PMPI_Bcast: Message truncated,

PMPI_Bcast: Message truncated,

Hi,

I am trying to debug some problems with getting an exe developed by another group in our company to run on Intel MPI. I am using Linux version 4.1.

Debug  output as below....

Does the error indicate a "programming error" on their part ( buffers not sized correctly?) or some other issue.

Thanks

[0] MPI startup(): Intel(R) MPI Library, Version 4.1 Update 2  Build 20131023
[0] MPI startup(): Copyright (C) 2003-2013 Intel Corporation.  All rights reserved.
[0] MPI startup(): shm and tcp data transfer modes
[1] MPI startup(): shm and tcp data transfer modes
[0] MPI startup(): Recognition mode: 2, selected platform: 8 own platform: 8
[1] MPI startup(): Recognition mode: 2, selected platform: 8 own platform: 8

 

[0] MPI startup(): Rank    Pid      Node name     Pin cpu
[0] MPI startup(): 0       30601    linuxdev      {0,1,2,3}
[0] MPI startup(): 1       15240    centosserver  {0,1,2,3}
[0] MPI startup(): Recognition=2 Platform(code=8 ippn=0 dev=5) Fabric(intra=1 inter=6 flags=0x0)
[0] MPI startup(): Topology split mode = 1

[1] MPI startup(): Recognition=2 Platform(code=8 ippn=0 dev=5) Fabric(intra=1 inter=6 flags=0x0)
| rank | node | space=2
|  0  |  0  |
|  1  |  1  |
[0] MPI startup(): I_MPI_DEBUG=100
[0] MPI startup(): I_MPI_FABRICS=shm:tcp
[0] MPI startup(): I_MPI_INFO_BRAND=Intel(R) Xeon(R)
[0] MPI startup(): I_MPI_INFO_CACHE1=0,1,2,3
[0] MPI startup(): I_MPI_INFO_CACHE2=0,1,2,3
[0] MPI startup(): I_MPI_INFO_CACHE3=0,0,0,0
[0] MPI startup(): I_MPI_INFO_CACHES=3
[0] MPI startup(): I_MPI_INFO_CACHE_SHARE=2,2,16
[0] MPI startup(): I_MPI_INFO_CACHE_SIZE=32768,262144,6291456
[0] MPI startup(): I_MPI_INFO_CORE=0,1,2,3
[0] MPI startup(): I_MPI_INFO_C_NAME=Wolfdale
[0] MPI startup(): I_MPI_INFO_DESC=1342208505
[0] MPI startup(): I_MPI_INFO_FLGB=0
[0] MPI startup(): I_MPI_INFO_FLGC=398124031
[0] MPI startup(): I_MPI_INFO_FLGD=-1075053569
[0] MPI startup(): I_MPI_INFO_LCPU=4
[0] MPI startup(): I_MPI_INFO_MODE=263
[0] MPI startup(): I_MPI_INFO_PACK=0,0,0,0
[0] MPI startup(): I_MPI_INFO_SERIAL=E31225
[0] MPI startup(): I_MPI_INFO_SIGN=132775
[0] MPI startup(): I_MPI_INFO_STATE=0
[0] MPI startup(): I_MPI_INFO_THREAD=0,0,0,0
[0] MPI startup(): I_MPI_INFO_VEND=1
[0] MPI startup(): I_MPI_PIN_INFO=x0,1,2,3
[0] MPI startup(): I_MPI_PIN_MAPPING=1:0 0

.....

 

                     
Fatal error in PMPI_Bcast: Message truncated, error stack:
PMPI_Bcast(2112)......................: MPI_Bcast(buf=0x2ae6d2ef9010, count=1, dtype=USER<vector>, root=0, comm=0x84000000) failed
MPIR_Bcast_impl(1670).................:
I_MPIR_Bcast_intra(1887)..............: Failure during collective
MPIR_Bcast_intra(1524)................: Failure during collective
MPIR_Bcast_intra(1510)................:
MPIR_Bcast_scatter_ring_allgather(841):
MPIDI_CH3U_Receive_data_found(129)....: Message from rank 0 and tag 2 truncated; 50000000 bytes received but buffer size is 20000000
MPIR_Bcast_scatter_ring_allgather(789):
scatter_for_bcast(301)................:
MPIDI_CH3U_Receive_data_found(129)....: Message from rank 0 and tag 2 truncated; 50000000 bytes received but buffer size is 20000000
rank = 1, revents = 8, state = 8

3 Beiträge / 0 neu
Letzter Beitrag
Nähere Informationen zur Compiler-Optimierung finden Sie in unserem Optimierungshinweis.

That error indicates that the MPI_Bcast call is trying to send too large of a message.  Keep the message under 2 GB and it should work.

Sincerely,
James Tullos
Technical Consulting Engineer
Intel® Cluster Tools

Excellent, thanks for  the tip!

Melden Sie sich an, um einen Kommentar zu hinterlassen.