@inproceedings{oai:repo.qst.go.jp:00078195,
 author = {Asahi, Yuuichi and Latu, Guillaume and Grandgirard, Virginie and Bigot, Julien and Yuuichi, Asahi},
 book = {WACCPD 2019: Accelerator Programming Using Directives},
 month = {Dec},
 note = {Performance portability is considered to be an inevitable requirement
in the exascale era. We explore a performance portable approach
for fusion plasma turbulence simulation code employing kinetic
model, namely the GYSELA code. For this purpose, we extract the
key features of GYSELA such as the high dimensionality and the semi-
Lagrangian scheme, and encapsulate them into a mini-application which
solves the similar but a simplied Vlasov-Poisson system. We implement
the mini-app with a mixed OpenACC/OpenMP and Kokkos implementation,
where we suppress unnecessary duplications of code lines. For
a reference case with the problem size of 1284, the Skylake (Kokkos),
Nvidia Tesla P100 (OpenACC), and P100 (Kokkos) versions achieve an
acceleration of 1.45, 12.95, and 17.83, respectively, with respect to the
baseline OpenMP version on Intel Skylake. In addition to the performance
portability, we discuss the code readability and productivity of
each implementation. Based on our experience, Kokkos can oer a readable
and productive code at the cost of initial porting eorts, which
would be enormous for a large scale simulation code like GYSELA.},
 pages = {117--139},
 publisher = {Springer},
 title = {Performance portable implementation of a kinetic plasma simulation mini-app},
 volume = {12017},
 year = {2019}
}