% 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:1049780,
      author       = {Herten, Andreas and Meinke, Jan and Haghighi Mood, Kaveh
                      and Penke, Carolin and Kraus, Jiri and Morgenstern, Laura},
      title        = {{GPU} {P}rogramming {P}art 1: {F}oundations},
      reportid     = {FZJ-2025-05564},
      year         = {2025},
      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 a GPU.The course will cover 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.This course is a basic
                      course covering the foundations of GPU programming including
                      an introduction to GPU/parallel computing, programming with
                      CUDA, GPU libraries, tools for debugging and profiling, and
                      performance optimizations.Topics covered will include
                      Introduction to GPUs and GPU computing, programming model
                      CUDA, tools for debugging and profiling, GPU libraries (like
                      cuBLAS, cuFFT), and introduction to multi-GPU programming.},
      month         = {Mar},
      date          = {2025-03-31},
      organization  = {JSC - as part of the Training
                       Programme of Forschungszentrum Jülich,
                       Jülich (Germany), 31 Mar 2025 - 2 Apr
                       2025},
      subtyp        = {Other},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / 5112 - Cross-Domain
                      Algorithms, Tools, Methods Labs (ATMLs) and Research Groups
                      (POF4-511) / 5122 - Future Computing $\&$ Big Data Systems
                      (POF4-512) / Grundlagen für zukünftige
                      Informationstechnologien (FUEK412) / ATML-X-DEV - ATML
                      Accelerating Devices (ATML-X-DEV) / BMBF 01 1H1 6013, NRW
                      325 – 8.03 – 133340 - SiVeGCS (DB001492)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5112 /
                      G:(DE-HGF)POF4-5122 / G:(DE-Juel1)FUEK412 /
                      G:(DE-Juel-1)ATML-X-DEV / G:(DE-Juel-1)DB001492},
      typ          = {PUB:(DE-HGF)17},
      url          = {https://juser.fz-juelich.de/record/1049780},
}