cjolivier01 closed pull request #10232: [MXNET-136] Enabling USE_DIST_KVSTORE flag for CI URL: https://github.com/apache/incubator-mxnet/pull/10232
This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a foreign pull request (from a fork), the diff is supplied below (as it won't show otherwise due to GitHub magic): diff --git a/3rdparty/ps-lite b/3rdparty/ps-lite index aee325276bc..a6dda54604a 160000 --- a/3rdparty/ps-lite +++ b/3rdparty/ps-lite @@ -1 +1 @@ -Subproject commit aee325276bccb092f516df0bce30d3a8333f4038 +Subproject commit a6dda54604a07d1fb21b016ed1e3f4246b08222a diff --git a/Jenkinsfile b/Jenkinsfile index 45b86fbdafe..3892906b45a 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -22,6 +22,8 @@ // mxnet libraries mx_lib = 'lib/libmxnet.so, lib/libmxnet.a, 3rdparty/dmlc-core/libdmlc.a, 3rdparty/nnvm/lib/libnnvm.a' +// for scala build, need to pass extra libs when run with dist_kvstore +mx_dist_lib = 'lib/libmxnet.so, lib/libmxnet.a, 3rdparty/dmlc-core/libdmlc.a, 3rdparty/nnvm/lib/libnnvm.a, 3rdparty/ps-lite/build/libps.a, deps/lib/libprotobuf-lite.a, deps/lib/libzmq.a' // mxnet cmake libraries, in cmake builds we do not produce a libnvvm static library by default. mx_cmake_lib = 'build/libmxnet.so, build/libmxnet.a, build/3rdparty/dmlc-core/libdmlc.a, build/tests/mxnet_unit_tests, build/3rdparty/openmp/runtime/src/libomp.so' mx_cmake_mkldnn_lib = 'build/libmxnet.so, build/libmxnet.a, build/3rdparty/dmlc-core/libdmlc.a, build/tests/mxnet_unit_tests, build/3rdparty/openmp/runtime/src/libomp.so, build/3rdparty/mkldnn/src/libmkldnn.so, build/3rdparty/mkldnn/src/libmkldnn.so.0' @@ -164,7 +166,7 @@ try { ws('workspace/build-cpu-openblas') { init_git() sh "ci/build.py --platform ubuntu_cpu /work/runtime_functions.sh build_ubuntu_cpu_openblas" - pack_lib('cpu') + pack_lib('cpu', mx_dist_lib) } } }, @@ -224,8 +226,8 @@ try { node('mxnetlinux-cpu') { ws('workspace/build-gpu') { init_git() - sh "ci/build.py --platform ubuntu_build_cuda /work/runtime_functions.sh build_ubuntu_gpu_cuda91_cudnn7" - pack_lib('gpu') + sh "ci/build.py --platform ubuntu_build_cuda /work/runtime_functions.sh build_ubuntu_gpu_cuda91_cudnn7" + pack_lib('gpu', mx_dist_lib) stash includes: 'build/cpp-package/example/test_score', name: 'cpp_test_score' stash includes: 'build/cpp-package/example/test_optimizer', name: 'cpp_test_optimizer' } @@ -475,7 +477,7 @@ try { node('mxnetlinux-cpu') { ws('workspace/ut-scala-cpu') { init_git() - unpack_lib('cpu') + unpack_lib('cpu', mx_dist_lib) timeout(time: max_time, unit: 'MINUTES') { sh "ci/build.py --platform ubuntu_cpu /work/runtime_functions.sh unittest_ubuntu_cpu_scala" } @@ -486,7 +488,7 @@ try { node('mxnetlinux-gpu') { ws('workspace/ut-scala-gpu') { init_git() - unpack_lib('gpu') + unpack_lib('gpu', mx_dist_lib) timeout(time: max_time, unit: 'MINUTES') { sh "ci/build.py --nvidiadocker --platform ubuntu_gpu /work/runtime_functions.sh unittest_ubuntu_gpu_scala" } diff --git a/ci/docker/install/ubuntu_core.sh b/ci/docker/install/ubuntu_core.sh index dc9b091f205..f588d06ab57 100755 --- a/ci/docker/install/ubuntu_core.sh +++ b/ci/docker/install/ubuntu_core.sh @@ -33,6 +33,7 @@ apt-get install -y \ wget \ unzip \ sudo \ + libzmq3-dev \ software-properties-common \ ninja-build diff --git a/ci/docker/runtime_functions.sh b/ci/docker/runtime_functions.sh index 3d58f344a33..a97f6b92af0 100755 --- a/ci/docker/runtime_functions.sh +++ b/ci/docker/runtime_functions.sh @@ -131,6 +131,7 @@ build_amzn_linux_cpu() { -DCMAKE_BUILD_TYPE=RelWithDebInfo\ -DUSE_MKL_IF_AVAILABLE=OFF\ -DUSE_LAPACK=OFF\ + -DUSE_DIST_KVSTORE=ON\ -G Ninja /work/mxnet ninja export MXNET_LIBRARY_PATH=`pwd`/libmxnet.so @@ -180,6 +181,7 @@ build_centos7_cpu() { USE_LAPACK=1 \ USE_LAPACK_PATH=/usr/lib64/liblapack.so \ USE_BLAS=openblas \ + USE_DIST_KVSTORE=1 \ -j$(nproc) } @@ -206,6 +208,7 @@ build_centos7_gpu() { USE_CUDA=1 \ USE_CUDA_PATH=/usr/local/cuda \ USE_CUDNN=1 \ + USE_DIST_KVSTORE=1 \ -j$(nproc) } @@ -215,6 +218,7 @@ build_ubuntu_cpu_openblas() { DEV=1 \ USE_CPP_PACKAGE=1 \ USE_BLAS=openblas \ + USE_DIST_KVSTORE=1 \ -j$(nproc) } @@ -224,6 +228,7 @@ build_ubuntu_cpu_clang39() { USE_CPP_PACKAGE=1 \ USE_BLAS=openblas \ USE_OPENMP=0 \ + USE_DIST_KVSTORE=1 \ CXX=clang++-3.9 \ CC=clang-3.9 \ -j$(nproc) @@ -235,6 +240,7 @@ build_ubuntu_cpu_clang50() { USE_CPP_PACKAGE=1 \ USE_BLAS=openblas \ USE_OPENMP=1 \ + USE_DIST_KVSTORE=1 \ CXX=clang++-5.0 \ CC=clang-5.0 \ -j$(nproc) @@ -296,6 +302,7 @@ build_ubuntu_gpu_cuda91_cudnn7() { USE_CUDA_PATH=/usr/local/cuda \ USE_CUDNN=1 \ USE_CPP_PACKAGE=1 \ + USE_DIST_KVSTORE=1 \ -j$(nproc) } @@ -336,6 +343,7 @@ build_ubuntu_gpu_cmake() { -DUSE_CUDNN=1 \ -DUSE_MKLML_MKL=0 \ -DUSE_MKLDNN=0 \ + -DUSE_DIST_KVSTORE=1 \ -DCMAKE_BUILD_TYPE=Release \ -G Ninja \ /work/mxnet @@ -423,14 +431,14 @@ unittest_ubuntu_python3_quantization_gpu() { unittest_ubuntu_cpu_scala() { set -ex - make scalapkg USE_BLAS=openblas - make scalatest USE_BLAS=openblas + make scalapkg USE_BLAS=openblas USE_DIST_KVSTORE=1 + make scalatest USE_BLAS=openblas USE_DIST_KVSTORE=1 } unittest_ubuntu_gpu_scala() { set -ex - make scalapkg USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1 - make scalatest USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1 SCALA_TEST_ON_GPU=1 + make scalapkg USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1 USE_DIST_KVSTORE=1 + make scalatest USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1 SCALA_TEST_ON_GPU=1 USE_DIST_KVSTORE=1 } unittest_ubuntu_cpugpu_perl() { ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services