James Shirley edited CUDA_Implementation.tex  about 11 years ago

Commit id: 2aa3839e81055d94d9be4283a19934a475ece415

deletions | additions      

       

To do this in cuBLAS you can do the following:  /begin{verbatim}  float rhsModeli;  cublasSdot(cublasHandle,numObs,currentDataLocus.data(),0,RInverseY.data(),0,&rhsModeli);  rhsModeli += (diagLhs(i) * oldSamplei);  /end{verbatim}  You must also setup the handle that cuBLAS uses to access the GPU, this can be done like so: