These copies, along with possible scalings or transpositions, are
implemented as CUDA kernels which can be applied to two
matrices of any size starting at any offset.
- Memory accesses are coalesced\index{coalesced memory accesses} \cite{CUDA_ProgGuide} in order to
+ Memory accesses are coalesced\index{GPU!coalesced memory accesses} \cite{CUDA_ProgGuide} in order to
provide the best performance for such memory-bound kernels.
\item[Step 2] (``Local copies''):~data are copied from
local $R$-matrices to temporary arrays ($U$, $V$) and to $\Re^{O}$.
