Introduction
Introduction Statistics Contact Development Disclaimer Help
tUncomment kernel - cuda-memscrub - scrubs the global device memory of CUDA GPUs
git clone git://src.adamsgaard.dk/cuda-memscrub
Log
Files
Refs
README
LICENSE
---
commit 1cf91a1710beee16200b48487cacf9bc45bb4938
parent 497671ceb1dd0f33aa11ad69d23fc579c8dc27dc
Author: Anders Damsgaard <[email protected]>
Date: Mon, 13 Jan 2014 13:40:43 +0100
Uncomment kernel
Diffstat:
M README.md | 2 +-
M scrub.cu | 3 +--
2 files changed, 2 insertions(+), 3 deletions(-)
---
diff --git a/README.md b/README.md
t@@ -23,7 +23,7 @@ The build options are configured in the `Makefile`. To build…
The application can optionally be installed at system level in `/usr/local/bin`
by calling:
- `make install`
+ `sudo make install`
Author
------
diff --git a/scrub.cu b/scrub.cu
t@@ -10,7 +10,6 @@
__global__ void write_value(int* d_mem, long unsigned int n_ints,
unsigned int nx, unsigned int ny)
{
- /*
// 3d thread index
unsigned int x = blockDim.x * blockIdx.x + threadIdx.x;
unsigned int y = blockDim.y * blockIdx.y + threadIdx.y;
t@@ -22,7 +21,7 @@ __global__ void write_value(int* d_mem, long unsigned int n_…
if (idx < n_ints) {
__syncthreads();
d_mem[idx] = VALUETOWRITE;
- }*/
+ }
}
int main(int argc, char** argv)
You are viewing proxied material from mx1.adamsgaard.dk. The copyright of proxied material belongs to its original authors. Any comments or complaints in relation to proxied material should be directed to the original authors of the content concerned. Please see the disclaimer for more details.