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

src/batched: Add BatchedDblBufGemm #1095

Merged
merged 21 commits into from Sep 30, 2021
Merged

Conversation

e10harvey
Copy link
Contributor

@e10harvey e10harvey commented Sep 3, 2021

This PR adds a new "double buffering" algorithm to the KokkosBatched namespace in kokkos-kernels. The PR also updates the BatchedGemm SQUARE heuristic to conditionally use BatchedDblBufGemm on GPUs with a tile size of 32x32x8.

Performance of BatchedGemm SQUARE heuristic on V100

LayoutLeft, BatchLayout::Right

$ ./KokkosBlas3_perf_test.LL --test=batched --routines=gemm --loop_type=parallel --batch_size_last_dim=1 --matrix_size_start=2x2,2x2,2x2 --matrix_size_stop=64x64,64x64,64x64 --matrix_size_step=2 --batch_size=$((80*1024)) --warm_up_loop=10 --iter=20 --verify=0
Testing gemm...
SCALAR:d, LAYOUT:N6Kokkos10LayoutLeftE, DEVICE:N6Kokkos4CudaE, SPACE:N6Kokkos9CudaSpaceE
algorithm vector_type transAtransB alpha beta team_size vector_len loop_type A_dims B_dims C_dims warm_up_n iter total_time(s) average_time(s) FLOPS GFLOP/average_time(s)
batched - NN 1 1 - - parallel 2x2x81920 2x2x81920 2x2x81920 10 20 0.000296876 1.48438e-05 1.31072e+06 88.3008
batched - NN 1 1 - - parallel 4x4x81920 4x4x81920 4x4x81920 10 20 0.00115557 5.77784e-05 1.04858e+07 181.482
batched - NN 1 1 - - parallel 6x6x81920 6x6x81920 6x6x81920 10 20 0.0033013 0.000165065 3.53894e+07 214.397
batched - NN 1 1 - - parallel 8x8x81920 8x8x81920 8x8x81920 10 20 0.00484021 0.00024201 8.38861e+07 346.622
batched - NN 1 1 - - parallel 10x10x81920 10x10x81920 10x10x81920 10 20 0.0106653 0.000533264 1.6384e+08 307.24
batched - NN 1 1 - - parallel 12x12x81920 12x12x81920 12x12x81920 10 20 0.0122351 0.000611757 2.83116e+08 462.791
batched - NN 1 1 - - parallel 14x14x81920 14x14x81920 14x14x81920 10 20 0.0312507 0.00156253 4.49577e+08 287.723
batched - NN 1 1 - - parallel 16x16x81920 16x16x81920 16x16x81920 10 20 0.0732057 0.00366029 6.71089e+08 183.343
batched - NN 1 1 - - parallel 18x18x81920 18x18x81920 18x18x81920 10 20 0.065681 0.00328405 9.55515e+08 290.956
batched - NN 1 1 - - parallel 20x20x81920 20x20x81920 20x20x81920 10 20 0.0766822 0.00383411 1.31072e+09 341.858
batched - NN 1 1 - - parallel 22x22x81920 22x22x81920 22x22x81920 10 20 0.122848 0.0061424 1.74457e+09 284.021
batched - NN 1 1 - - parallel 24x24x81920 24x24x81920 24x24x81920 10 20 0.0671947 0.00335974 2.26492e+09 674.138
batched - NN 1 1 - - parallel 26x26x81920 26x26x81920 26x26x81920 10 20 0.0793655 0.00396827 2.87965e+09 725.668
batched - NN 1 1 - - parallel 28x28x81920 28x28x81920 28x28x81920 10 20 0.0843876 0.00421938 3.59662e+09 852.403
batched - NN 1 1 - - parallel 30x30x81920 30x30x81920 30x30x81920 10 20 0.0956921 0.0047846 4.42368e+09 924.566
batched - NN 1 1 - - parallel 32x32x81920 32x32x81920 32x32x81920 10 20 0.091027 0.00455135 5.36871e+09 1179.59
batched - NN 1 1 - - parallel 34x34x81920 34x34x81920 34x34x81920 10 20 0.466776 0.0233388 6.43957e+09 275.917
batched - NN 1 1 - - parallel 36x36x81920 36x36x81920 36x36x81920 10 20 0.512853 0.0256427 7.64412e+09 298.101
batched - NN 1 1 - - parallel 38x38x81920 38x38x81920 38x38x81920 10 20 0.683339 0.034167 8.99023e+09 263.126
batched - NN 1 1 - - parallel 40x40x81920 40x40x81920 40x40x81920 10 20 0.931151 0.0465576 1.04858e+10 225.221
batched - NN 1 1 - - parallel 42x42x81920 42x42x81920 42x42x81920 10 20 0.873163 0.0436581 1.21386e+10 278.037
batched - NN 1 1 - - parallel 44x44x81920 44x44x81920 44x44x81920 10 20 0.973009 0.0486504 1.39565e+10 286.874
batched - NN 1 1 - - parallel 46x46x81920 46x46x81920 46x46x81920 10 20 0.405205 0.0202603 1.59475e+10 787.133
batched - NN 1 1 - - parallel 48x48x81920 48x48x81920 48x48x81920 10 20 0.42132 0.021066 1.81194e+10 860.124
batched - NN 1 1 - - parallel 50x50x81920 50x50x81920 50x50x81920 10 20 0.466039 0.023302 2.048e+10 878.896
batched - NN 1 1 - - parallel 52x52x81920 52x52x81920 52x52x81920 10 20 0.477679 0.0238839 2.30372e+10 964.54
batched - NN 1 1 - - parallel 54x54x81920 54x54x81920 54x54x81920 10 20 0.491249 0.0245625 2.57989e+10 1050.34
batched - NN 1 1 - - parallel 56x56x81920 56x56x81920 56x56x81920 10 20 0.497255 0.0248627 2.87729e+10 1157.27
batched - NN 1 1 - - parallel 58x58x81920 58x58x81920 58x58x81920 10 20 0.537861 0.026893 3.19672e+10 1188.68
batched - NN 1 1 - - parallel 60x60x81920 60x60x81920 60x60x81920 10 20 0.550495 0.0275248 3.53894e+10 1285.73
batched - NN 1 1 - - parallel 62x62x81920 62x62x81920 62x62x81920 10 20 0.564138 0.0282069 3.90477e+10 1384.33
batched - NN 1 1 - - parallel 64x64x81920 64x64x81920 64x64x81920 10 20 0.566884 0.0283442 4.29497e+10 1515.29

LayoutRight, BatchedLayout::Left

$ ./KokkosBlas3_perf_test.LR --test=batched --routines=gemm --loop_type=parallel --batch_size_last_dim=0 --matrix_size_start=2x2,2x2,2x2 --matrix_size_stop=64x64,64x64,64x64 --matrix_size_step=2 --batch_size=$((80*1024)) --warm_up_loop=10 --iter=20 --verify=0
Testing gemm...
SCALAR:d, LAYOUT:N6Kokkos11LayoutRightE, DEVICE:N6Kokkos4CudaE, SPACE:N6Kokkos9CudaSpaceE
algorithm vector_type transAtransB alpha beta team_size vector_len loop_type A_dims B_dims C_dims warm_up_n iter total_time(s) average_time(s) FLOPS GFLOP/average_time(s)
batched - NN 1 1 - - parallel 81920x2x2 81920x2x2 81920x2x2 10 20 0.000299394 1.49697e-05 1.31072e+06 87.5582
batched - NN 1 1 - - parallel 81920x4x4 81920x4x4 81920x4x4 10 20 0.00116804 5.84019e-05 1.04858e+07 179.545
batched - NN 1 1 - - parallel 81920x6x6 81920x6x6 81920x6x6 10 20 0.00287086 0.000143543 3.53894e+07 246.543
batched - NN 1 1 - - parallel 81920x8x8 81920x8x8 81920x8x8 10 20 0.00476374 0.000238187 8.38861e+07 352.186
batched - NN 1 1 - - parallel 81920x10x10 81920x10x10 81920x10x10 10 20 0.00834711 0.000417355 1.6384e+08 392.567
batched - NN 1 1 - - parallel 81920x12x12 81920x12x12 81920x12x12 10 20 0.0113745 0.000568725 2.83116e+08 497.807
batched - NN 1 1 - - parallel 81920x14x14 81920x14x14 81920x14x14 10 20 0.0172143 0.000860717 4.49577e+08 522.328
batched - NN 1 1 - - parallel 81920x16x16 81920x16x16 81920x16x16 10 20 0.0211365 0.00105682 6.71089e+08 635.005
batched - NN 1 1 - - parallel 81920x18x18 81920x18x18 81920x18x18 10 20 0.0308505 0.00154252 9.55515e+08 619.449
batched - NN 1 1 - - parallel 81920x20x20 81920x20x20 81920x20x20 10 20 0.0367313 0.00183657 1.31072e+09 713.68
batched - NN 1 1 - - parallel 81920x22x22 81920x22x22 81920x22x22 10 20 0.0506981 0.0025349 1.74457e+09 688.219
batched - NN 1 1 - - parallel 81920x24x24 81920x24x24 81920x24x24 10 20 0.0555592 0.00277796 2.26492e+09 815.319
batched - NN 1 1 - - parallel 81920x26x26 81920x26x26 81920x26x26 10 20 0.0705398 0.00352699 2.87965e+09 816.462
batched - NN 1 1 - - parallel 81920x28x28 81920x28x28 81920x28x28 10 20 0.0746802 0.00373401 3.59662e+09 963.205
batched - NN 1 1 - - parallel 81920x30x30 81920x30x30 81920x30x30 10 20 0.0806893 0.00403446 4.42368e+09 1096.47
batched - NN 1 1 - - parallel 81920x32x32 81920x32x32 81920x32x32 10 20 0.0748412 0.00374206 5.36871e+09 1434.69
batched - NN 1 1 - - parallel 81920x34x34 81920x34x34 81920x34x34 10 20 0.153192 0.00765958 6.43957e+09 840.721
batched - NN 1 1 - - parallel 81920x36x36 81920x36x36 81920x36x36 10 20 0.167731 0.00838657 7.64412e+09 911.471
batched - NN 1 1 - - parallel 81920x38x38 81920x38x38 81920x38x38 10 20 0.212169 0.0106084 8.99023e+09 847.461
batched - NN 1 1 - - parallel 81920x40x40 81920x40x40 81920x40x40 10 20 0.220466 0.0110233 1.04858e+10 951.234
batched - NN 1 1 - - parallel 81920x42x42 81920x42x42 81920x42x42 10 20 0.278568 0.0139284 1.21386e+10 871.499
batched - NN 1 1 - - parallel 81920x44x44 81920x44x44 81920x44x44 10 20 0.305086 0.0152543 1.39565e+10 914.924
batched - NN 1 1 - - parallel 81920x46x46 81920x46x46 81920x46x46 10 20 0.349248 0.0174624 1.59475e+10 913.251
batched - NN 1 1 - - parallel 81920x48x48 81920x48x48 81920x48x48 10 20 0.363568 0.0181784 1.81194e+10 996.753
batched - NN 1 1 - - parallel 81920x50x50 81920x50x50 81920x50x50 10 20 0.402868 0.0201434 2.048e+10 1016.71
batched - NN 1 1 - - parallel 81920x52x52 81920x52x52 81920x52x52 10 20 0.414658 0.0207329 2.30372e+10 1111.14
batched - NN 1 1 - - parallel 81920x54x54 81920x54x54 81920x54x54 10 20 0.424799 0.0212399 2.57989e+10 1214.64
batched - NN 1 1 - - parallel 81920x56x56 81920x56x56 81920x56x56 10 20 0.438306 0.0219153 2.87729e+10 1312.92
batched - NN 1 1 - - parallel 81920x58x58 81920x58x58 81920x58x58 10 20 0.47642 0.023821 3.19672e+10 1341.97
batched - NN 1 1 - - parallel 81920x60x60 81920x60x60 81920x60x60 10 20 0.482666 0.0241333 3.53894e+10 1466.42
batched - NN 1 1 - - parallel 81920x62x62 81920x62x62 81920x62x62 10 20 0.498624 0.0249312 3.90477e+10 1566.22
batched - NN 1 1 - - parallel 81920x64x64 81920x64x64 81920x64x64 10 20 0.461842 0.0230921 4.29497e+10 1859.93

Fixes #1045.
Related to #933.

@e10harvey e10harvey added this to In progress in Developer: E10HARVEY via automation Sep 3, 2021
@e10harvey e10harvey self-assigned this Sep 3, 2021
@e10harvey e10harvey changed the title Issue1045 src/batched: Add BatchedDblBufGemm Sep 3, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_GCC720_GCC740 to start: Total Wait = 3603

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_CUDA9 to start: Total Wait = 3603

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 45
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 424
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 71
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 415
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 46
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 401
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 45
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 43
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 41
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (e10harvey/kokkos-kernels)
  • Branch: issue1045
  • SHA: 44b0fc9
  • Mode: TEST_REPO

Pull Request Author: e10harvey

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED

Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run.

Pull Request Auto Testing has FAILED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 45
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 424
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 71
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 415
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 46
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 401
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 45
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 43
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 41
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 44b0fc9
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light # 45 (click to expand)

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/serial/Test_Serial_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=Power8,Pascal60 --compiler=/home/projects/ppc64le/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls= --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/KokkosKernels_PullRequest_GCC720_Light.45/TestAll_2021-09-03_23.56.27/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=Power8,Pascal60 --compiler=/home/projects/ppc64le/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls= --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/KokkosKernels_PullRequest_GCC720_Light.45/TestAll_2021-09-03_23.56.27/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.2.0-Serial-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Serial --arch=Power8,Pascal60 --compiler=/home/projects/ppc64le/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls= --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_GCC720_Light/KokkosKernels_PullRequest_GCC720_Light.45/TestAll_2021-09-03_23.56.27/gcc/7.2.0/Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720 # 424 (click to expand)

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls= --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.424/TestAll_2021-09-03_23.20.10/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.2.0-Pthread_Serial-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls= --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.424/TestAll_2021-09-03_23.20.10/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
salloc: Relinquishing job allocation 1014431
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light_LayoutRight # 71 (click to expand)

                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls= --with-options= --with-cuda-options= --with-spaces=hostspace --no-examples --no-default-eti

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.71/TestAll_2021-09-03_23.20.17/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.2.0-Pthread_Serial-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls= --with-options= --with-cuda-options= --with-spaces=hostspace --no-examples --no-default-eti

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.71/TestAll_2021-09-03_23.20.17/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
salloc: Relinquishing job allocation 1014432
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720 # 415 (click to expand)

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
[ 92%] Linking CXX executable KokkosKernels_sparse_serial
[ 92%] Built target KokkosKernels_sparse_serial
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/serial/Test_Serial_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.415/TestAll_2021-09-03_23.20.27/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
salloc: Relinquishing job allocation 1014433
salloc: Job allocation 1014433 has been revoked.
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10 # 46 (click to expand)

[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE_MEMSPACE_HOSTSPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDASPACE_MEMSPACE_CUDASPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDASPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDASPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE_MEMSPACE_HOSTSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/batched/KokkosBatched_Util.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosBlas_Cuda_tpl.cpp.o
[ 81%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosKernels_tpl_handles.cpp.o
[ 81%] Linking CXX static library libkokkoskernels.a
[ 81%] Built target kokkoskernels
Scanning dependencies of target graph_color
Scanning dependencies of target sparse_kk_spmv
Scanning dependencies of target sparse_spmv_struct
Scanning dependencies of target KokkosBatched_Test_BlockJacobi
Scanning dependencies of target KokkosBatched_Test_BlockTridiag
Scanning dependencies of target graph_mis_d2
Scanning dependencies of target sparse_spadd
Scanning dependencies of target graph_color_d2
Scanning dependencies of target sparse_sptrsv
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color.dir/KokkosGraph_color.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_kk_spmv.dir/KokkosSparse_kk_spmv.cpp.o
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockJacobi.dir/KokkosBatched_Test_BlockJacobi_Tutorial.cpp.o
Scanning dependencies of target sparse_spgemm
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_mis_d2.dir/KokkosGraph_mis_d2.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spadd.dir/KokkosSparse_spadd.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color_d2.dir/KokkosGraph_color_d2.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spmv_struct.dir/KokkosSparse_spmv_struct.cpp.o
Scanning dependencies of target sparse_sptrsv_supernode
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv.dir/KokkosSparse_sptrsv.cpp.o
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spgemm.dir/KokkosSparse_spgemm.cpp.o
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv_supernode.dir/KokkosSparse_sptrsv_supernode.cpp.o
Scanning dependencies of target sparse_pcg
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_pcg.dir/KokkosSparse_pcg.cpp.o
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In lambda function:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:15: error: declaration of k shadows a previous local [-Werror=shadow]
                     for (unsigned k = 0; k < __tile_k; ++k) {
               ^
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:319:15: note: shadowed declaration is here
       for (unsigned k = 1; k < __n_tile_k_tiles + partial_tile; ++k) {
               ^
[ 82%] Linking CXX executable KokkosBatched_Test_BlockJacobi
cc1plus: all warnings being treated as errors
make[2]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o] Error 1
make[1]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 82%] Built target KokkosBatched_Test_BlockJacobi
[ 82%] Linking CXX executable sparse_spgemm
[ 82%] Linking CXX executable sparse_sptrsv
[ 82%] Built target sparse_spgemm
[ 82%] Built target sparse_sptrsv
[ 82%] Linking CXX executable sparse_pcg
[ 83%] Linking CXX executable sparse_spmv_struct
[ 83%] Built target sparse_pcg
[ 83%] Built target sparse_spmv_struct
[ 83%] Linking CXX executable sparse_spadd
[ 83%] Built target sparse_spadd
[ 83%] Linking CXX executable graph_mis_d2
[ 83%] Built target graph_mis_d2
[ 84%] Linking CXX executable sparse_sptrsv_supernode
[ 84%] Linking CXX executable graph_color_d2
[ 84%] Built target sparse_sptrsv_supernode
[ 85%] Linking CXX executable graph_color
[ 85%] Built target graph_color_d2
[ 85%] Built target graph_color
[ 86%] Linking CXX executable sparse_kk_spmv
[ 86%] Built target sparse_kk_spmv
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
cuda-10.1.243-Cuda_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243 --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10/KokkosKernels_PullRequest_Tpls_CUDA10.46/TestAll_2021-09-04_00.14.18/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL18 # 401 (click to expand)

            instantiation of "void Kokkos::parallel_for(const std::__cxx11::string &, const ExecPolicy &, const FunctorType &) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::__Functor]" at line 187
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::__run() [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=view_type_3d, BViewType=view_type_3d,
                      CViewType=view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::No, TILE_M=32, TILE_N=32, TILE_K=8]" at line 103
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=view_type_3d, BViewType=view_type_3d,
                      CViewType=view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::No, TILE_M=32, TILE_N=32, TILE_K=8]" at line 469 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/src/batched/KokkosBatched_Gemm_Decl.hpp"
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle,
                      ScalarType=default_scalar={double}, AViewType=view_type_3d, BViewType=view_type_3d, CViewType=view_type_3d]" at line 486 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_batchedGemm_parallel(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 541 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_batchedGemm_parallel_wrapper(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 2206 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"

[ 94%] Linking CXX executable KokkosKernels_wiki_rcm
[ 94%] Built target KokkosKernels_wiki_rcm
Scanning dependencies of target KokkosKernels_gmres_test_prec
[ 94%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_prec.dir/test_prec.cpp.o
[ 94%] Linking CXX executable KokkosKernels_wiki_coarsening
[ 94%] Built target KokkosKernels_wiki_coarsening
Scanning dependencies of target gmres_test_cmplx_A
[ 95%] Building CXX object example/gmres/CMakeFiles/gmres_test_cmplx_A.dir/test_cmplx_A.cpp.o
[ 95%] Linking CXX executable KokkosKernels_wiki_coloring
[ 95%] Built target KokkosKernels_wiki_coloring
[ 96%] Linking CXX executable KokkosKernels_gmres_test_real_A
[ 96%] Built target KokkosKernels_gmres_test_real_A
[ 96%] Linking CXX executable gmres_ex_real_A
[ 96%] Built target gmres_ex_real_A
[ 97%] Linking CXX executable KokkosKernels_gmres_test_prec
[ 97%] Built target KokkosKernels_gmres_test_prec
[ 97%] Linking CXX executable gmres_test_cmplx_A
[ 97%] Built target gmres_test_cmplx_A
[ 98%] Linking CXX executable sparse_spmv_struct_tuning
[ 98%] Built target sparse_spmv_struct_tuning
[ 99%] Linking CXX executable KokkosKernels_common_threads
[ 99%] Built target KokkosKernels_common_threads
[100%] Linking CXX executable KokkosKernels_blas_threads
[100%] Built target KokkosKernels_blas_threads
compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp (code 2)
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 2
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[100%] Linking CXX executable KokkosKernels_graph_threads
[100%] Built target KokkosKernels_graph_threads
compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/unit_test/threads/Test_Threads_Batched.cpp (code 2)
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_threads.dir/threads/Test_Threads_Batched.cpp.o] Error 2
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_threads.dir/all] Error 2
[100%] Linking CXX executable KokkosKernels_sparse_threads
[100%] Built target KokkosKernels_sparse_threads
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
intel-18.1.163-OpenMP-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.401/TestAll_2021-09-03_23.56.38/intel/18.1.163/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
intel-18.1.163-Pthread-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.401/TestAll_2021-09-03_23.56.38/intel/18.1.163/Pthread-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
salloc: Relinquishing job allocation 1014434
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight # 45 (click to expand)

[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosBlas_Cuda_tpl.cpp.o
[ 81%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosKernels_tpl_handles.cpp.o
[ 81%] Linking CXX static library libkokkoskernels.a
[ 81%] Built target kokkoskernels
Scanning dependencies of target sparse_sptrsv
Scanning dependencies of target sparse_kk_spmv
Scanning dependencies of target graph_color
Scanning dependencies of target graph_mis_d2
Scanning dependencies of target sparse_spmv_struct
Scanning dependencies of target KokkosBatched_Test_BlockJacobi
Scanning dependencies of target sparse_spadd
Scanning dependencies of target KokkosBatched_Test_BlockTridiag
Scanning dependencies of target graph_color_d2
Scanning dependencies of target sparse_spgemm
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color.dir/KokkosGraph_color.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_mis_d2.dir/KokkosGraph_mis_d2.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spadd.dir/KokkosSparse_spadd.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv.dir/KokkosSparse_sptrsv.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_kk_spmv.dir/KokkosSparse_kk_spmv.cpp.o
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockJacobi.dir/KokkosBatched_Test_BlockJacobi_Tutorial.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spmv_struct.dir/KokkosSparse_spmv_struct.cpp.o
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color_d2.dir/KokkosGraph_color_d2.cpp.o
Scanning dependencies of target sparse_sptrsv_supernode
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spgemm.dir/KokkosSparse_spgemm.cpp.o
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv_supernode.dir/KokkosSparse_sptrsv_supernode.cpp.o
Scanning dependencies of target sparse_pcg
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_pcg.dir/KokkosSparse_pcg.cpp.o
[ 83%] Linking CXX executable sparse_sptrsv_supernode
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In lambda function:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:15: error: declaration of k shadows a previous local [-Werror=shadow]
                     for (unsigned k = 0; k < __tile_k; ++k) {
               ^
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:319:15: note: shadowed declaration is here
       for (unsigned k = 1; k < __n_tile_k_tiles + partial_tile; ++k) {
               ^
[ 83%] Built target sparse_sptrsv_supernode
Scanning dependencies of target sparse_spmv
[ 83%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spmv.dir/KokkosSparse_spmv.cpp.o
[ 83%] Linking CXX executable KokkosBatched_Test_BlockJacobi
[ 83%] Built target KokkosBatched_Test_BlockJacobi
Scanning dependencies of target sparse_spmv_struct_tuning
[ 83%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spmv_struct_tuning.dir/KokkosSparse_spmv_struct_tuning.cpp.o
[ 83%] Linking CXX executable sparse_sptrsv
cc1plus: all warnings being treated as errors
make[2]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o] Error 1
make[1]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 83%] Built target sparse_sptrsv
[ 83%] Linking CXX executable sparse_pcg
[ 83%] Linking CXX executable sparse_spgemm
[ 83%] Built target sparse_pcg
[ 83%] Built target sparse_spgemm
[ 83%] Linking CXX executable sparse_spadd
[ 83%] Built target sparse_spadd
[ 83%] Linking CXX executable graph_mis_d2
[ 83%] Built target graph_mis_d2
[ 83%] Linking CXX executable sparse_spmv
[ 84%] Linking CXX executable graph_color
[ 84%] Linking CXX executable graph_color_d2
[ 84%] Built target sparse_spmv
[ 84%] Built target graph_color
[ 84%] Built target graph_color_d2
[ 84%] Linking CXX executable sparse_spmv_struct_tuning
[ 84%] Built target sparse_spmv_struct_tuning
[ 85%] Linking CXX executable sparse_spmv_struct
[ 85%] Built target sparse_spmv_struct
[ 86%] Linking CXX executable sparse_kk_spmv
[ 86%] Built target sparse_kk_spmv
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
cuda-10.1.243-Cuda_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243 --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda --with-spaces=hostspace,cudaspace,cudauvmspace --no-examples --no-default-eti

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight.45/TestAll_2021-09-04_00.18.44/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA9 # 43 (click to expand)

