The HPCG (High Performance Conjugate Gradient) benchmark measures how fast a computer can solve symmetric sparse linear system equations using the conjugate gradient method preconditioned with a multi-grid symmetric Gauss-Seidel smoother. Problems of this type are typically encountered in actual engineering and industrial applications, and require a balance between calculation performance, memory performance and communication performance, unlike LINPACK, which looks at calculation speed alone.
For this result, all of the K computer's 82,944 compute nodes were used, achieving a performance of 602 teraflops. This figure is higher than the supercomputers that placed higher than the K computer in the TOP500 rankings, demonstrating outstanding performance in various science and engineering fields.
According to Mike Heroux of Sandia National Laboratories, who developed the HPCG benchmark: "The HPCG benchmark is very demanding. A good score requires strong and versatile memory system performance, excellent interconnect network performance at scale, and an overall balanced system. The top ranking of the K computer is no surprise."
The award will be presented at ISC High Performance 2017 in Frankfurt, Germany.