Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
tsoc
openmm
Commits
bd4fb844
Commit
bd4fb844
authored
Sep 14, 2010
by
Peter Eastman
Browse files
Fixed error in launch bounds
parent
7f367d00
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
6 deletions
+6
-6
plugins/amoeba/platforms/cuda/src/kernels/kCalculateAmoebaCudaPME.cu
...eba/platforms/cuda/src/kernels/kCalculateAmoebaCudaPME.cu
+6
-6
No files found.
plugins/amoeba/platforms/cuda/src/kernels/kCalculateAmoebaCudaPME.cu
View file @
bd4fb844
...
@@ -101,11 +101,11 @@ __device__ void computeBSplinePoint(float4* thetai, float w, float* array)
...
@@ -101,11 +101,11 @@ __device__ void computeBSplinePoint(float4* thetai, float w, float* array)
*/
*/
__global__
__global__
#if (__CUDA_ARCH__ >= 200)
#if (__CUDA_ARCH__ >= 200)
__launch_bounds__
(
512
,
1
)
__launch_bounds__
(
448
,
1
)
#elif (__CUDA_ARCH__ >= 120)
#elif (__CUDA_ARCH__ >= 120)
__launch_bounds__
(
256
,
1
)
__launch_bounds__
(
160
,
1
)
#else
#else
__launch_bounds__
(
1
28
,
1
)
__launch_bounds__
(
1
60
,
1
)
#endif
#endif
void
kComputeAmoebaBsplines_kernel
()
void
kComputeAmoebaBsplines_kernel
()
{
{
...
@@ -854,11 +854,11 @@ void kCalculateAmoebaPMEFixedMultipoleField(amoebaGpuContext amoebaGpu)
...
@@ -854,11 +854,11 @@ void kCalculateAmoebaPMEFixedMultipoleField(amoebaGpuContext amoebaGpu)
int
threads
;
int
threads
;
gpuContext
gpu
=
amoebaGpu
->
gpuContext
;
gpuContext
gpu
=
amoebaGpu
->
gpuContext
;
if
(
gpu
->
sm_version
>=
SM_20
)
if
(
gpu
->
sm_version
>=
SM_20
)
threads
=
512
;
threads
=
448
;
else
if
(
gpu
->
sm_version
>=
SM_12
)
else
if
(
gpu
->
sm_version
>=
SM_12
)
threads
=
256
;
threads
=
160
;
else
else
threads
=
1
28
;
threads
=
1
60
;
kComputeAmoebaBsplines_kernel
<<<
gpu
->
sim
.
blocks
,
threads
,
threads
*
AMOEBA_PME_ORDER
*
AMOEBA_PME_ORDER
*
sizeof
(
float
)
>>>
();
kComputeAmoebaBsplines_kernel
<<<
gpu
->
sim
.
blocks
,
threads
,
threads
*
AMOEBA_PME_ORDER
*
AMOEBA_PME_ORDER
*
sizeof
(
float
)
>>>
();
LAUNCHERROR
(
"kComputeAmoebaBsplines"
);
LAUNCHERROR
(
"kComputeAmoebaBsplines"
);
bbSort
(
gpu
->
psPmeAtomGridIndex
->
_pDevData
,
gpu
->
natoms
);
bbSort
(
gpu
->
psPmeAtomGridIndex
->
_pDevData
,
gpu
->
natoms
);
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment