Why were most of the benchmarks not carried over from CPU2006, HPC2002 or OMP2001?
Many applications in the CPU2006 suite were not designed to run with MPI parallelism, so would not realistically measure MPI performance. The benchmarks in the HPC2002 and OMP2001 suites either • are older applications that have been replaced by more general, more exact, or more efficient applications that solve the same problem, • are not native MPI-parallel applications, • do not scale well to the sizes of modern systems, • for some reason it was not possible to create a longer-running or more robust workload, or • SPEC felt that they did not add significant performance information compared to the other benchmarks under consideration.
Many applications in the CPU2006 suite were not designed to run with MPI parallelism, so would not realistically measure MPI performance. The benchmarks in the HPC2002 and OMP2001 suites either • are older applications that have been replaced by more general, more exact, or more efficient applications that solve the same problem, • are not native MPI-parallel applications, • do not scale well to the sizes of modern systems, • for some reason it was not possible to create a longer-running or more robust workload, or • SPEC felt that they did not add significant performance information compared to the other benchmarks under consideration.
