[WIP: Do not merge] Fix cat while keeping the memory layout

.bazelrc

@@ -1,4 +1,4 @@
-build --cxxopt=--std=c++14
+build --cxxopt=--std=c++17
 build --copt=-I.
 # Bazel does not support including its cc_library targets as system
 # headers. We work around this for generated code

.circleci/docker/build.sh

@@ -33,7 +33,7 @@ function extract_all_from_image_name() {
     if [ "x${name}" = xpy ]; then
       vername=ANACONDA_PYTHON_VERSION
     fi
-    # skip non-conforming fields such as "pytorch", "linux" or "xenial" without version string
+    # skip non-conforming fields such as "pytorch", "linux" or "bionic" without version string
     if [ -n "${name}" ]; then
       extract_version_from_image_name "${name}" "${vername}"
     fi
@@ -46,11 +46,7 @@ if [[ "$image" == *xla* ]]; then
   exit 0
 fi
 
-if [[ "$image" == *-xenial* ]]; then
-  UBUNTU_VERSION=16.04
-elif [[ "$image" == *-artful* ]]; then
-  UBUNTU_VERSION=17.10
-elif [[ "$image" == *-bionic* ]]; then
+if [[ "$image" == *-bionic* ]]; then
   UBUNTU_VERSION=18.04
 elif [[ "$image" == *-focal* ]]; then
   UBUNTU_VERSION=20.04
@@ -79,56 +75,17 @@ elif [[ "$image" == *rocm* ]]; then
   DOCKERFILE="${OS}-rocm/Dockerfile"
 fi
 
-if [[ "$image" == *xenial* ]] || [[ "$image" == *bionic* ]]; then
-  CMAKE_VERSION=3.13.5
-fi
+# CMake 3.18 is needed to support CUDA17 language variant
+CMAKE_VERSION=3.18.5
 
 TRAVIS_DL_URL_PREFIX="https://s3.amazonaws.com/travis-python-archives/binaries/ubuntu/14.04/x86_64"
 _UCX_COMMIT=31e74cac7bee0ef66bef2af72e7d86d9c282e5ab
-_UCC_COMMIT=12944da33f911daf505d9bbc51411233d0ed85e1
+_UCC_COMMIT=1c7a7127186e7836f73aafbd7697bbc274a77eee
 
 # It's annoying to rename jobs every time you want to rewrite a
 # configuration, so we hardcode everything here rather than do it
 # from scratch
 case "$image" in
-  pytorch-linux-xenial-py3.8)
-    ANACONDA_PYTHON_VERSION=3.8
-    GCC_VERSION=7
-    # Do not install PROTOBUF, DB, and VISION as a test
-    ;;
-  pytorch-linux-xenial-py3.7-gcc7.2)
-    ANACONDA_PYTHON_VERSION=3.7
-    GCC_VERSION=7
-    # Do not install PROTOBUF, DB, and VISION as a test
-    ;;
-  pytorch-linux-xenial-py3.7-gcc7)
-    ANACONDA_PYTHON_VERSION=3.7
-    GCC_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ;;
-  pytorch-linux-xenial-cuda10.2-cudnn7-py3-gcc7)
-    CUDA_VERSION=10.2
-    CUDNN_VERSION=7
-    ANACONDA_PYTHON_VERSION=3.7
-    GCC_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    KATEX=yes
-    ;;
-  pytorch-linux-xenial-cuda11.3-cudnn8-py3-gcc7)
-    CUDA_VERSION=11.3.0 # Deviating from major.minor to conform to nvidia's Docker image names
-    CUDNN_VERSION=8
-    TENSORRT_VERSION=8.0.1.6
-    ANACONDA_PYTHON_VERSION=3.7
-    GCC_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    KATEX=yes
-    ;;
   pytorch-linux-bionic-cuda11.3-cudnn8-py3-clang9)
     CUDA_VERSION=11.3.0 # Deviating from major.minor to conform to nvidia's Docker image names
     CUDNN_VERSION=8
@@ -167,20 +124,6 @@ case "$image" in
     UCC_COMMIT=${_UCC_COMMIT}
     CONDA_CMAKE=yes
     ;;
-  pytorch-linux-xenial-py3-clang5-asan)
-    ANACONDA_PYTHON_VERSION=3.7
-    CLANG_VERSION=5.0
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ;;
-  pytorch-linux-xenial-py3-clang7-asan)
-    ANACONDA_PYTHON_VERSION=3.7
-    CLANG_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ;;
   pytorch-linux-focal-py3-clang7-asan)
     ANACONDA_PYTHON_VERSION=3.7
     CLANG_VERSION=7
@@ -189,13 +132,6 @@ case "$image" in
     VISION=yes
     CONDA_CMAKE=yes
     ;;
-  pytorch-linux-xenial-py3-clang7-onnx)
-    ANACONDA_PYTHON_VERSION=3.7
-    CLANG_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ;;
   pytorch-linux-focal-py3-clang10-onnx)
     ANACONDA_PYTHON_VERSION=3.7
     CLANG_VERSION=10
@@ -204,23 +140,16 @@ case "$image" in
     VISION=yes
     CONDA_CMAKE=yes
     ;;
-  pytorch-linux-xenial-py3-clang5-android-ndk-r19c)
+  pytorch-linux-focal-py3-clang7-android-ndk-r19c)
     ANACONDA_PYTHON_VERSION=3.7
-    CLANG_VERSION=5.0
+    CLANG_VERSION=7
     LLVMDEV=yes
     PROTOBUF=yes
     ANDROID=yes
     ANDROID_NDK_VERSION=r19c
     GRADLE_VERSION=6.8.3
     NINJA_VERSION=1.9.0
     ;;
-  pytorch-linux-xenial-py3.7-clang7)
-    ANACONDA_PYTHON_VERSION=3.7
-    CLANG_VERSION=7
-    PROTOBUF=yes
-    DB=yes
-    VISION=yes
-    ;;
   pytorch-linux-bionic-py3.7-clang9)
     ANACONDA_PYTHON_VERSION=3.7
     CLANG_VERSION=9
@@ -259,17 +188,17 @@ case "$image" in
     VISION=yes
     CONDA_CMAKE=yes
     ;;
-  pytorch-linux-focal-rocm5.1-py3.7)
-    ANACONDA_PYTHON_VERSION=3.7
+  pytorch-linux-focal-rocm5.1-py3.8)
+    ANACONDA_PYTHON_VERSION=3.8
     GCC_VERSION=9
     PROTOBUF=yes
     DB=yes
     VISION=yes
     ROCM_VERSION=5.1.1
     CONDA_CMAKE=yes
     ;;
-  pytorch-linux-focal-rocm5.2-py3.7)
-    ANACONDA_PYTHON_VERSION=3.7
+  pytorch-linux-focal-rocm5.2-py3.8)
+    ANACONDA_PYTHON_VERSION=3.8
     GCC_VERSION=9
     PROTOBUF=yes
     DB=yes
@@ -279,7 +208,6 @@ case "$image" in
     ;;
   pytorch-linux-focal-py3.7-gcc7)
     ANACONDA_PYTHON_VERSION=3.7
-    CMAKE_VERSION=3.16.9  # Required for precompiled header support
     GCC_VERSION=7
     PROTOBUF=yes
     DB=yes
@@ -320,6 +248,10 @@ case "$image" in
     fi
     if [[ "$image" == *rocm* ]]; then
       extract_version_from_image_name rocm ROCM_VERSION
+      NINJA_VERSION=1.9.0
+    fi
+    if [[ "$image" == *centos7* ]]; then
+      NINJA_VERSION=1.10.2
     fi
     if [[ "$image" == *gcc* ]]; then
       extract_version_from_image_name gcc GCC_VERSION

.circleci/docker/common/install_base.sh

@@ -68,7 +68,10 @@ install_ubuntu() {
     sudo \
     vim \
     jq \
-    libtool
+    libtool \
+    vim \
+    unzip \
+    gdb
 
   # Should resolve issues related to various apt package repository cert issues
   # see: https://github.com/pytorch/pytorch/issues/65931
@@ -126,7 +129,9 @@ install_centos() {
     opencv-devel \
     sudo \
     wget \
-    vim
+    vim \
+    unzip \
+    gdb
 
   # Cleanup
   yum clean all

.circleci/docker/common/install_conda.sh

@@ -104,9 +104,6 @@ if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
     conda_install magma-cuda$(TMP=${CUDA_VERSION/./};echo ${TMP%.*[0-9]}) -c pytorch
   fi
 
-  # TODO: This isn't working atm
-  conda_install nnpack -c killeent
-
   # Install some other packages, including those needed for Python test reporting
   pip_install -r /opt/conda/requirements-ci.txt
 

.circleci/docker/common/install_cudnn.sh

@@ -6,9 +6,9 @@ if [[ ${CUDNN_VERSION} == 8 ]]; then
     CUDNN_NAME="cudnn-linux-x86_64-8.3.2.44_cuda11.5-archive"
     if [[ ${CUDA_VERSION:0:4} == "11.7" ]]; then
         CUDNN_NAME="cudnn-linux-x86_64-8.5.0.96_cuda11-archive"
-        curl -OLs https://ossci-linux.s3.amazonaws.com/${CUDNN_NAME}.tar.xz
+        curl --retry 3 -OLs https://ossci-linux.s3.amazonaws.com/${CUDNN_NAME}.tar.xz
     else
-        curl -OLs  https://developer.download.nvidia.com/compute/redist/cudnn/v8.3.2/local_installers/11.5/${CUDNN_NAME}.tar.xz
+        curl --retry 3 -OLs  https://developer.download.nvidia.com/compute/redist/cudnn/v8.3.2/local_installers/11.5/${CUDNN_NAME}.tar.xz
     fi
 
     tar xf ${CUDNN_NAME}.tar.xz

.circleci/docker/common/install_docs_reqs.sh

@@ -7,10 +7,10 @@ if [ -n "$KATEX" ]; then
   # Ignore error if gpg-agent doesn't exist (for Ubuntu 16.04)
   apt-get install -y gpg-agent || :
 
-  curl -sL https://deb.nodesource.com/setup_12.x | sudo -E bash -
+  curl --retry 3 -sL https://deb.nodesource.com/setup_12.x | sudo -E bash -
   sudo apt-get install -y nodejs
 
-  curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | sudo apt-key add -
+  curl --retry 3 -sS https://dl.yarnpkg.com/debian/pubkey.gpg | sudo apt-key add -
   echo "deb https://dl.yarnpkg.com/debian/ stable main" | sudo tee /etc/apt/sources.list.d/yarn.list
 
   apt-get update

.circleci/docker/common/install_protobuf.sh

@@ -12,7 +12,7 @@ install_protobuf_317() {
   #   g++: error: ./../lib64/crti.o: No such file or directory
   ln -s /usr/lib64 "$pb_dir/lib64"
 
-  curl -LO "https://github.com/protocolbuffers/protobuf/releases/download/v3.17.3/protobuf-all-3.17.3.tar.gz"
+  curl -LO "https://github.com/protocolbuffers/protobuf/releases/download/v3.17.3/protobuf-all-3.17.3.tar.gz" --retry 3
   tar -xvz -C "$pb_dir" --strip-components 1 -f protobuf-all-3.17.3.tar.gz
   # -j6 to balance memory usage and speed.
   # naked `-j` seems to use too much memory.

.circleci/docker/common/install_rocm.sh

@@ -29,7 +29,12 @@ install_ubuntu() {
     if [[ $(ver $ROCM_VERSION) -ge $(ver 4.5) ]]; then
         # Add amdgpu repository
         UBUNTU_VERSION_NAME=`cat /etc/os-release | grep UBUNTU_CODENAME | awk -F= '{print $2}'`
-        local amdgpu_baseurl="https://repo.radeon.com/amdgpu/${AMDGPU_VERSIONS[$ROCM_VERSION]}/ubuntu"
+        local amdgpu_baseurl
+        if [[ $(ver $ROCM_VERSION) -ge $(ver 5.3) ]]; then
+          amdgpu_baseurl="https://repo.radeon.com/amdgpu/${ROCM_VERSION}/ubuntu"
+        else
+          amdgpu_baseurl="https://repo.radeon.com/amdgpu/${AMDGPU_VERSIONS[$ROCM_VERSION]}/ubuntu"
+        fi
         echo "deb [arch=amd64] ${amdgpu_baseurl} ${UBUNTU_VERSION_NAME} main" > /etc/apt/sources.list.d/amdgpu.list
     fi
 
@@ -38,6 +43,10 @@ install_ubuntu() {
         ROCM_REPO="xenial"
     fi
 
+    if [[ $(ver $ROCM_VERSION) -ge $(ver 5.3) ]]; then
+        ROCM_REPO="${UBUNTU_VERSION_NAME}"
+    fi
+
     # Add rocm repository
     wget -qO - http://repo.radeon.com/rocm/rocm.gpg.key | apt-key add -
     local rocm_baseurl="http://repo.radeon.com/rocm/apt/${ROCM_VERSION}"
@@ -78,7 +87,16 @@ install_centos() {
 
   if [[ $(ver $ROCM_VERSION) -ge $(ver 4.5) ]]; then
       # Add amdgpu repository
-      local amdgpu_baseurl="https://repo.radeon.com/amdgpu/${AMDGPU_VERSIONS[$ROCM_VERSION]}/rhel/7.9/main/x86_64"
+      local amdgpu_baseurl
+      if [[ $OS_VERSION == 9 ]]; then
+          amdgpu_baseurl="https://repo.radeon.com/amdgpu/${AMDGPU_VERSIONS[$ROCM_VERSION]}/rhel/9.0/main/x86_64"
+      else
+        if [[ $(ver $ROCM_VERSION) -ge $(ver 5.3) ]]; then
+          amdgpu_baseurl="https://repo.radeon.com/amdgpu/${ROCM_VERSION}/rhel/7.9/main/x86_64"
+        else
+          amdgpu_baseurl="https://repo.radeon.com/amdgpu/${AMDGPU_VERSIONS[$ROCM_VERSION]}/rhel/7.9/main/x86_64"
+        fi
+      fi
       echo "[AMDGPU]" > /etc/yum.repos.d/amdgpu.repo
       echo "name=AMDGPU" >> /etc/yum.repos.d/amdgpu.repo
       echo "baseurl=${amdgpu_baseurl}" >> /etc/yum.repos.d/amdgpu.repo

