We report on GPU implementations of block-level addition, subtraction, multiplication and division for midsize integers, with operands of $2^{15}$ to $2^{19}$ bits using the high-level functional language Futhark. Comparing with hand-written C++/CUDA versions and CGBN, we identify which functional constructs compile well, where memory placement and sequentialization are effective, and what compiler support is needed. The results show that high-level code can express the algorithms compactly while approaching competitive performance after certain compiler improvements. In particular, we find that automated placement of arrays in GPU register memory is critical for performance.

翻译：暂无翻译