Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix cuaev angular kernel bug when center atom pairs are more than 32 #555

Merged
merged 1 commit into from
Nov 27, 2020
Merged

Fix cuaev angular kernel bug when center atom pairs are more than 32 #555

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions tests/test_cuaev.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,6 +94,18 @@ def testNIST(self):
_, cu_aev = self.cuaev_computer((species, coordinates))
self.assertEqual(cu_aev, aev)

def testVeryDenseMolecule(self):
for i in range(100):
datafile = os.path.join(path, 'test_data/tripeptide-md/{}.dat'.format(i))
with open(datafile, 'rb') as f:
coordinates, species, _, _, _, _, _, _ = pickle.load(f)
# change angstrom coordinates to 10 times smaller
coordinates = 0.1 * torch.from_numpy(coordinates).float().unsqueeze(0).to(self.device)
species = torch.from_numpy(species).unsqueeze(0).to(self.device)
_, aev = self.aev_computer((species, coordinates))
_, cu_aev = self.cuaev_computer((species, coordinates))
self.assertEqual(cu_aev, aev, atol=5e-5, rtol=5e-5)


if __name__ == '__main__':
unittest.main()
2 changes: 1 addition & 1 deletion torchani/cuaev/aev.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,7 +209,7 @@ __global__ void cuAngularAEVs(
theta = acos(0.95 * (sdx[jj] * sdx[kk] + sdy[jj] * sdy[kk] + sdz[jj] * sdz[kk]) / (Rij * Rik));
}

for (int srcLane = 0; kk_start + srcLane < min(32, jnum); ++srcLane) {
for (int srcLane = 0; srcLane < 32 && (kk_start + srcLane) < jnum; ++srcLane) {
int kk = kk_start + srcLane;
DataT theta_ijk = __shfl_sync(0xFFFFFFFF, theta, srcLane);

Expand Down