Cuda Visual Profiler unspecified launch failure - profiling

Question

So when I run my code it executes perfectly, but when I try to run it in Visual Profiler it works the first time, but it seems to want to run the program seven times, and the second time it results in an unspecified launch failure. Why would that happen? My code looks like below, and my error checking tells me the error is occurring with
cudaMemcpy(p->siteset, rsites, sitesize, cudaMemcpyDeviceToHost);
(Probably easiest to find in the code by searching for memcpy11, it'll be the line above)
I can't think of a reason a program would essentially seg fault the second time it's run but not the first, and if I run it multiple times in terminal it's totally fine. Can anyone come up with what might be going on?
Thanks!
void fillin(node *p, node *left, node *rt)
{
size_t stepsize = chars * sizeof(long);
size_t sitesize = chars * sizeof(sitearray);
seqptr lsites;
cudaMalloc((void **) &lsteps, stepsize);
checkCUDAError("malloc");
cudaMalloc((void **) &lsites, sitesize);
checkCUDAError("malloc");
cudaMemcpy(lsteps, left->numsteps, stepsize, cudaMemcpyHostToDevice);
checkCUDAError("memcpy7");
cudaMemcpy(lsites, left->siteset, sitesize, cudaMemcpyHostToDevice);
checkCUDAError("memcpy8");
steptr rsteps;
seqptr rsites;
cudaMalloc((void **) &rsteps, stepsize);
checkCUDAError("malloc");
cudaMalloc((void **) &rsites, sitesize);
checkCUDAError("malloc");
cudaMemcpy(rsteps, rt->numsteps, stepsize, cudaMemcpyHostToDevice);
checkCUDAError("memcpy9");
cudaMemcpy(rsites, rt->siteset, sitesize, cudaMemcpyHostToDevice);
checkCUDAError("memcpy");
//call kernel
int block_size = 1;
int n_blocks = chars;
fillinBoth <<<n_blocks, block_size>>> (lsteps, lsites, rsteps, rsites, chars);
cudaMemcpy(p->numsteps, rsteps, stepsize, cudaMemcpyDeviceToHost);
checkCUDAError("memcpy10");
cudaMemcpy(p->siteset, rsites, sitesize, cudaMemcpyDeviceToHost);
checkCUDAError("memcpy11");
cudaFree(rsites); cudaFree(rsteps);
cudaFree(lsites); cudaFree(lsteps);
checkCUDAError("free");
}
}
__global__ void fillinBoth (steptr lsteps, seqptr lsite, steptr rsteps, seqptr rsite, long max){
boolean counted;
aas aa;
long s;
long i, j, k, n;
int idx = blockIdx.x;
//reduce array references; may or may not be useful
__shared__ long ls[3];
__shared__ long rs[3];
__shared__ long qs[3];
counted = false;
k = 0;
//computation from original program, but now need to do manual address calculation
if(idx < max){
for(i = 0; i < 3; i++){
rs[i]=rsite[idx][i];
ls[i]=lsite[idx][i];
}
n = lsteps[idx] + rsteps[idx];
counted = false;
for (i = 0; i <= 5; i++) {
if (k < 3) {
switch (i) {
case 0:
s = ls[0] & rs[0];
break;
case 1:
s = (ls[0] & rs[1]) | (ls[1] & rs[0]);
break;
case 2:
s = (ls[0] & rs[2]) | (ls[1] & rs[1]) | (ls[2] & rs[0]);
break;
case 3:
s = ls[0] | (ls[1] & rs[2]) | (ls[2] & rs[1]) | rs[0];
break;
case 4:
s = ls[1] | (ls[2] & rs[2]) | rs[1];
break;
case 5:
s = ls[2] | rs[2];
break;
}
if (counted || s != 0) {
qs[k] = s;
k++;
counted = true;
} else if (!counted)
n += cudaWeight[idx];
}
}
for (i = 0; i <= 1; i++) {
for (aa = ala; (long)aa <= (long)stop; aa = (aas)((long)aa + 1)) {
if (((1L << ((long)aa)) & qs[i]) != 0) {
for (j = i + 1; j <= 2; j++)
qs[j] |= cudaTranslate[(long)aa - (long)ala][j - i];
}
}
}
rsteps[idx] = n;
for(i = 0; i < 3; i++)
rsite[idx][i]=qs[i];
}
}

Answer 1

Try to disable all counters in the profile session settings. Also try to remove all files like "temp_compute_profiler_1_1.csv" from your working folder (see profile setting "Working Folder", by default in is the same with the place of your executable).
There is the same error (OpenCL over CUDA): http://www.khronos.org/message_boards/viewtopic.php?t=4324