| commit | 77d7fe67bbc6df4776c84fcc209ab674addacfae | |
| author | Szilárd Páll <pall.szilard@gmail.com> | |
| Mon, 16 Oct 2017 18:15:25 +0000 (16 20:15 +0200) | ||
| committer | Berk Hess <hess@kth.se> | |
| Thu, 26 Oct 2017 10:16:31 +0000 (26 12:16 +0200) | ||
| tree | 34a832324aa43aa6dd87e9c40ce24c67e3680c8a | treesnapshot (tar.gz zip) |
| parent | 262938e6885f938617693387278fe048300b0611 | commitdiff |
Reorganize PME GPU launch
Wrapped the first (prep/spread) and second stage (fft/gather) of PME GPU
in functions. Moved the second stage of the regular PME GPU mode to after
the nonbonded x transform to ensure that the transform can overlap with
spread even when the launch overhead of the FFT kernels is high.
Also removed TPI-related PME-GPU launch conditions as this should be
checked much earlier. Noted in the force flags docs that the current
code assumes GMX_FORCE_STATECHANGED is used only with TPI.
Change-Id: I7f765d66c6c4e7e54812b81b2dd23751af0b06b5
Wrapped the first (prep/spread) and second stage (fft/gather) of PME GPU
in functions. Moved the second stage of the regular PME GPU mode to after
the nonbonded x transform to ensure that the transform can overlap with
spread even when the launch overhead of the FFT kernels is high.
Also removed TPI-related PME-GPU launch conditions as this should be
checked much earlier. Noted in the force flags docs that the current
code assumes GMX_FORCE_STATECHANGED is used only with TPI.
Change-Id: I7f765d66c6c4e7e54812b81b2dd23751af0b06b5
| src/gromacs/mdlib/force_flags.h | diffblobblamehistory | |
| src/gromacs/mdlib/sim_util.cpp | diffblobblamehistory |