% 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”.

@INPROCEEDINGS{Brank:911147,
      author       = {Brank, Bine and Pleiter, Dirk},
      title        = {{A}ssessing the {S}tate of {A}utovectorization {S}upport
                      based on {SVE}},
      publisher    = {IEEE},
      reportid     = {FZJ-2022-04463},
      pages        = {556–562},
      year         = {2022},
      abstract     = {So-called SIMD instructions, which trigger operations that
                      process in each clock cycle a data tuple, have become
                      widespread in modern processor architectures. In particular,
                      processors for high-performance computing (HPC) systems rely
                      on this additional level of parallelism to reach a high
                      throughput of arithmetic operations. Leveraging these SIMD
                      instructions can still be challenging for application
                      software developers. This challenge has become simpler due
                      to a compiler technique called auto-vectorization. In this
                      paper, we explore the current state of auto-vectorization
                      capabilities using state-of-the-art compilers using a recent
                      extension of the Arm instruction set architecture, called
                      SVE. We measure the performance gains on a recent processor
                      architecture supporting SVE, namely the Fujitsu A64FX
                      processor.},
      month         = {Sep},
      date          = {2022-09-05},
      organization  = {2022 IEEE International Conference on
                       Cluster Computing (CLUSTER), Heidelberg
                       (Germany), 5 Sep 2022 - 8 Sep 2022},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5122 - Future Computing $\&$ Big Data Systems (POF4-512) /
                      Mont-Blanc 2020 - Mont-Blanc 2020, European scalable,
                      modular and power efficient HPC processor (779877)},
      pid          = {G:(DE-HGF)POF4-5122 / G:(EU-Grant)779877},
      typ          = {PUB:(DE-HGF)8},
      UT           = {WOS:000920273100058},
      doi          = {10.1109/CLUSTER51413.2022.00073},
      url          = {https://juser.fz-juelich.de/record/911147},
}