concept default in category parallel computing

appears as: default, default, The default, defaults
Parallel and High Performance Computing

This is an excerpt from Manning's book Parallel and High Performance Computing.

find_package(Vector)
if (CMAKE_VECTOR_VERBOSE)
   set(VECTOR_C_FLAGS "${VECTOR_C_FLAGS} ${VECTOR_C_VERBOSE}")
endif()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${VECTOR_C_FLAGS}")
  • #pragma omp simd - vectorize the following loop or block of code
  • When thinking about a parallel application, we have a set of processes and a set of processors. How do we map the processes to the processors? In the previous example, we wanted to spread the processes over four nodes so that every process would have more memory than they would if they were on a single node. The more general form for mapping processes in OpenMPI is --map-by hwresource, where the argument is any of a large number of hardware components. The most common are