Parallel Programming Concepts (WT 2012/13) - tele-TASKhttps://www.tele-task.de/series/924/Since the very beginning of computers, processors were build with ever-increasing clock frequencies and instruction-level optimizations for faster serial code execution, such as ILP, caches, or speculative engines. Software developers and industry got used to the fact that applications get faster by just exchanging the underlying hardware. For several years now, these rules are proven to be no longer valid. Moore's law about the ever-increasing number of transistors per die is still valid, but decreased structural sizes and increased power consumption demand stalling, or even reduced, clock frequencies. Due to this development, serial execution performance no longer improves automatically with the next processor generation. In the 'many-core era' that happens now, additional transistors are used not to speed up serial code paths, but to offer multiple execution engines ('cores') per processor. This changes every desktop-, server-, or even mobile system into a parallel computer. The exploitation of additional transistors is therefore now the responsibility of software, which makes parallel programming a mandatory approach for all software with scalability demands.High quality e-learning content created with tele-TASK - more than video! Powered by Hasso Plattner Institute (HPI)Dr. Peter TrögerSince the very beginning of computers, processors were build with ever-increasing clock frequencies and instruction-level optimizations for faster serial code execution, such as ILP, caches, or speculative engines. Software developers and industry got used to the fact that applications get faster by just exchanging the underlying hardware. For several years now, these rules are proven to be no longer valid. Moore's law about the ever-increasing number of transistors per die is still valid, but decreased structural sizes and increased power consumption demand stalling, or even reduced, clock frequencies. Due to this development, serial execution performance no longer improves automatically with the next processor generation. In the 'many-core era' that happens now, additional transistors are used not to speed up serial code paths, but to offer multiple execution engines ('cores') per processor. This changes every desktop-, server-, or even mobile system into a parallel computer. The exploitation of additional transistors is therefore now the responsibility of software, which makes parallel programming a mandatory approach for all software with scalability demands.notele-TASKtele-task@hpi.deen℗; ©; tele-TASKSun, 07 Jun 2020 09:07:15 GMTPyRSS2Gen-1.1.0http://blogs.law.harvard.edu/tech/rssParallel Algorithmshttps://www.tele-task.de/lecture/video/3756/Dr. Peter Tröger01:25:07tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3756/Mon, 04 Feb 2013 09:16:00 GMTImplicit Parallelism & Mixed Approacheshttps://www.tele-task.de/lecture/video/3735/Dr. Peter Tröger01:26:55tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3735/Mon, 28 Jan 2013 09:18:00 GMTMessage Passinghttps://www.tele-task.de/lecture/video/3724/Dr. Peter Tröger01:29:17tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3724/Mon, 21 Jan 2013 09:19:00 GMTGPU Computing Deviceshttps://www.tele-task.de/lecture/video/3710/Frank Feinbube01:26:34tele-TASK, HPI, computer science, technology, Germany, PotsdamFrank FeinbubeFrank Feinbubehttps://www.tele-task.de/lecture/video/3710/Mon, 14 Jan 2013 09:20:00 GMTGPU Computing with OpenCLhttps://www.tele-task.de/lecture/video/3700/Frank Feinbube01:07:21tele-TASK, HPI, computer science, technology, Germany, PotsdamFrank FeinbubeFrank Feinbubehttps://www.tele-task.de/lecture/video/3700/Mon, 07 Jan 2013 09:46:00 GMTOpenMPhttps://www.tele-task.de/lecture/video/3685/Dr. Peter Tröger01:33:04tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3685/Mon, 17 Dec 2012 09:17:00 GMTMulticomputer Systemshttps://www.tele-task.de/lecture/video/3677/Prof. Dr. Andreas Polze01:29:37tele-TASK, HPI, computer science, technology, Germany, PotsdamProf. Dr. Andreas PolzeProf. Dr. Andreas Polzehttps://www.tele-task.de/lecture/video/3677/Mon, 10 Dec 2012 09:22:00 GMTProgramming Modelshttps://www.tele-task.de/lecture/video/3636/Dr. Peter Tröger01:22:24tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3636/Mon, 26 Nov 2012 09:19:00 GMTParallel Computershttps://www.tele-task.de/lecture/video/3627/Prof. Dr. Andreas Polze01:25:23tele-TASK, HPI, computer science, technology, Germany, PotsdamProf. Dr. Andreas PolzeProf. Dr. Andreas Polzehttps://www.tele-task.de/lecture/video/3627/Mon, 19 Nov 2012 09:21:00 GMTMulticomputerhttps://www.tele-task.de/lecture/video/3594/Dr. Peter Tröger01:22:09tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3594/Mon, 12 Nov 2012 09:21:00 GMTLocks and Monitorshttps://www.tele-task.de/lecture/video/3589/Dr. Peter Tröger01:27:08tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3589/Mon, 05 Nov 2012 00:00:00 GMTMotivation and Shared Memoryhttps://www.tele-task.de/lecture/video/3569/Dr. Peter Tröger01:29:28tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3569/Mon, 29 Oct 2012 09:18:00 GMTIntroductionhttps://www.tele-task.de/lecture/video/3525/Dr. Peter Tröger01:26:25tele-TASK, HPI, computer science, technology, Germany, PotsdamDr. Peter TrögerDr. Peter Trögerhttps://www.tele-task.de/lecture/video/3525/Mon, 22 Oct 2012 09:17:00 GMT