Update on "Add correct __all__ for torch.distributed and torch.cuda s…

…ubmodules"

[ghstack-poisoned]

.circleci/docker/centos-rocm/Dockerfile

@@ -71,6 +71,9 @@ ARG ROCM_VERSION
 COPY ./common/install_rocm.sh install_rocm.sh
 RUN bash ./install_rocm.sh
 RUN rm install_rocm.sh
+COPY ./common/install_rocm_magma.sh install_rocm_magma.sh
+RUN bash ./install_rocm_magma.sh
+RUN rm install_rocm_magma.sh
 ENV PATH /opt/rocm/bin:$PATH
 ENV PATH /opt/rocm/hcc/bin:$PATH
 ENV PATH /opt/rocm/hip/bin:$PATH

.circleci/docker/common/install_rocm.sh

@@ -2,34 +2,6 @@
 
 set -ex
 
-install_magma() {
-    # "install" hipMAGMA into /opt/rocm/magma by copying after build
-    git clone https://bitbucket.org/icl/magma.git
-    pushd magma
-    # Fixes memory leaks of magma found while executing linalg UTs
-    git checkout 5959b8783e45f1809812ed96ae762f38ee701972
-    cp make.inc-examples/make.inc.hip-gcc-mkl make.inc
-    echo 'LIBDIR += -L$(MKLROOT)/lib' >> make.inc
-    echo 'LIB += -Wl,--enable-new-dtags -Wl,--rpath,/opt/rocm/lib -Wl,--rpath,$(MKLROOT)/lib -Wl,--rpath,/opt/rocm/magma/lib' >> make.inc
-    echo 'DEVCCFLAGS += --gpu-max-threads-per-block=256' >> make.inc
-    export PATH="${PATH}:/opt/rocm/bin"
-    if [[ -n "$PYTORCH_ROCM_ARCH" ]]; then
-      amdgpu_targets=`echo $PYTORCH_ROCM_ARCH | sed 's/;/ /g'`
-    else
-      amdgpu_targets=`rocm_agent_enumerator | grep -v gfx000 | sort -u | xargs`
-    fi
-    for arch in $amdgpu_targets; do
-      echo "DEVCCFLAGS += --amdgpu-target=$arch" >> make.inc
-    done
-    # hipcc with openmp flag may cause isnan() on __device__ not to be found; depending on context, compiler may attempt to match with host definition
-    sed -i 's/^FOPENMP/#FOPENMP/g' make.inc
-    make -f make.gen.hipMAGMA -j $(nproc)
-    LANG=C.UTF-8 make lib/libmagma.so -j $(nproc) MKLROOT=/opt/conda
-    make testing/testing_dgemm -j $(nproc) MKLROOT=/opt/conda
-    popd
-    mv magma /opt/rocm
-}
-
 ver() {
     printf "%3d%03d%03d%03d" $(echo "$1" | tr '.' ' ');
 }
@@ -89,8 +61,6 @@ install_ubuntu() {
       DEBIAN_FRONTEND=noninteractive apt-get install -y --allow-unauthenticated ${MIOPENKERNELS}
     fi
 
-    install_magma
-
     # Cleanup
     apt-get autoclean && apt-get clean
     rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
@@ -135,8 +105,6 @@ install_centos() {
                    rocprofiler-dev \
                    roctracer-dev
 
-  install_magma
-
   # Cleanup
   yum clean all
   rm -rf /var/cache/yum

.circleci/docker/common/install_rocm_magma.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+set -ex
+
+# "install" hipMAGMA into /opt/rocm/magma by copying after build
+git clone https://bitbucket.org/icl/magma.git
+pushd magma
+# Fixes memory leaks of magma found while executing linalg UTs
+git checkout 5959b8783e45f1809812ed96ae762f38ee701972
+cp make.inc-examples/make.inc.hip-gcc-mkl make.inc
+echo 'LIBDIR += -L$(MKLROOT)/lib' >> make.inc
+echo 'LIB += -Wl,--enable-new-dtags -Wl,--rpath,/opt/rocm/lib -Wl,--rpath,$(MKLROOT)/lib -Wl,--rpath,/opt/rocm/magma/lib' >> make.inc
+echo 'DEVCCFLAGS += --gpu-max-threads-per-block=256' >> make.inc
+export PATH="${PATH}:/opt/rocm/bin"
+if [[ -n "$PYTORCH_ROCM_ARCH" ]]; then
+  amdgpu_targets=`echo $PYTORCH_ROCM_ARCH | sed 's/;/ /g'`
+else
+  amdgpu_targets=`rocm_agent_enumerator | grep -v gfx000 | sort -u | xargs`
+fi
+for arch in $amdgpu_targets; do
+  echo "DEVCCFLAGS += --amdgpu-target=$arch" >> make.inc
+done
+# hipcc with openmp flag may cause isnan() on __device__ not to be found; depending on context, compiler may attempt to match with host definition
+sed -i 's/^FOPENMP/#FOPENMP/g' make.inc
+make -f make.gen.hipMAGMA -j $(nproc)
+LANG=C.UTF-8 make lib/libmagma.so -j $(nproc) MKLROOT=/opt/conda
+make testing/testing_dgemm -j $(nproc) MKLROOT=/opt/conda
+popd
+mv magma /opt/rocm

.circleci/docker/requirements-ci.txt

@@ -124,6 +124,11 @@ numba==0.55.2 ; python_version == "3.10"
 #Pinned versions: 1.9.0
 #test that import:
 
+opt-einsum==3.3
+#Description: Python library to optimize tensor contraction order, used in einsum
+#Pinned versions: 3.3
+#test that import: test_linalg.py
+
 #pillow
 #Description:  Python Imaging Library fork
 #Pinned versions:

.circleci/docker/ubuntu-rocm/Dockerfile

@@ -64,6 +64,9 @@ ARG ROCM_VERSION
 COPY ./common/install_rocm.sh install_rocm.sh
 RUN bash ./install_rocm.sh
 RUN rm install_rocm.sh
+COPY ./common/install_rocm_magma.sh install_rocm_magma.sh
+RUN bash ./install_rocm_magma.sh
+RUN rm install_rocm_magma.sh
 ENV PATH /opt/rocm/bin:$PATH
 ENV PATH /opt/rocm/hcc/bin:$PATH
 ENV PATH /opt/rocm/hip/bin:$PATH

.circleci/generate_config_yml.py

@@ -143,9 +143,9 @@ def gen_build_workflows_tree():
         cimodel.data.simple.mobile_definitions.get_workflow_jobs,
         cimodel.data.simple.nightly_ios.get_workflow_jobs,
         cimodel.data.simple.anaconda_prune_defintions.get_workflow_jobs,
-        # cimodel.data.simple.macos_definitions.get_new_workflow_jobs,
-        # cimodel.data.simple.upload_test_stats_definition.get_workflow_job,
-        # cimodel.data.simple.ios_definitions.get_workflow_jobs,
+        cimodel.data.simple.macos_definitions.get_new_workflow_jobs,
+        cimodel.data.simple.upload_test_stats_definition.get_workflow_job,
+        cimodel.data.simple.ios_definitions.get_workflow_jobs,
     ]
     build_jobs = [f() for f in build_workflows_functions]
     build_jobs.extend(

.circleci/scripts/binary_ios_test.sh

@@ -1,30 +1,19 @@
 #!/bin/bash
 set -ex -o pipefail
 
+if ! [ "$IOS_PLATFORM" == "SIMULATOR" ]; then
+    exit 0
+fi
+
 echo ""
 echo "DIR: $(pwd)"
 PROJ_ROOT=/Users/distiller/project
 cd ${PROJ_ROOT}/ios/TestApp
 # install fastlane
 sudo gem install bundler && bundle install
-# install certificates
-echo "${IOS_CERT_KEY_2022}" >> cert.txt
-base64 --decode cert.txt -o Certificates.p12
-rm cert.txt
-bundle exec fastlane install_root_cert
-bundle exec fastlane install_dev_cert
-# install the provisioning profile
-PROFILE=PyTorch_CI_2022.mobileprovision
-PROVISIONING_PROFILES=~/Library/MobileDevice/Provisioning\ Profiles
-mkdir -pv "${PROVISIONING_PROFILES}"
-cd "${PROVISIONING_PROFILES}"
-echo "${IOS_SIGN_KEY_2022}" >> cert.txt
-base64 --decode cert.txt -o ${PROFILE}
-rm cert.txt
 # run the ruby build script
 if ! [ -x "$(command -v xcodebuild)" ]; then
     echo 'Error: xcodebuild is not installed.'
     exit 1
 fi
-PROFILE=PyTorch_CI_2022
-ruby ${PROJ_ROOT}/scripts/xcode_build.rb -i ${PROJ_ROOT}/build_ios/install -x ${PROJ_ROOT}/ios/TestApp/TestApp.xcodeproj -p ${IOS_PLATFORM} -c ${PROFILE} -t ${IOS_DEV_TEAM_ID}
+ruby ${PROJ_ROOT}/scripts/xcode_build.rb -i ${PROJ_ROOT}/build_ios/install -x ${PROJ_ROOT}/ios/TestApp/TestApp.xcodeproj -p ${IOS_PLATFORM}

.circleci/scripts/binary_ios_upload.sh

@@ -33,7 +33,7 @@ fi
 cp ${PROJ_ROOT}/LICENSE ${ZIP_DIR}/
 # zip the library
 export DATE="$(date -u +%Y%m%d)"
-export IOS_NIGHTLY_BUILD_VERSION="1.13.0.${DATE}"
+export IOS_NIGHTLY_BUILD_VERSION="1.14.0.${DATE}"
 if [ "${BUILD_LITE_INTERPRETER}" == "1" ]; then
     # libtorch_lite_ios_nightly_1.11.0.20210810.zip
     ZIPFILE="libtorch_lite_ios_nightly_${IOS_NIGHTLY_BUILD_VERSION}.zip"

.circleci/scripts/binary_populate_env.sh

@@ -59,7 +59,7 @@ PIP_UPLOAD_FOLDER='nightly/'
 # We put this here so that OVERRIDE_PACKAGE_VERSION below can read from it
 export DATE="$(date -u +%Y%m%d)"
 #TODO: We should be pulling semver version from the base version.txt
-BASE_BUILD_VERSION="1.13.0.dev$DATE"
+BASE_BUILD_VERSION="1.14.0.dev$DATE"
 # Change BASE_BUILD_VERSION to git tag when on a git tag
 # Use 'git -C' to make doubly sure we're in the correct directory for checking
 # the git tag
@@ -131,7 +131,7 @@ else
 fi
 export PYTORCH_EXTRA_INSTALL_REQUIREMENTS="${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}"
 export DATE="$DATE"
-export NIGHTLIES_DATE_PREAMBLE=1.13.0.dev
+export NIGHTLIES_DATE_PREAMBLE=1.14.0.dev
 export PYTORCH_BUILD_VERSION="$PYTORCH_BUILD_VERSION"
 export PYTORCH_BUILD_NUMBER="$PYTORCH_BUILD_NUMBER"
 export OVERRIDE_PACKAGE_VERSION="$PYTORCH_BUILD_VERSION"

.circleci/scripts/binary_upload.sh

@@ -14,6 +14,12 @@ UPLOAD_CHANNEL=${UPLOAD_CHANNEL:-nightly}
 UPLOAD_SUBFOLDER=${UPLOAD_SUBFOLDER:-cpu}
 UPLOAD_BUCKET="s3://pytorch"
 BACKUP_BUCKET="s3://pytorch-backup"
+BUILD_NAME=${BUILD_NAME:-}
+
+# this is temporary change to upload pypi-cudnn builds to separate folder
+if [[ ${BUILD_NAME} == *with-pypi-cudnn* ]]; then
+  UPLOAD_SUBFOLDER="${UPLOAD_SUBFOLDER}_pypi_cudnn"
+fi
 
 DRY_RUN=${DRY_RUN:-enabled}
 # Don't actually do work unless explicit
@@ -26,7 +32,7 @@ fi
 
 # Sleep 2 minutes between retries for conda upload
 retry () {
-  "$@"  || (sleep 2m && "$@") || (sleep 2m && "$@")
+  "$@"  || (sleep 5m && "$@") || (sleep 5m && "$@") || (sleep 5m && "$@") || (sleep 5m && "$@")
 }
 
 do_backup() {