pmode Versus spmd

pmode lets you work interactively with a communicating job running simultaneously on several workers. Commands you type at the pmode prompt in the Parallel Command Window are executed on all workers at the same time. Each worker executes the commands in its own workspace on its own variables.

The way the workers remain synchronized is that each worker becomes idle when it completes a command or statement, waiting until all the workers working on this job have completed the same statement. Only when all the workers are idle, do they then proceed together to the next pmode command.

In contrast to spmd, pmode provides a desktop with a display for each worker running the job, where you can enter commands, see results, access each worker's workspace, etc. What pmode does not let you do is to freely interleave serial and parallel work, like spmd does. When you exit your pmode session, its job is effectively destroyed, and all information and data on the workers is lost. Starting another pmode session always begins from a clean state.

Was this topic helpful?