GPU Acceleration of Collinear and Noncollinear DFT Using a Numerical Atomic Orbital-Based DFT Code
We implement GPU acceleration of collinear and noncollinear density functional theory (DFT) calculations in the numerical atomic orbitals (NAOs) code OpenMX by offloading matrix multiplications and eigenvalue solves (plus selected auxiliary steps) to cuBLAS/cuSOLVER and OpenACC. Benchmarks on the Pegasus supercomputer (per node: a 48-core Intel Xeon Platinum 8468 CPU and one NVIDIA H100 GPU) compare GPU-accelerated and CPU-only runs under identical settings. For a 512-atom collinear case on two nodes (two GPUs total), the GPU-accelerated calculation achieves a 2.02 times speedup over a CPU-only run on two nodes (96 CPU cores total); for a 384-atom noncollinear case on two nodes (two GPUs total), the speedup is 2.60 times over two CPU-only nodes (96 cores). These results demonstrate practical GPU-accelerated DFT in an NAO-based code for both collinear and noncollinear calculations.