Error when running tool

Yong-Ju — Thu, 18 Sep 2025 01:44:18 GMT

The following error was displayed when running QuantumATK software.

Do you have any guide to resolve the issue ?

[nsw_psadmin@cds-lstc01-vn01-r7cp128-001 tool_check]$ quantumatk [1758001114.064839] [cds-lstc01-vn01-r7cp128-001:21442:0] ucp_context.c:1197 UCX WARN transport 'rc' is not available, please use one or more of: cma, mm, posix, self, shm, sm, sysv, tcp [1758001114.066771] [cds-lstc01-vn01-r7cp128-001:21442:0] sys.c:915 UCX ERROR shmget(size=36864 flags=0x7b0) for mm_recv_fifo failed: No space left on device, please check shared memory limits by 'ipcs -l' [1758001114.066782] [cds-lstc01-vn01-r7cp128-001:21442:0] mm_sysv.c:114 UCX ERROR failed to allocate 33023 bytes with mm for mm_recv_fifo [1758001114.066791] [cds-lstc01-vn01-r7cp128-001:21442:0] uct_mem.c:157 UCX ERROR failed to allocate 33023 bytes using md sysv for mm_recv_fifo: Out of memory [1758001114.066795] [cds-lstc01-vn01-r7cp128-001:21442:0] mm_iface.c:790 UCX ERROR mm_iface failed to allocate receive FIFO Abort(1615247) on node 0 (rank 0 in comm 0): Fatal error in PMPI_Init: Unknown error class, error stack: MPIR_Init_thread(196)........: MPID_Init(1719)..............: MPIDI_OFI_mpi_init_hook(1690): create_vni_context(2277).....: OFI endpoint open failed (ofi_init.c:2277:create_vni_context:Cannot allocate memory) [unset]: write_line error; fd=-1 buf=:cmd=abort exitcode=1615247 : system msg for write_line failure : Bad file descriptor Abort(1615247) on node 0 (rank 0 in comm 0): Fatal error in PMPI_Init: Unknown error class, error stack: MPIR_Init_thread(196)........: MPID_Init(1719)..............: MPIDI_OFI_mpi_init_hook(1690): create_vni_context(2277).....: OFI endpoint open failed (ofi_init.c:2277:create_vni_context:Cannot allocate memory) [unset]: write_line error; fd=-1 buf=:cmd=abort exitcode=1615247 : system msg for write_line failure : Bad file descriptor [cds-lstc01-vn01-r7cp128-001:21442:0:21442] Caught signal 11 (Segmentation fault: address not mapped to object at address (nil)) ==== backtrace (tid: 21442) ==== 0 0x000000000045a906 MPIR_Err_return_comm() ???:0 1 0x00000000005a3336 MPI_Init() ???:0 …

Re: Error when running tool

TobiasK — Fri, 10 Oct 2025 16:41:22 GMT

@Yong-Ju from the log it seems you have UCX installed but not Infiniband device or at least configured the UCX/Infiniband stack not correctly:
UCX WARN transport 'rc' is not available, please use one or more of: cma, mm, posix, self, shm, sm, sysv, tcp

If you are running a single node job, please set
I_MPI_FABRICS=shm
to disable OFI and the network stack

topic Error when running tool in Intel® MPI Library

Error when running tool

Re: Error when running tool