[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_OPENMP_MEMSPACE_HOSTSPACE_MEMSPACE_HOSTSPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDASPACE_MEMSPACE_CUDASPACE.cpp.o
[ 79%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDASPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDASPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_CUDA_MEMSPACE_CUDAUVMSPACE_MEMSPACE_CUDAUVMSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/generated_specializations_cpp/gauss_seidel_apply/Sparse_gauss_seidel_apply_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_SIZE_T_LAYOUTLEFT_EXECSPACE_OPENMP_MEMSPACE_HOSTSPACE_MEMSPACE_HOSTSPACE.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/batched/KokkosBatched_Util.cpp.o
[ 80%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosBlas_Cuda_tpl.cpp.o
[ 81%] Building CXX object src/CMakeFiles/kokkoskernels.dir/impl/tpls/KokkosKernels_tpl_handles.cpp.o
[ 81%] Linking CXX static library libkokkoskernels.a
[ 81%] Built target kokkoskernels
Scanning dependencies of target graph_mis_d2
Scanning dependencies of target sparse_spmv_struct
Scanning dependencies of target sparse_spadd
Scanning dependencies of target graph_color
Scanning dependencies of target sparse_kk_spmv
Scanning dependencies of target KokkosBatched_Test_BlockJacobi
Scanning dependencies of target sparse_sptrsv_supernode
Scanning dependencies of target KokkosBatched_Test_BlockTridiag
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_mis_d2.dir/KokkosGraph_mis_d2.cpp.o
Scanning dependencies of target sparse_sptrsv
Scanning dependencies of target graph_color_d2
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spadd.dir/KokkosSparse_spadd.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color.dir/KokkosGraph_color.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spmv_struct.dir/KokkosSparse_spmv_struct.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_kk_spmv.dir/KokkosSparse_kk_spmv.cpp.o
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockJacobi.dir/KokkosBatched_Test_BlockJacobi_Tutorial.cpp.o
[ 81%] Building CXX object perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv_supernode.dir/KokkosSparse_sptrsv_supernode.cpp.o
Scanning dependencies of target sparse_spgemm
[ 81%] Building CXX object perf_test/sparse/CMakeFiles/sparse_sptrsv.dir/KokkosSparse_sptrsv.cpp.o
[ 81%] Building CXX object perf_test/graph/CMakeFiles/graph_color_d2.dir/KokkosGraph_color_d2.cpp.o
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_spgemm.dir/KokkosSparse_spgemm.cpp.o
Scanning dependencies of target sparse_pcg
[ 82%] Building CXX object perf_test/sparse/CMakeFiles/sparse_pcg.dir/KokkosSparse_pcg.cpp.o
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In lambda function:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:15: error: declaration of k shadows a previous local [-Werror=shadow]
                     for (unsigned k = 0; k < __tile_k; ++k) {
               ^
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:319:15: note: shadowed declaration is here
       for (unsigned k = 1; k < __n_tile_k_tiles + partial_tile; ++k) {
               ^
[ 82%] Linking CXX executable KokkosBatched_Test_BlockJacobi
cc1plus: all warnings being treated as errors
make[2]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/KokkosBatched_Test_BlockTridiagDirect.cpp.o] Error 1
make[1]: *** [perf_test/batched/CMakeFiles/KokkosBatched_Test_BlockTridiag.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 82%] Built target KokkosBatched_Test_BlockJacobi
[ 82%] Linking CXX executable sparse_sptrsv
[ 82%] Linking CXX executable sparse_spgemm
[ 82%] Built target sparse_sptrsv
[ 82%] Built target sparse_spgemm
[ 83%] Linking CXX executable sparse_spmv_struct
[ 83%] Built target sparse_spmv_struct
[ 83%] Linking CXX executable sparse_pcg
[ 83%] Linking CXX executable sparse_spadd
[ 83%] Built target sparse_spadd
[ 83%] Built target sparse_pcg
[ 83%] Linking CXX executable graph_mis_d2
[ 83%] Built target graph_mis_d2
[ 84%] Linking CXX executable sparse_sptrsv_supernode
[ 84%] Built target sparse_sptrsv_supernode
[ 85%] Linking CXX executable graph_color
[ 85%] Linking CXX executable graph_color_d2
[ 85%] Built target graph_color
[ 85%] Built target graph_color_d2
[ 86%] Linking CXX executable sparse_kk_spmv
[ 86%] Built target sparse_kk_spmv
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
cuda-9.2.88-Cuda_OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 cuda/9.2.88 gcc/7.2.0 netlib/3.8.0/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,OpenMP --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/9.2.88 --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=force_uvm,enable_lambda --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9/KokkosKernels_PullRequest_Tpls_CUDA9.43/TestAll_2021-09-04_01.32.32/cuda/9.2.88/Cuda_OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
Build step 'Execute shell' marked build as failure
Finished: FAILURE

Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720_GCC740 # 41 (click to expand)

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 0; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 65536; int TILE_N = 1; int TILE_K = 65536]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 2; int STRIDE_M = 65536; int STRIDE_N = 65536; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 65536; int TILE_N = 131072; int TILE_K = 65536]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[1] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp: In member function void KokkosBatched::Impl::BatchedDblBufGemm::__Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View; BViewType = Kokkos::View; CViewType = Kokkos::View; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:407:23: error: prefetch_reg_b[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svB_scr(vlane_id, thread_offset + i * STRIDE_N) =
                       ^~~~~~~
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Gemm_DblBuf_Impl.hpp:424:23: error: prefetch_reg_a[0] may be used uninitialized in this function [-Werror=maybe-uninitialized]
                       svA_scr(vlane_id, thread_offset + i * STRIDE_M) =
                       ^~~~~~~
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=Power9,Volta70 --compiler=/home/projects/ppc64le/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_GCC720_GCC740.41/TestAll_2021-09-04_02.04.46/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.2.0-Serial-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Serial --arch=Power9,Volta70 --compiler=/home/projects/ppc64le/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_GCC720_GCC740.41/TestAll_2021-09-04_02.04.46/gcc/7.2.0/Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
gcc-7.4.0-OpenMP-release (build failed)
#######################################################

Reproducer instructions:

Load modules:

    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.4.0 openblas/0.2.20/gcc/7.2.0 gcc/7.4.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=Power9,Volta70 --compiler=/home/projects/ppc64le/gcc/7.4.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags="" --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options= --no-examples

To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:

  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_GCC720_GCC740.41/TestAll_2021-09-04_02.04.46/gcc/7.4.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V

#######################################################
Build step 'Execute shell' marked build as failure
Finished: FAILURE

@e10harvey e10harvey added AT: RETEST Have this PR retested. and removed AT: RETEST Have this PR retested. labels Sep 7, 2021
@e10harvey e10harvey moved this from In progress to Review in progress in Developer: E10HARVEY Sep 7, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_GCC720_GCC740 to start: Total Wait = 3603

