% 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:915928, author = {Herten, Andreas and Hater, Thorsten and Haghighi Mood, Kaveh and Kraus, Jiri and Hrywniak, Markus}, title = {{D}irective-based {GPU} programming with {O}pen{ACC}}, reportid = {FZJ-2022-05791}, year = {2022}, 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 the GPU. The course covered basic aspects of GPU architectures and programming. Focus was on the usage of the directive-based OpenACC programming model, which allows for portable application development. Examples of increasing complexity were used to demonstrate optimization and tuning of scientific applications. Topics covered: Introduction to GPU/Parallel computing, Programming model OpenACC, Interoperability of OpenACC with GPU libraries (like cuBLAS and cuFFT) and CUDA, Multi-GPU Programming with MPI and OpenACC, Tools for debugging and profiling, Performance optimization. The course consists of lectures and interactive hands-on sessions in C or Fortran (the attendee’s choice).}, month = {Oct}, date = {2022-10-26}, organization = {PRACE Training Course at JSC, online (Germany), 26 Oct 2022 - 28 Oct 2022}, subtyp = {Other}, cin = {JSC}, cid = {I:(DE-Juel1)JSC-20090406}, pnm = {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)POF4-5122 / G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)ATML-X-DEV}, typ = {PUB:(DE-HGF)17}, url = {https://juser.fz-juelich.de/record/915928}, }