On 11/01/2012 09:56 AM, J R Jones wrote:
HiI am trying to build OpenMPI 1.6.3 with the Intel compilers, but one of the tests in make check fails with a segmentation fault. I wondered if anyone else has come across this and if so, how they got around it? $ icc --version icc (ICC) 12.0.4 20110427 I have logged the output of the build process and include it as a tarball. The interesting part seems to be this, in make.check: [blue34:26873] Datatype 0x6794570[] size 36000 align 8 id 0 length 6 used 3 true_lb 0 true_ub 39592 (true_extent 39592) lb 0 ub 39592 (extent 39592) nbElems 4500 loops 2 flags 104 (commited )-c-----GD--[---][---] contain OPAL_FLOAT8 --C--------[---][---] OPAL_LOOP 450 times the next 2 elements extent 88 --C---P-D--[---][---] OPAL_FLOAT8 count 10 disp 0x0 (0) extent 8 (size 80) --C--------[---][---] OPAL_END_LOOP prev 2 elements first elem displacement 0 size of data 80 -------G---[---][---] OPAL_END_LOOP prev 3 elements first elem displacement 0 size of data 36000 Optimized description --C--------[---][---] OPAL_LOOP 450 times the next 2 elements extent 88 -cC---P-DB-[---][---] OPAL_UINT1 count 80 disp 0x0 (0) extent 1 (size 80) --C--------[---][---] OPAL_END_LOOP prev 2 elements first elem displacement 0 size of data 80 -------G---[---][---] OPAL_END_LOOP prev 3 elements first elem displacement 0 size of data 36000 /bin/sh: line 5: 26873 Segmentation fault ${dir}$tst FAIL: opal_datatype_test Has anyone seen this issue before?
Seems to be working okay for me with icc (ICC) 13.0.1 20121010 x86_64, though perhaps it's dependent on compile flags...
-- Orion Poplawski Technical Manager 303-415-9701 x222 NWRA, Boulder Office FAX: 303-415-9702 3380 Mitchell Lane or...@nwra.com Boulder, CO 80301 http://www.nwra.com
