Skip to content

GitLab

Commit c4008bb2 authored by Peter Eastman's avatar Peter Eastman
Browse files

Increased block sizes on Fermi

parent 2bce659f
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
plugins/amoeba/platforms/cuda/src/kernels/kCalculateAmoebaCudaMutualInducedAndGkFields.cu
View file @ c4008bb2
......@@ -578,7 +578,7 @@ static void cudaComputeAmoebaMutualInducedAndGkFieldMatrixMultiply( amoebaGpuCon
if( threadsPerBlock == 0 ){
unsigned int maxThreads;
if (gpu->sm_version >= SM_20)
maxThreads = 256;
maxThreads = 384;
else if (gpu->sm_version >= SM_12)
maxThreads = 128;
else
......
plugins/amoeba/platforms/cuda/src/kernels/kCalculateAmoebaCudaMutualInducedAndGkFields.h
View file @ c4008bb2
......@@ -28,7 +28,7 @@
__global__
#if (__CUDA_ARCH__ >= 200)
__launch_bounds__(256, 1)
__launch_bounds__(384, 1)
#elif (__CUDA_ARCH__ >= 130)
__launch_bounds__(128, 1)
#else
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment