Optimizing CUDA L2 norm.

src/core/cuda/CMakeLists.txt

src/core/cuda/cuda-prefix-sum_impl.cu

src/core/cuda/cuda-prefix-sum_impl.h

src/core/cuda/cuda-reduction-abs-max_impl.cu

src/core/cuda/cuda-reduction-abs-min_impl.cu

src/core/cuda/cuda-reduction-abs-sum_impl.cu

src/core/cuda/cuda-reduction-and_impl.cu

src/core/cuda/cuda-reduction-diff-abs-max_impl.cu

src/core/cuda/cuda-reduction-diff-abs-min_impl.cu

src/core/cuda/cuda-reduction-diff-abs-sum_impl.cu

src/core/cuda/cuda-reduction-diff-l2-norm_impl.cu

src/core/cuda/cuda-reduction-diff-lp-norm_impl.cu

src/core/cuda/cuda-reduction-diff-max_impl.cu

src/core/cuda/cuda-reduction-diff-min_impl.cu

src/core/cuda/cuda-reduction-diff-sum_impl.cu

src/core/cuda/cuda-reduction-equalities_impl.cu

src/core/cuda/cuda-reduction-inequalities_impl.cu

src/core/cuda/cuda-reduction-l2-norm_impl.cu

src/core/cuda/cuda-reduction-lp-norm_impl.cu

src/core/cuda/cuda-reduction-max_impl.cu