deletions | additions       diff --git a/CUDA_Implementation.tex b/CUDA_Implementation.tex  index 072f0e1..dc849d0 100644  --- a/CUDA_Implementation.tex  +++ b/CUDA_Implementation.tex 
...
\begin{verbatim}  cudaMalloc((void**)&devCurrentDataLocus,numObs*sizeof(float));  cudaMalloc((void**)&devRInverseY,numObs*sizeof(float)); cudaMemcpy(devCurrentDataLocus,currentDataLocus.data(),numObs*sizeof(float),cudaMemcpyHostToDevice); cudaMemcpy(devRInverseY,RInverseY.data(),numObs*sizeof(float),cudaMemcpyHostToDevice); 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: