Practice of parallelizing network applications on multi-core architectures Export

@inproceedings{network-parallelization-ics09, abstract = {The industry wide shift to multi-core architectures arouses great interests in parallelizing sequential applications. However, it is very difficult to parallelize fine-grained applications for multi-core architectures due to insufficient hardware support of fast communication and synchronization. Fortunately, network applications can be decomposed into pipelined structures that are amenable to streaming based parallel processing. To realize the potential of pipelining on multi-core architectures, it requires reevaluating the basic tradeoffs in parallel processing, including the ones between load balance and data locality and between general lock mechanisms and special lock-free data structures. This paper presents the practice of building a high-performance multi-core based network processing platform in which connection-affinity and lock-free design principles are applied effectively for better data locality and faster core-to-core synchronization and communication.}, address = {New York, NY, USA}, author = {Wang, Junchang and Cheng, Haipeng and Hua, Bei and Tang, Xinan}, booktitle = {ICS '09: Proceedings of the 23rd international conference on Supercomputing}, citeulike-article-id = {6086475}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1542307}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1542275.1542307}, doi = {10.1145/1542275.1542307}, isbn = {978-1-60558-498-0}, keywords = {ics, ics09, leah, network, parallelization, studygroup}, location = {Yorktown Heights, NY, USA}, pages = {204--213}, posted-at = {2009-11-08 18:26:57}, priority = {2}, publisher = {ACM}, title = {Practice of parallelizing network applications on multi-core architectures}, url = {http://dx.doi.org/10.1145/1542275.1542307}, year = {2009} }

TY - CONF ID - network-parallelization-ics09 L3 - citeulike-article-id:6086475 N2 - The industry wide shift to multi-core architectures arouses great interests in parallelizing sequential applications. However, it is very difficult to parallelize fine-grained applications for multi-core architectures due to insufficient hardware support of fast communication and synchronization. Fortunately, network applications can be decomposed into pipelined structures that are amenable to streaming based parallel processing. To realize the potential of pipelining on multi-core architectures, it requires reevaluating the basic tradeoffs in parallel processing, including the ones between load balance and data locality and between general lock mechanisms and special lock-free data structures. This paper presents the practice of building a high-performance multi-core based network processing platform in which connection-affinity and lock-free design principles are applied effectively for better data locality and faster core-to-core synchronization and communication. CY - Yorktown Heights, NY, USA SN - 978-1-60558-498-0 AD - New York, NY, USA EP - 213 TI - Practice of parallelizing network applications on multi-core architectures PB - ACM T2 - ICS '09: Proceedings of the 23rd international conference on Supercomputing SP - 204 KW - ics KW - ics09 KW - leah KW - network KW - parallelization KW - studygroup AU - Wang, Junchang AU - Cheng, Haipeng AU - Hua, Bei AU - Tang, Xinan PY - 2009/// UR - http://dx.doi.org/10.1145/1542275.1542307 ER -