{"0ace774f7a6793874363bb34e9e65a7bbastiankoller":{"DOI":"","ISBN":"","ISSN":"","URL":"","abstract":"","annote":"","author":[{"family":"Cheptsov","given":"Alexey"},{"family":"Koller","given":"Bastian"}],"citation-label":"cheptsov2015leveraging","collection-editor":[],"collection-title":"","container-author":[],"container-title":"","documents":[],"edition":"","editor":[],"event-date":{"date-parts":[["2015"]],"literal":"2015"},"event-place":"","id":"0ace774f7a6793874363bb34e9e65a7bbastiankoller","interhash":"921f863d6d1f0846708c323a613df400","intrahash":"0ace774f7a6793874363bb34e9e65a7b","issue":"","issued":{"date-parts":[["2015"]],"literal":"2015"},"keyword":"Data-as-a-Service MPI OMPIJava Parallelisation Performance","note":"","number":"","page":"","page-first":"","publisher":"","publisher-place":"","status":"","title":"Leveraging High-Performance Computing Infrastructures to Web Data Analytic Applications by Means of Message-Passing Interface","type":"chapter","username":"bastiankoller","version":"","volume":""},"a4a5c9728db0683dda1b2b3318fa0c9damerwafai":{"DOI":"","ISBN":"","ISSN":"","URL":"","abstract":"This paper introduces the porting of an industrial neural network simulator onto GPUs used in a tool-chain to sort massive amounts of E-mails and other textual data. Compared to other previous work, all steps are being executed on the GPU, achieving overall up to 33× speedup without using any cuBLAS functionality. All the time-consuming routines have been ported onto the GPU, i.e. the training-, the simulation- and the verification-phases, the training being the most time-consuming. It is planned to include these GPU-kernels into the product for special costumer's demands.","annote":"","author":[{"family":"Wafai","given":"Mhd. Amer"},{"family":"Ahmed","given":"Zaheer"},{"family":"Keller","given":"Rainer"},{"family":"Holzmann","given":"Sven"},{"family":"Sander","given":"Björn"},{"family":"Resch","given":"Michael"}],"citation-label":"wafai12","collection-editor":[{"family":"Chiu","given":"Dickson K. W."},{"family":"Wang","given":"Minhong"},{"family":"Popescu","given":"Elvira"},{"family":"Li","given":"Qing"},{"family":"Lau","given":"Rynson"}],"collection-title":"LNCS","container-author":[{"family":"Chiu","given":"Dickson K. W."},{"family":"Wang","given":"Minhong"},{"family":"Popescu","given":"Elvira"},{"family":"Li","given":"Qing"},{"family":"Lau","given":"Rynson"}],"container-title":"New Horizons in Web Based Learning","documents":[],"edition":"","editor":[{"family":"Chiu","given":"Dickson K. W."},{"family":"Wang","given":"Minhong"},{"family":"Popescu","given":"Elvira"},{"family":"Li","given":"Qing"},{"family":"Lau","given":"Rynson"}],"event-date":{"date-parts":[["2011","December"]],"literal":"2011"},"event-place":"","id":"a4a5c9728db0683dda1b2b3318fa0c9damerwafai","interhash":"0f4f1b3c77004231f7c17f1c80480dfe","intrahash":"a4a5c9728db0683dda1b2b3318fa0c9d","issue":"","issued":{"date-parts":[["2011","December"]],"literal":"2011"},"keyword":"Back CUDA GPGPU GPU HLRS Network Neural Parallelisation Propagation SCOPE myown","misc":{"date-added":"2015-08-18 14:03:50 +0000","date-modified":"2015-08-18 14:20:22 +0000"},"note":"","number":"","number-of-pages":"8","page":"21-29","page-first":"21","publisher":"Springer Berlin Heidelberg","publisher-place":"","status":"","title":"Optimization of industrial Neural Network simulators for GPGPUs","type":"paper-conference","username":"amerwafai","version":"","volume":"7697"}}