PARALLEL NUMERICAL COMPUTATION: A COMPARATIVE STUDY ON CPU-GPU PERFORMANCE IN PI DIGITS COMPUTATION

As the usage of GPU (Graphical Processing Unit) for non-graphical computation is rising, one important area to study how device helps improve numerical calculations. In this work, we present a time performance comparison between purely CPU (serial) and GPU-assisted (parallel) programs in computation. Specifically, design implement calculation hexadecimal -digit irrational number Pi two ways: serial parallel. Both are based upon BBP formula form infinite series identity. We then provide detailed analysis both on magnitude. Our result shows that parallel algorithm ran hundred times faster than algorithm. To be more precise, offer as value grows, ratio execution algorithms also increases. Moreover, when it large enough, This efficiency converges constant, showing GPU's maximally utilized capacity. On other hand, sufficiently small performed solely works since parallelism does not help much compared arithmetic complexity.