% 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”.

@PROCEEDINGS{Theodoropoulos:1019555,
      author       = {Theodoropoulos, Dimitris and Pekridis, Giorgos and
                      Miliadis, Panagiotis and Alverti, Chloe and Mpakos,
                      Panagiotis and Pnevmatikatos, Dionisios and Malakonakis,
                      Pavlos and Georgopoulos, Konstantinos and Mavroidis, Iakovos
                      and Perna, Gino and Zanotti, Marisa and Isotton, Giovanni
                      and Engelen, Max and Ioannou, Aggelos and Papaefstathiou,
                      Ioannis and Kahira, Albert Njoroge and Herten, Andreas},
      title        = {{E}arly {R}esults of {M}apping {I}ndustrial {A}pplications
                      on {H}eterogeneous {HPC} {S}ystems},
      publisher    = {ACM New York, NY, USA},
      reportid     = {FZJ-2023-05495},
      year         = {2023},
      abstract     = {The OPTIMA project aims to port and optimize industrial
                      applications and a set of open-source libraries into two
                      novel FPGA-populated HPC systems. Target applications are
                      from the domains of robotics simulation, underground
                      analysis and computational fluid dynamics (CFD), where data
                      processing is based on differential equations, matrix-matrix
                      and matrix-vector operations. Moreover, the OPTIMA OPen
                      Source (OOPS) library will support basic linear algebraic
                      operations, sparse matrix-vector arithmetic, as well as
                      computer-aided engineering (CAE) solvers. The OPTIMA target
                      platforms are JUMAX, an HPC system that couples an AMD Epyc
                      Server with Maxeler FPGA-based Dataflow Engines (DFEs), and
                      server class machines with Alveo FPGA cards installed.
                      Experimental results show that performance on robotic
                      simulation can be enhanced up to 1.2x, and CFD calculations
                      up to 4.7x. Finally, BLAS L1 routines are improved up to 7x,
                      with a performance-per-Watt ratio boost of more than 40x
                      compared to multi-threaded software routines from the Intel
                      Math Kernel Library (MKL) suite when executed on an Intel
                      Xeon server-class machine.},
      month         = {May},
      date          = {2023-05-09},
      organization  = {CF '23: 20th ACM International
                       Conference on Computing Frontiers,
                       Bologna (Italy), 9 May 2023 - 11 May
                       2023},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5121 - Supercomputing $\&$ Big Data Facilities (POF4-512) /
                      OPTIMA - Optimizing Industrial Applications for
                      Heterogeneous HPC systems (955739) / ATML-X-DEV - ATML
                      Accelerating Devices (ATML-X-DEV)},
      pid          = {G:(DE-HGF)POF4-5121 / G:(EU-Grant)955739 /
                      G:(DE-Juel-1)ATML-X-DEV},
      typ          = {PUB:(DE-HGF)26},
      UT           = {WOS:001116950900050},
      doi          = {10.1145/3587135.3592177},
      url          = {https://juser.fz-juelich.de/record/1019555},
}