{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T04:07:40Z","timestamp":1744258060769,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642314759"},{"type":"electronic","value":"9783642314766"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31476-6_8","type":"book-chapter","created":{"date-parts":[[2012,9,21]],"date-time":"2012-09-21T09:58:03Z","timestamp":1348221483000},"page":"93-104","source":"Crossref","is-referenced-by-count":2,"title":["Trace-Based Performance Analysis for Hardware Accelerators"],"prefix":"10.1007","author":[{"given":"Guido","family":"Juckeland","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,8,2]]},"reference":[{"key":"8_CR1","unstructured":"AMD: APP Profiler. Online. http:\/\/developer.amd.com\/tools\/AMDAPPProfiler (2011)"},{"key":"8_CR2","unstructured":"Clearspeed: Visual Profiler. Online. http:\/\/www.clearspeed.com\/products\/sdk_details.php (2011)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Dietrich, R., Ilsche, T., Juckeland, G.: Non-intrusive performance analysis of parallel hardware accelerated applications on hybrid architectures. In: International Conference on Parallel Processing Workshops, San Diego, pp. 135\u2013143 (2010). doi: 10.1109\/icppw.2010.30","DOI":"10.1109\/ICPPW.2010.30"},{"key":"8_CR4","unstructured":"Farooqui, N., Kerr, A., Diamos, G., Yalamanchili, S., Schwan, K.: A framework for dynamically instrumenting gpu compute applications within gpu ocelot. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, GPGPU-4, pp. 9:1\u20139:9. ACM, New York, NY (2011). doi: http:\/\/doi.acm.org\/10.1145\/1964179.1964192 . http:\/\/doi.acm.org\/10.1145\/1964179.1964192"},{"key":"8_CR5","unstructured":"Fuerlinger, K., Wright, N.J., Skinner, D.: Comprehensive performance monitoring for gpu cluster systems. In: Proceedings of the 12th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC), in conjunction with IPDPS-11, Anchorage, AK (2011). http:\/\/projekt17.pub.lab.nm.ifi.lmu.de\/fuerling\/research\/pubs\/\/FUERLINGER_2011_PDSEC.pdf"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Hackenberg, D., Brunst, H., Nagel, W.E.: Event tracing and visualization for cell broadband engine systems. In: Luque, E., Margalef, T., Ben\u00edtez, D. (eds.) Euro-Par 2008, LNCS 5168, pp. 172\u2013181. Springer, Berlin\/New York (2008). doi: 10.1007\/978-3-540-85451-7_19","DOI":"10.1007\/978-3-540-85451-7_19"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Hackenberg, D., Juckeland, G., Brunst, H.: Performance analysis of multi-level parallelism: inter-node, intra-node and hardware accelerators. Concurr. Comput. Pract. Exp. (2011). doi: 10.1002\/cpe.1725","DOI":"10.1002\/cpe.1725"},{"key":"8_CR8","unstructured":"IBM: PA-SDK3-Tool. Online. http:\/\/www.ibm.com\/developerworks\/power\/tutorials\/pa-sdk3tool (2011)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Kn\u00fcpfer, A., Brendel, R., Brunst, H., Mix, H., Nagel, W.E.: Introducing the open trace format (otf). In: Alxandrov, V.N., Albada, G.D., Sloot, P.M.A., Dongarra, J.J. (eds.) 6th International Conference on Computational Science (ICCS), vol.\u00a02, pp. 526\u2013533. Springer, Reading (2006)","DOI":"10.1007\/11758525_71"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Mayanglambam, S., Malony, A., Sottile, M.: Performance measurement of applications with GPU acceleration using CUDA. In: International Conference on Parallel Computing (PARCO 2009), Lyon (2009)","DOI":"10.3233\/978-1-60750-530-3-341"},{"key":"8_CR11","unstructured":"Mellor-Crummey, J., Tallent, N., Liu, X.: Hpctoolkit: new capabilities, ongoing work, and challenges ahead. In: CScADS Summer 2011 Workshops \u2013 Performance Tools for Extreme Scale Computing, Tahoe City, CA (2011). http:\/\/cscads.rice.edu\/workshops\/summer-2011\/slides\/performance-tools\/Rice-HPCToolkit-CScADS-2011.pdf"},{"key":"8_CR12","unstructured":"M\u00fcller, M.S., Kn\u00fcpfer, A., Jurenz, M., Lieber, M., Brunst, H., Mix, H., Nagel, W.E.: Developing scalable applications with vampir, vampirserver and vampirtrace. In: Bischof,\u00a0C., B\u00fccker, M., Gibbon, P., Joubert, G.R., Lippert, T., Mohr, B., Peters, F.J. (eds.) Parallel Computing: Architectures, Algorithms and Applications. Advances in Parallel Computing, vol.\u00a015, pp. 637\u2013644. IOS Press, Amsterdam (2008). http:\/\/www.booksonline.iospress.nl\/Content\/View.aspx?piid=8455"},{"key":"8_CR13","unstructured":"NVIDIA: CUDA Visual Profiler. Online. http:\/\/developer.download.nvidia.com\/compute\/DevZone\/docs\/html\/C\/doc\/Compute_Visual_Profiler_User_Guide.pdf (2011)"},{"key":"8_CR14","unstructured":"NVIDIA: Parallel NSight. Online. http:\/\/developer.nvidia.com\/nvidia-parallel-nsight (2011)"},{"key":"8_CR15","unstructured":"Vijayakumar, K., Mueller, F., Ma, X., Roth, P.C.: Scalable I\/O tracing and analysis. Technical report, Department of Computer Science, North Carolina State University; Computer Science and Mathematics Division, Oak Ridge National Laboratory (2009)"}],"container-title":["Tools for High Performance Computing 2011"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31476-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T04:19:37Z","timestamp":1744172377000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31476-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642314759","9783642314766"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31476-6_8","relation":{},"subject":[],"published":{"date-parts":[[2012]]}}}