Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Intel nightly test failures: team_vector #2852

Closed
ndellingwood opened this issue Mar 11, 2020 · 6 comments
Closed

Intel nightly test failures: team_vector #2852

ndellingwood opened this issue Mar 11, 2020 · 6 comments
Assignees
Labels
Bug Broken / incorrect code; it could be Kokkos' responsibility, or others’ (e.g., Trilinos)

Comments

@ndellingwood
Copy link
Contributor

The intel/15.0.2, intel/16.0.3, intel/17.0.1 Serial nightly tests are failing on kokkos-dev with the following sample failure output:

19:26:08 1: [ RUN      ] serial.team_vector
19:26:08 1: FAILED vector_par_reduce_reducer 0 0 86400.000000 43200.000000
19:26:08 1: FAILED vector_par_reduce_reducer 1 0 86400.000000 43200.000000
...
[  FAILED  ] serial.team_vector

Sample reproducer instructions:

 # Reproducer instructions:
  #   Load modules:
        module load sems-env sems-cmake/3.12.2 kokkos-env kokkos-hwloc/1.10.1/base sems-intel/15.0.2

  #   Use generate_makefile line below to call cmake which generates makefile for this build:
        <KOKKOS_PATH>/generate_makefile.bash --with-devices=Serial --arch=Kepler35 --compiler=/projects/sems/install/rhel6-x86_64/sems/compiler/intel/15.0.2/base/bin/icpc --cxxflags="-O3 -Wall -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="11" --ldflags=""  --kokkos-path=<KOKKOS_PATH> --no-examples --with-options=enable_large_mem_tests
@ndellingwood ndellingwood added Bug Broken / incorrect code; it could be Kokkos' responsibility, or others’ (e.g., Trilinos) DevelopOnly Blocks Promotion Overview issue for release-blocking bugs labels Mar 11, 2020
@ndellingwood ndellingwood added this to the Tentative 3.1 Release milestone Mar 11, 2020
@ndellingwood
Copy link
Contributor Author

Potential culprit PRs: #2839 or #2605
Adding @crtrott and @jeffmiles63

@crtrott
Copy link
Member

crtrott commented Mar 11, 2020

It can't be 2839 since that only touches containers ...

@crtrott
Copy link
Member

crtrott commented Mar 11, 2020

Yeah it was #2605

a0d011f shows the problem, 07ac180 does not.

commit a0d011fb30022362c61b3bb000ae3de6906cb6a7
Merge: 07ac180 0002adb
Author: Christian Trott <crtrott@sandia.gov>
Date:   Tue Mar 10 08:42:47 2020 -0700

    Merge pull request #2605 from jeffmiles63/prototype-view-tracker
    
    Add ViewTracking Layer between View and SharedAllocation Tracker

commit 07ac1808ad5438f471c01e45e7e6658a41be7a6e
Merge: e4a31d6 f3e03f6
Author: Christian Trott <crtrott@sandia.gov>
Date:   Tue Mar 10 07:56:22 2020 -0700

    Merge pull request #2839 from crtrott/device-type-for-scatter-view
    
    Device type for scatter view

@crtrott
Copy link
Member

crtrott commented Mar 11, 2020

Doesn't make any sense though ...

@crtrott
Copy link
Member

crtrott commented Mar 11, 2020

OK I think I gonna revert that PR and we figure it out after the release ...

@ndellingwood
Copy link
Contributor Author

Reversion of #2855 fixed the issues, older intel nightlies are now passing again. Removing BLOCKS PROMOTION and closing the issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Bug Broken / incorrect code; it could be Kokkos' responsibility, or others’ (e.g., Trilinos)
Projects
None yet
Development

No branches or pull requests

2 participants