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_GCC720_GCC740 to start: Total Wait = 3603

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_GCC720_GCC740 to start: Total Wait = 3603

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 51
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 430
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 77
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 421
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 52
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 407
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 51
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 49
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 43
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (e10harvey/kokkos-kernels)
  • Branch: issue1045
  • SHA: 86ad148
  • Mode: TEST_REPO

Pull Request Author: e10harvey

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: all Jobs PASSED

Pull Request Auto Testing has PASSED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 51
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 430
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 77
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 421
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 52
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 407
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 51
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 49
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 43
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 86ad148
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 9ecbb0c
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Merge Inspection' - - This Pull Request Requires Inspection... The code must be inspected by a member of the Team before Testing/Merging
NO REVIEWS HAVE BEEN PERFORMED ON THIS PULL REQUEST!

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@e10harvey
Copy link
Contributor Author

@srajama1, @lucbv, @vqd8a: This is ready for a first round of reviews.

@vqd8a
Copy link
Contributor

vqd8a commented Sep 8, 2021

@e10harvey Thanks, Evan. I will review it.

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

3 similar comments
@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Merge Inspection' - - This Pull Request Requires Inspection... The code must be inspected by a member of the Team before Testing/Merging
THE LAST COMMIT TO THIS PULL REQUEST HAS BEEN REVIEWED, BUT NOT ACCEPTED OR REQUIRES CHANGES

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@vqd8a
Copy link
Contributor

vqd8a commented Sep 21, 2021

@e10harvey Thanks for the changes. Please remember to fix these in the tables:

I will change these to a - since the vector_type doesn't apply and the team_size and vector_len must be calculated in the DblBuf algo by using the requested tile size.

Otherwise, LGTM.

Let's wait for @srajama1 and @lucbv 's feedbacks.

Developer: E10HARVEY automation moved this from Review in progress to Reviewer approved Sep 21, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 67
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 445
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 92
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 436
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 67
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 422
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 66
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 64
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 58
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (e10harvey/kokkos-kernels)
  • Branch: issue1045
  • SHA: 3d2992f
  • Mode: TEST_REPO

Pull Request Author: e10harvey

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: all Jobs PASSED

Pull Request Auto Testing has PASSED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light

  • Build Num: 67
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 445
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 92
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 436
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10

  • Build Num: 67
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 422
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_LayoutRight

  • Build Num: 66
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9

  • Build Num: 64
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720_GCC740

  • Build Num: 58
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH issue1045
KOKKOSKERNELS_SOURCE_REPO https://github.com/e10harvey/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 3d2992f
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA c8c0f21
PR_LABELS feature request
PULLREQUESTNUM 1095
TEST_REPO_ALIAS KOKKOSKERNELS

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Merge Inspection' - SUCCESS: The last commit to this Pull Request has been INSPECTED AND APPROVED by [ vqd8a ]!

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

2 similar comments
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

@e10harvey
Copy link
Contributor Author

@srajama1, @lucbv: Ready to merge?

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

2 similar comments
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest....

1 similar comment
@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest....

Copy link
Contributor

@lucbv lucbv left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't have real comments on the implementation, just some small clean-up

src/batched/KokkosBatched_Util.hpp Show resolved Hide resolved
@@ -117,6 +150,10 @@ void impl_test_batched_gemm_with_handle(BatchedGemmHandle* batchedGemmHandle,
}
}
}
// std::cout << "algo_type:" << algo_type << std::endl;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should be removed

? (c_m >= 16)
: (c_m >= 24 && c_m <= 32) || (c_m >= 45 && c_m <= 64))) {
handle->teamSz = handle->vecLen = 8;
// constexpr int tile_m = 32, tile_n = 32, tile_k = 8;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can probably be removed

ret = BatchedSerialGemm<ArgTransA, ArgTransB, bsgModeType, ArgBatchSzDim,
bsgResultsPerThread, ScalarType, AViewType,
BViewType, CViewType>(alpha, A, B, beta, C)
// if (on_gpu && c_m >= 20 &&
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does this need to be kept?

Copy link
Contributor Author

@e10harvey e10harvey Sep 29, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No, it is just a placeholder for invoking another algo that moves entire matrices into shared memory before GEMM.

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest....

1 similar comment
@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest....

@e10harvey e10harvey merged commit 8ebb965 into kokkos:develop Sep 30, 2021
Developer: E10HARVEY automation moved this from Reviewer approved to Done Sep 30, 2021
e10harvey added a commit to e10harvey/kokkos-kernels that referenced this pull request Oct 1, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Development

Successfully merging this pull request may close these issues.

None yet

4 participants