diff options
| author | Adrian Kummerlaender | 2019-10-26 23:00:50 +0200 |
|---|---|---|
| committer | Adrian Kummerlaender | 2019-10-26 23:00:50 +0200 |
| commit | 7fa72d8718d96727bcfd60cc3bcb1609526d3c9b (patch) | |
| tree | 826f7b1380c1c735cc17d52c81f508ca3d90e31a /boltzgen.py | |
| parent | 2a976c2c60565ea3f904feaf4ea573b2769e3084 (diff) | |
| download | boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar.gz boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar.bz2 boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar.lz boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar.xz boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.tar.zst boltzgen-7fa72d8718d96727bcfd60cc3bcb1609526d3c9b.zip | |
Add extra toggle for OpenMP in C++ test function
Yields ~160 MLUPs on a Xeon E3-1241 for D2Q9 double precision lid driven cavity.
Obviously not anywhere near what is possible on GPUs but respectable for a CPU implementation.
Especially considering how simple it is.
Diffstat (limited to 'boltzgen.py')
0 files changed, 0 insertions, 0 deletions