.circleci/docker/requirements-ci.txt

@@ -159,8 +159,13 @@ pytest-shard
 #Pinned versions:
 #test that import:
 
+pytest-flakefinder==1.1.0
+#Description: plugin for rerunning tests a fixed number of times in pytest
+#Pinned versions: 1.1.0
+#test that import:
+
 pytest-rerunfailures
-#Description: plugin for rerunning tests in pytest
+#Description: plugin for rerunning failure tests in pytest
 #Pinned versions:
 #test that import:
 

.circleci/scripts/binary_install_miniconda.sh

@@ -31,9 +31,9 @@ fi
 
 conda_sh="$workdir/install_miniconda.sh"
 if [[ "$(uname)" == Darwin ]]; then
-  curl --retry 3 -o "$conda_sh" https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
+  curl --retry 3 --retry-all-errors -o "$conda_sh" https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
 else
-  curl --retry 3 -o "$conda_sh" https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
+  curl --retry 3 --retry-all-errors -o "$conda_sh" https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
 fi
 chmod +x "$conda_sh"
 "$conda_sh" -b -p "$MINICONDA_ROOT"

.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="1.14.0.${DATE}"
+export IOS_NIGHTLY_BUILD_VERSION="2.0.0.${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_linux_test.sh

@@ -98,7 +98,7 @@ if [[ "$PACKAGE_TYPE" == conda ]]; then
     conda install \${EXTRA_CONDA_FLAGS} -y "\$pkg" --offline
   )
 elif [[ "$PACKAGE_TYPE" != libtorch ]]; then
-  pip install "\$pkg"
+  pip install "\$pkg" --extra-index-url "https://download.pytorch.org/whl/nightly/${DESIRED_CUDA}"
   retry pip install -q future numpy protobuf typing-extensions six
 fi
 if [[ "$PACKAGE_TYPE" == libtorch ]]; then

.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="$(date -u +%Y%m%d)"
 #TODO: We should be pulling semver version from the base version.txt
-BASE_BUILD_VERSION="1.14.0.dev$DATE"
+BASE_BUILD_VERSION="2.0.0.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

.circleci/scripts/build_android_gradle.sh

@@ -20,6 +20,11 @@ do
   touch "$file" || true
 done < <(find /var/lib/jenkins/.gradle -type f -print0)
 
+# Patch pocketfft (as Android does not have aligned_alloc even if compiled with c++17
+if [ -f ~/workspace/third_party/pocketfft/pocketfft_hdronly.h ]; then
+  sed -i -e "s/#if __cplusplus >= 201703L/#if 0/" ~/workspace/third_party/pocketfft/pocketfft_hdronly.h
+fi
+
 export GRADLE_LOCAL_PROPERTIES=~/workspace/android/local.properties
 rm -f $GRADLE_LOCAL_PROPERTIES
 echo "sdk.dir=/opt/android/sdk" >> $GRADLE_LOCAL_PROPERTIES

.circleci/scripts/driver_update.bat

@@ -1,5 +1,5 @@
 set "DRIVER_DOWNLOAD_LINK=https://s3.amazonaws.com/ossci-windows/452.39-data-center-tesla-desktop-win10-64bit-international.exe"
-curl --retry 3 -kL %DRIVER_DOWNLOAD_LINK% --output 452.39-data-center-tesla-desktop-win10-64bit-international.exe
+curl --retry 3 --retry-all-errors -kL %DRIVER_DOWNLOAD_LINK% --output 452.39-data-center-tesla-desktop-win10-64bit-international.exe
 if errorlevel 1 exit /b 1
 
 start /wait 452.39-data-center-tesla-desktop-win10-64bit-international.exe -s -noreboot

.circleci/scripts/python_doc_push_script.sh

@@ -135,6 +135,9 @@ git commit -m "Generate Python docs from pytorch/pytorch@${GITHUB_SHA}" || true
 git status
 
 if [[ "${WITH_PUSH:-}" == true ]]; then
+  # push to a temp branch first to trigger CLA check and satisfy branch protections
+  git push -u origin HEAD:pytorchbot/temp-branch-py -f
+  sleep 30
   git push -u origin "${branch}"
 fi