| commit | 2aa05015eeb6d3352d0871958a7903ecb2fabd8d | |
| author | Szilárd Páll <pall.szilard@gmail.com> | |
| Sun, 19 Mar 2017 23:47:32 +0000 (20 00:47 +0100) | ||
| committer | Aleksei Iupinov <a.yupinov@gmail.com> | |
| Sat, 25 Mar 2017 09:56:53 +0000 (25 10:56 +0100) | ||
| tree | 03a29c6d1814676ab06b6f0eff5b6cb3e5fab186 | treesnapshot (tar.gz zip) |
| parent | a1bffbe185c573ee113da97a30290fa89dea9fd1 | commitdiff |
Conditional tweak in the nonbonded GPU kernels
GPU compilers miss an easy optimization of a loop invariant in the
inner-lop conditional. Precomputing part of the conditional together
with using bitwise instead of logical and/or improves performance with
most compilers by up to 5%.
Change-Id: I3ba0b9025b11af3d8465e0d26ca69a78e32a0ece
GPU compilers miss an easy optimization of a loop invariant in the
inner-lop conditional. Precomputing part of the conditional together
with using bitwise instead of logical and/or improves performance with
most compilers by up to 5%.
Change-Id: I3ba0b9025b11af3d8465e0d26ca69a78e32a0ece