intel-mpi | 易学教程

why does mpirun behave as it does when used with slurm?

阅读更多关于 why does mpirun behave as it does when used with slurm?

问题 I am using Intel MPI and have encountered some confusing behavior when using mpirun in conjunction with slurm. If I run (in a login node) mpirun -n 2 python -c "from mpi4py import MPI; print(MPI.COMM_WORLD.Get_rank())" then I get as output the expected 0 and 1 printed out. If however I salloc --time=30 --nodes=1 and run the same mpirun from the interactive compute node, I get two 0s printed out instead of the expected 0 and 1. Then, if I change -n 2 to -n 3 (still in compute node), I get a

MPI message received in different communicator - erroneous program or MPI implementation bug?

阅读更多关于 MPI message received in different communicator - erroneous program or MPI implementation bug?

问题 This is a follow-up to this previous question of mine, for which the conclusion was that the program was erroneous, and therefore the expected behavior was undefined. What I'm trying to create here is a simple error-handling mechanism, for which I use that Irecv request for the empty message as an " abort handle ", attaching it to my normal MPI_Wait call (and turning it into MPI_WaitAny ), in order to allow me to unblock process 1 in case an error occurs on process 0 and it can no longer

MPI message received in different communicator

阅读更多关于 MPI message received in different communicator

问题 It was my understanding that MPI communicators restrict the scope of communication, such that messages sent from one communicator should never be received in a different one. However, the program inlined below appears to contradict this. I understand that the MPI_Send call returns before a matching receive is posted because of the internal buffering it does under the hood (as opposed to MPI_Ssend ). I also understand that MPI_Comm_free doesn't destroy the communicator right away, but merely

MPI_SEND takes huge part of virtual memory

阅读更多关于 MPI_SEND takes huge part of virtual memory

问题 Debugging my program on big counts of kernels, I faced with very strange error of insufficient virtual memory . My investigations lead to peace of code, where master sends small messages to each slave. Then I wrote small program, where 1 master simply send 10 integers with MPI_SEND and all slaves receives it with MPI_RECV . Comparison of files /proc/self/status before and after MPI_SEND showed, that difference between memory sizes is huge! The most interesting thing (which crashes my program)

Intel MPI mpirun does not terminate using java Process.destroy()

阅读更多关于 Intel MPI mpirun does not terminate using java Process.destroy()

问题 My Intel MPI version is impi/5.0.2.044/intel64 installed on a RHEL machine. I am using java to invoke an MPI program using the following code: ProcessBuilder builder = new ProcessBuilder(); builder.command("mpirun ./myProgram"); builder.redirectError(Redirect.to(new File("stderr"))); builder.redirectOutput(Redirect.to(new File("stdout"))); Process p = null; try { p = builder.start(); } catch (IOException e) { e.printStackTrace(); } // Process has started here p.destroy(); try { // i = 143 int

Prevent MPI from busy looping

阅读更多关于 Prevent MPI from busy looping

问题 I have an MPI program which oversubscribes/overcommits its processors. That is: there are many more processes than processors. Only a few of these processes are active at a given time, though, so there shouldn't be contention for computational resources. But, much like the flock of seagulls from Finding Nemo , when those processes are waiting for communication they're all busy-looping, asking "Mine? Mine? Mine?" I am using both Intel MPI and OpenMPI (for different machines). How can I

MPI_SEND takes huge part of virtual memory

阅读更多关于 MPI_SEND takes huge part of virtual memory

Debugging my program on big counts of kernels, I faced with very strange error of insufficient virtual memory . My investigations lead to peace of code, where master sends small messages to each slave. Then I wrote small program, where 1 master simply send 10 integers with MPI_SEND and all slaves receives it with MPI_RECV . Comparison of files /proc/self/status before and after MPI_SEND showed, that difference between memory sizes is huge! The most interesting thing (which crashes my program), is that this memory won't deallocate after MPI_Send and still take huge space. Any ideas? System