You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Adding gpuErrchk ( cudaMemcpy(d_PQ,PQ,sizeof(unsigned int)*N,cudaMemcpyHostToDevice) ); in __alloc_gpu should fix this issue.
By the way, several cudaFree and free should be added to address device & host memory leaks.
Refer to master...turtleizzy:DA_STAR:master . Several api-breaking features have been added in my fork making it difficult to submit a PR directly from my fork.
The text was updated successfully, but these errors were encountered:
Hi @turtleizzy, thank you! for going through the code and finding and fixing the bugs.
Can you create a separate branch with your changes and then create pull request to the master?
PS: I have sent you the invitation to access to the repository.
There is a bug in
__alloc_gpu
(https://github.com/lkoshale/DA_STAR/blob/f17db9039e393f7b67956df51c579790bbd33f23/include/a_star.cu#L72C1-L72C40) rendering all sssp with starting node other than 0 fail to proceed.Adding
gpuErrchk ( cudaMemcpy(d_PQ,PQ,sizeof(unsigned int)*N,cudaMemcpyHostToDevice) );
in__alloc_gpu
should fix this issue.By the way, several
cudaFree
andfree
should be added to address device & host memory leaks.Refer to master...turtleizzy:DA_STAR:master . Several api-breaking features have been added in my fork making it difficult to submit a PR directly from my fork.
The text was updated successfully, but these errors were encountered: