Multicore Performance of Block Algebraic Iterative Reconstruction Methods. Sørensen, H., H., B. & Hansen, P., C. SIAM Journal on Scientific Computing, 36(5):C524-C546, SIAM PUBLICATIONS, 3600 UNIV CITY SCIENCE CENTER, PHILADELPHIA, PA 19104-2688 USA, 10, 2014.
Multicore Performance of Block Algebraic Iterative Reconstruction Methods [link]Website  abstract   bibtex   
Algebraic iterative methods are routinely used for solving the ill-posed sparse linear systems arising in tomographic image reconstruction. Here we consider the algebraic reconstruction technique (ART) and the simultaneous iterative reconstruction techniques (SIRT), both of which rely on semiconvergence. Block versions of these methods, based on a partitioning of the linear system, are able to combine the fast semiconvergence of ART with the better multicore properties of SIRT. These block methods separate into two classes: those that, in each iteration, access the blocks in a sequential manner, and those that compute a result for each block in parallel and then combine these results before the next iteration. The goal of this work is to demonstrate which block methods are best suited for implementation on modern multicore computers. To compare the performance of the different block methods, we use a fixed relaxation parameter in each method, namely, the one that leads to the fastest semiconvergence. Computational results show that for multicore computers, the sequential approach is preferable.
@article{
 title = {Multicore Performance of Block Algebraic Iterative Reconstruction Methods},
 type = {article},
 year = {2014},
 identifiers = {[object Object]},
 keywords = {3-DIMENSIONAL RECONSTRUCTION,ART,CONVERGENCE,EFFICIENT,IMAGE-RECONSTRUCTION,LINEAR-SYSTEMS,PARALLEL ALGORITHM,PROJECTION METHODS,RELAXATION PARAMETERS,SIRT,SIRT ALGORITHMS,TOMOGRAPHY,algebraic iterative reconstruction,block methods,relaxation parameter,semiconvergence,tomographic imaging},
 pages = {C524-C546},
 volume = {36},
 websites = {http://apps.webofknowledge.com.globalproxy.cvt.dk/full_record.do?product=UA&search_mode=GeneralSearch&qid=5&SID=R1gI9xzWGe5XCgFDbbu&page=1&doc=2},
 month = {10},
 publisher = {SIAM PUBLICATIONS, 3600 UNIV CITY SCIENCE CENTER, PHILADELPHIA, PA 19104-2688 USA},
 day = {9},
 id = {0341a3b6-548e-3405-a5d0-f2ef53e3892a},
 created = {2015-11-15T22:03:53.000Z},
 accessed = {2015-11-15},
 file_attached = {false},
 profile_id = {72235656-d597-370e-a1e5-8453c60fa280},
 group_id = {d0e361cc-e4f9-3361-a178-f7e6d1f6363f},
 last_modified = {2018-04-09T10:03:06.501Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Sørensen2014},
 private_publication = {false},
 abstract = {Algebraic iterative methods are routinely used for solving the ill-posed sparse linear systems arising in tomographic image reconstruction. Here we consider the algebraic reconstruction technique (ART) and the simultaneous iterative reconstruction techniques (SIRT), both of which rely on semiconvergence. Block versions of these methods, based on a partitioning of the linear system, are able to combine the fast semiconvergence of ART with the better multicore properties of SIRT. These block methods separate into two classes: those that, in each iteration, access the blocks in a sequential manner, and those that compute a result for each block in parallel and then combine these results before the next iteration. The goal of this work is to demonstrate which block methods are best suited for implementation on modern multicore computers. To compare the performance of the different block methods, we use a fixed relaxation parameter in each method, namely, the one that leads to the fastest semiconvergence. Computational results show that for multicore computers, the sequential approach is preferable.},
 bibtype = {article},
 author = {Sørensen, Hans Henrik B. and Hansen, Per Christian},
 journal = {SIAM Journal on Scientific Computing},
 number = {5}
}

Downloads: 0