% IMPORTANT: The following is UTF-8 encoded. This means that in the presence % of non-ASCII characters, it will not work with BibTeX 0.99 or older. % Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or % “biber”. @MISC{Herten:903617, author = {Herten, Andreas and Meinke, Jan and Haghighi Mood, Kaveh and Hrywniak, Markus and Kraus, Jiri}, title = {{PRACE} {T}raining {C}ourse: {GPU} {P}rogramming with {CUDA}}, reportid = {FZJ-2021-05271}, year = {2021}, note = {Online course within the PRACE and FZJ training program.}, abstract = {GPU-accelerated computing drives current scientific research. Writing fast numeric algorithms for GPUs offers high application performance by offloading compute-intensive portions of the code to an NVIDIA GPU. The course will cover basic aspects of GPU architectures and programming. Focus is on the usage of the parallel programming language CUDA-C which allows maximum control of NVIDIA GPU hardware. Examples of increasing complexity are used to demonstrate optimization and tuning of scientific applications.Topics covered include: Introduction to GPU/Parallel computing Programming model CUDA GPU libraries like CuBLAS and CuFFT Tools for debugging and profiling Performance optimizationsThis course is a PRACE training course.}, month = {Apr}, date = {2021-04-26}, organization = {, 26 Apr 2021 - 30 Apr 2021}, subtyp = {Other}, cin = {JSC}, cid = {I:(DE-Juel1)JSC-20090406}, pnm = {5121 - Supercomputing $\&$ Big Data Facilities (POF4-512) / 5122 - Future Computing $\&$ Big Data Systems (POF4-512) / 5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) / ATML-X-DEV - ATML Accelerating Devices (ATML-X-DEV)}, pid = {G:(DE-HGF)POF4-5121 / G:(DE-HGF)POF4-5122 / G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)ATML-X-DEV}, typ = {PUB:(DE-HGF)17}, url = {https://juser.fz-juelich.de/record/903617}, }