (2). 56--69. Google ScholarDigital Library
- Wittenbrink, C. M., Kilgariff, E. and Prabhu, A. Fermi GF100 GPU Architecture. Micro, IEEE, 31 (2). 50--59. Google ScholarDigital Library
- Nvidia GeForce GTX 680. Whitepaper. NVIDIA Corporation (2012). DOI=http://www.geforce.com/Active/en_US/en_US/pdf/GeForce-GTX-680-Whitepaper-FINAL.pdfGoogle Scholar
- Gerard Salton. 1989. Automatic Text Processing: the Transformation, Analysis, and Retrieval of Information by Computer. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA. Google ScholarDigital Library
- S. Bird, E. Klein, and E. Loper. 2009. Natural language processing with Python, Sebastopol, Calif.: O'Reilly Media, Inc., 2009. Google ScholarDigital Library
- Klimt, B. and Yang, Y. The enron corpus: A new dataset for email classification research. Machine Learning: ECML 2004. 217--226.Google Scholar
- J. Panigrahy. 2011. Generating Tensor Representation from Concept Tree in meaning based search, Master's Thesis, Computer Science and Engineering, Texas A&M University, College Station, TX, 2011.Google Scholar
- A. Broder, and M. Mitzenmacher, Network Applications of Bloom Filters: A Survey, Internet Mathematics, vol. 1, no. 4, pp. 485--509, 2002.Google ScholarCross Ref
- Avarm Perez. 1983. Byte-wise CRC Calculations in Proc. IEEE Micro, vol. 3, no. 40, 1983. Google ScholarDigital Library
- M. Harris et al. 2007. Optimizing parallel reduction in CUDA, Proc. ACM SIGMOD, vol. 13, no. 21, pp. 104--110, 2007.Google Scholar
- Wen-mei W. Hwu. 2011. GPU Computing Gems Jade Edition, Morgan Kaufmann (Elsevier), 2011. Google ScholarDigital Library
- Ye, X., et al. 2010. High performance comparison-based sorting algorithm on many-core GPUs. in Proc. IEEE Parallel & Distributed Processing (IPDPS), 2010.Google Scholar
- W. Fang et. al. 2008. Parallel Data Mining on Graphics Processors, Technical Report HKUST-CS08-07, 2008.Google Scholar
- Ulmer, C., Gokhale, M., Gallagher, B., Top, P. and Eliassi-Rad, T. Massively parallel acceleration of a document-similarity classifier to detect web attacks. J. Parallel Distrib. Comput., 71 (2). 225--235. Google ScholarDigital Library
- Mohan, S., Biswas, A., Tripathy, A., Pannigrahy, J. and Mahapatra, R., A parallel architecture for meaning comparison. In Parallel & Distributed Processing (IPDPS), 2010 IEEE International Symposium on, (2010), IEEE, 1--10.Google ScholarCross Ref
Index Terms
- Exploring GPU architectures to accelerate semantic comparison for intention-based search
Recommendations
Exploring the performance and portability of the k-means algorithm on SYCL across CPU and GPU architectures
AbstractThe aim of SYCL is to reduce the gap between the performance and code portability of the main accelerators used in HPC, such as multi-vendor CPUs, GPUs, and FPGAs. To evaluate SYCL’s performance portability, this paper uses the k-means algorithm ...
Compiler-based code generation and autotuning for geometric multigrid on GPU-accelerated supercomputers
Highlights- Generate parallel CUDA code from sequential C input code using a compiler-based tool for key operators in Geometric Multigrid.
AbstractGPUs, with their high bandwidths and computational capabilities are an increasingly popular target for scientific computing. Unfortunately, to date, harnessing the power of the GPU has required use of a GPU-specific programming model ...
On the Efficacy of a Fused CPU+GPU Processor (or APU) for Parallel Computing
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance ComputingThe graphics processing unit (GPU) has made significant strides as an accelerator in parallel computing. However, because the GPU has resided out on PCIe as a discrete device, the performance of GPU applications can be bottlenecked by data transfers ...
Comments