{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T23:01:36Z","timestamp":1777676496309,"version":"3.51.4"},"reference-count":31,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2012,6,29]],"date-time":"2012-06-29T00:00:00Z","timestamp":1340928000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2013,5]]},"abstract":"<jats:p>Volume reconstruction by backprojection is the computational bottleneck in many interventional clinical computed tomography (CT) applications. Today vendors in this field replace special purpose hardware accelerators with standard hardware such as multicore chips and GPGPUs. Medical imaging algorithms are on the verge of employing high-performance computing (HPC) technology, and are therefore an interesting new candidate for optimization. This paper presents low-level optimizations for the backprojection algorithm, guided by a thorough performance analysis on four generations of Intel multicore processors (Harpertown, Westmere, Westmere EX, and Sandy Bridge). We choose the RabbitCT benchmark, a standardized testcase well supported in industry, to ensure transparent and comparable results. Our aim is to provide not only the fastest possible implementation but also compare with performance models and hardware counter data in order to fully understand the results. We separate the influence of algorithmic optimizations, parallelization, SIMD vectorization, and microarchitectural issues and pinpoint problems with current SIMD instruction set extensions on standard CPUs (SSE, AVX). The use of assembly language is mandatory for best performance. Finally, we compare our results to the best GPGPU implementations available for this open competition benchmark.<\/jats:p>","DOI":"10.1177\/1094342012442424","type":"journal-article","created":{"date-parts":[[2012,6,29]],"date-time":"2012-06-29T21:56:56Z","timestamp":1341007016000},"page":"162-177","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":22,"title":["Pushing the limits for medical image reconstruction on recent standard multicore processors"],"prefix":"10.1177","volume":"27","author":[{"given":"Jan","family":"Treibig","sequence":"first","affiliation":[{"name":"Erlangen Regional Computing Center, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Hager","sequence":"additional","affiliation":[{"name":"Erlangen Regional Computing Center, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hannes G.","family":"Hofmann","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, University Erlangen-Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joachim","family":"Hornegger","sequence":"additional","affiliation":[{"name":"Pattern Recognition Lab, University Erlangen-Nuremberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Wellein","sequence":"additional","affiliation":[{"name":"Erlangen Regional Computing Center, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2012,6,29]]},"reference":[{"key":"bibr1-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.1.000612"},{"key":"bibr2-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1117\/12.722160"},{"key":"bibr3-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1002\/ima.10027"},{"key":"bibr4-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1201\/EBK1439811924"},{"key":"bibr5-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"bibr6-1094342012442424","unstructured":"Heigl B, Kowarschik M (2007) High-speed reconstruction for C-arm computed tomography. In 9th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, Lindau, pp. 25\u201328, http:\/\/www.fully3d.org."},{"key":"bibr7-1094342012442424","unstructured":"Hofmann HG, Keck B, Hornegger J (2010) Accelerated C-arm reconstruction by out-of-projection prediction. In Deserno TM, Handels H, Meinzer H-P, Tolxdorff T (eds), Bildverarbeitung f\u00fcr die Medizin 2010, Berlin, pp. 380\u2013384. Available at: http:\/\/www5.informatik.uni-erlangen.de\/Forschung\/Publikationen\/2010\/Hofmann10-ACR.pdf."},{"key":"bibr8-1094342012442424","doi-asserted-by":"crossref","first-page":"3940","DOI":"10.1118\/1.3525838","volume":"38","author":"Hofmann HG","year":"2011","journal-title":"Medical Physics"},{"key":"bibr9-1094342012442424","unstructured":"Intel (1999) AP-803 increasing the accuracy of the results from the reciprocal and reciprocal square root instructions using the Newton\u2013Raphson method."},{"key":"bibr10-1094342012442424","unstructured":"Intel (2011 a) Intel advanced vector extensions programming reference."},{"key":"bibr11-1094342012442424","unstructured":"Intel (2011 b) Intel architecture code analyzer. Available at: http:\/\/software.intel.com\/en-us\/articles\/intel-architecture-code-analyzer\/."},{"key":"bibr12-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1118\/1.2710328"},{"key":"bibr13-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719277"},{"key":"bibr14-1094342012442424","doi-asserted-by":"crossref","unstructured":"Keck B, Hofmann H, Scherl H, Kowarschik M, Hornegger J (2009) High resolution iterative CT reconstruction using graphics hardware. In Yu B (ed.), 2009 IEEE Nuclear Science Symposium Conference Record, pp. 4035\u20134040. Available at: http:\/\/www5.informatik.uni-erlangen.de\/Forschung\/Publikationen\/2009\/Keck09-HRI.pdf.","DOI":"10.1109\/NSSMIC.2009.5402433"},{"key":"bibr15-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1117\/12.707336"},{"key":"bibr16-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1117\/12.878502"},{"key":"bibr17-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1117\/12.716797"},{"key":"bibr18-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1109\/NSSMIC.1998.773839"},{"key":"bibr19-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0056194"},{"key":"bibr20-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2010.01.004"},{"key":"bibr21-1094342012442424","volume-title":"Workshop on High Performance Image Reconstruction (HPIR)","author":"Papenhausen E","year":"2011"},{"key":"bibr22-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1118\/1.3180956"},{"key":"bibr23-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04268-3_17"},{"key":"bibr24-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1109\/NSSMIC.2007.4437102"},{"key":"bibr25-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1117\/12.708754"},{"key":"bibr26-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-33125-4_3"},{"key":"bibr27-1094342012442424","volume-title":"Proceedings of the Workshop Memory issues on Multi- and Manycore Platforms at PPAM 2009, the 8th International Conference on Parallel Processing and Applied Mathematics","author":"Treibig J","year":"2009"},{"key":"bibr28-1094342012442424","volume-title":"High Performance Computing in Science and Engineering","author":"Treibig J","year":"2009"},{"key":"bibr29-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2010.38"},{"key":"bibr30-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1109\/42.870250"},{"key":"bibr31-1094342012442424","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/29160"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342012442424","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1094342012442424","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342012442424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:19:09Z","timestamp":1777450749000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1094342012442424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,29]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,5]]}},"alternative-id":["10.1177\/1094342012442424"],"URL":"https:\/\/doi.org\/10.1177\/1094342012442424","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,29]]}}}