portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-17 15:27:06 +01:00
Code Releases Activity

Fixed Lanczos calling aligned alloc in threaded region hitting up against pointer-cache no-threading restrictions

Browse Source 
Fixed Lattice::reset not compiling with new Grid explicit memory region handling
Fixed memory leak in Lattice::resize that occurs when data region has been previously allocated
This commit is contained in:
Christopher Kelly
2019-08-26 16:47:44 -04:00
parent 9b7a6d197f
commit 114ebb7914
2 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Grid/algorithms/iterative/ImplicitlyRestartedLanczos.h
View File

@ -62,9 +62,12 @@ void basisRotate(std::vector<Field> &basis,Eigen::MatrixXd& Qt,int j0, int j1, i
basis_v[k] = basis[k].View();
}
std::vector < vobj , commAllocator<vobj> > Bt(thread_max() * Nm); // Thread private
thread_region
{
std::vector < vobj , commAllocator<vobj> > B(Nm); // Thread private
vobj* B = Bt.data() + Nm * thread_num();
thread_for_in_region(ss, grid->oSites(),{
for(int j=j0; j<j1; ++j) B[j]=0.;