1 # Smpi Allreduce collectives tests
5 $ $VALGRIND_NO_LEAK_CHECK ${bindir:=.}/../../../smpi_script/bin/smpirun -map -hostfile ../hostfile_coll -platform ${platfdir:=.}/small_platform.xml -np 16 --log=xbt_cfg.thres:critical ${bindir:=.}/coll-allreduce-with-leaks --log=smpi_config.thres:warning --cfg=smpi/display-allocs:yes --cfg=smpi/simulate-computation:no --log=smpi_coll.thres:error --log=smpi_mpi.thres:error --log=smpi_pmpi.thres:error
18 > [rank 12] -> Ginette
19 > [rank 13] -> Ginette
20 > [rank 14] -> Ginette
21 > [rank 15] -> Ginette
22 > If this is too much, consider sharing allocations for computation buffers.
23 > Largest allocation at once from a single process was 64 bytes, at sysdep.h:61. It was called 32 times during the whole simulation.
24 > Running smpirun with -wrapper "valgrind --leak-check=full" can provide more information
25 > This can be done automatically by setting --cfg=smpi/auto-shared-malloc-thresh to the minimum size wanted size (this can alter execution if data content is necessary)
26 > [0.023768] [smpi_utils/INFO] Probable memory leaks in your code: SMPI detected 31 unfreed MPI handles : display types and addresses (n max) with --cfg=smpi/list-leaks:n.
27 > [0.023768] [smpi_utils/INFO] Memory Usage: Simulated application allocated 2048 bytes during its lifetime through malloc/calloc calls.