The High Performance Conjugate Gradients (HPCG) benchmark is designed to measure performance that is representative of modern scientific applications. It does so by exercising the computational and communication patterns that are commonly found in real science and engineering codes, which are often based on sparse iterative solvers. HPCG exhibits the same irregular accesses to memory and fine-grain recursive computations that dominate large-scale scientific workloads used to simulate complex physical phenomena. As an emerging HPC metric of choice, HPCG implements the preconditioned conjugate gradient algorithm with a local symmetric Gauss-Seidel as the preconditioner. Additionally, the essential components of the geometric multigrid method are present in the code as a way to represent execution patterns of modern multigrid solvers.
HPCG 3.0 Reference Code was released on November 11, 2015 for the SC15 conference in Austin, TX. In addition to bug fixes, this release positions HPCG to even better represent modern PDE solvers, which reflect the behavior of explicit methods that involve unassembled matrices, and aids in running HPCG on production supercomputing installations. The reference version is accompanied by binary releases from Intel and NVIDIA that are carefully optimized for the vendors’ respective hardware platforms. Since its inception in 2013, the community’s reception of the benchmark has been overwhelmingly positive, and the constant feedback leads to the continuous improvement of the code and its scope. The current HPCG Performance List was released at SC16 and now features over 100 supercomputing sites. HPCG is a collaboration between ICL and Sandia National Laboratories.
Find out more at http://www.hpcg-benchmark.org
In Collaboration With
- Sandia National Laboratories