File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Parallel Binomial American Option Pricing On CPU-GPU Hybrid Platform

TitleParallel Binomial American Option Pricing On CPU-GPU Hybrid Platform
Authors
Issue Date2012
PublisherWorld Scientific Pub. Co..
Citation
The International MultiConference of Engineers and Computer Scientists, Hong Kong, China, 14-16 March 2012. In IAENG Transactions on Electrical Engineering, 2013, v. 1, p. 161-174 How to Cite?
AbstractWe present a novel parallel binomial algorithm to compute prices of American options. The algorithm partitions a binomial tree into blocks of multiple levels of nodes, and assigns each such block to multiple processors. Each processor in parallel with the others computes the option's values at the assigned nodes. The algorithm is implemented and tested on a heterogeneous system consisting of an Intel multi-core processor and a NVIDIA GPU. The whole task is split and divided over the CPU and GPU so that the computations are performed on the two processors simultaneously. In the hybrid processing, the GPU is always assigned the last part of a block, and makes use of a couple of buffers in the on-chip shared memory to reduce the number of accesses to the off-chip device memory. The performance of the hybrid processing is compared with an optimised CPU serial code, a CPU parallel implementation and a GPU standalone program.
Persistent Identifierhttp://hdl.handle.net/10722/199745
ISBN

 

DC FieldValueLanguage
dc.contributor.authorZhang, Nen_US
dc.contributor.authorLei, CUen_US
dc.contributor.authorMan, KLen_US
dc.date.accessioned2014-07-22T01:32:29Z-
dc.date.available2014-07-22T01:32:29Z-
dc.date.issued2012en_US
dc.identifier.citationThe International MultiConference of Engineers and Computer Scientists, Hong Kong, China, 14-16 March 2012. In IAENG Transactions on Electrical Engineering, 2013, v. 1, p. 161-174en_US
dc.identifier.isbn9789814439077-
dc.identifier.urihttp://hdl.handle.net/10722/199745-
dc.description.abstractWe present a novel parallel binomial algorithm to compute prices of American options. The algorithm partitions a binomial tree into blocks of multiple levels of nodes, and assigns each such block to multiple processors. Each processor in parallel with the others computes the option's values at the assigned nodes. The algorithm is implemented and tested on a heterogeneous system consisting of an Intel multi-core processor and a NVIDIA GPU. The whole task is split and divided over the CPU and GPU so that the computations are performed on the two processors simultaneously. In the hybrid processing, the GPU is always assigned the last part of a block, and makes use of a couple of buffers in the on-chip shared memory to reduce the number of accesses to the off-chip device memory. The performance of the hybrid processing is compared with an optimised CPU serial code, a CPU parallel implementation and a GPU standalone program.-
dc.languageengen_US
dc.publisherWorld Scientific Pub. Co..-
dc.relation.ispartofIAENG Transactions on Electrical Engineeringen_US
dc.titleParallel Binomial American Option Pricing On CPU-GPU Hybrid Platformen_US
dc.typeConference_Paperen_US
dc.identifier.emailLei, CU: culei@eee.hku.hken_US
dc.identifier.authorityLei, CU=rp01908en_US
dc.identifier.doi10.1142/9789814439084_0013-
dc.identifier.hkuros230644en_US
dc.identifier.volume1en_US
dc.identifier.spage161en_US
dc.identifier.epage174en_US
dc.publisher.placeSingapore; Hackensack, N.J.en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats