release memory of task node on the fly

.clang-format

@@ -19,7 +19,7 @@ AlwaysBreakBeforeMultilineStrings: false
 AlwaysBreakTemplateDeclarations: true
 BinPackArguments: true
 BinPackParameters: true
-BraceWrapping:   
+BraceWrapping:
   AfterClass:      true
   AfterControlStatement: false
   AfterEnum:       false
@@ -37,19 +37,18 @@ BreakBeforeTernaryOperators: true
 BreakConstructorInitializersBeforeComma: false
 BreakAfterJavaFieldAnnotations: false
 BreakStringLiterals: true
-ColumnLimit:     80
+ColumnLimit:     100
 CommentPragmas:  '^ IWYU pragma:'
 BreakBeforeInheritanceComma: false
 ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 4
 ContinuationIndentWidth: 4
 Cpp11BracedListStyle: true
-DerivePointerAlignment: true
 DisableFormat:   false
 ExperimentalAutoDetectBinPacking: false
 FixNamespaceComments: true
 ForEachMacros:   [ foreach, Q_FOREACH, BOOST_FOREACH ]
-IncludeCategories: 
+IncludeCategories:
   - Regex:           '^<.*\.h>'
     Priority:        1
   - Regex:           '^<.*'
@@ -78,7 +77,7 @@ PenaltyExcessCharacter: 1000000
 PenaltyReturnTypeOnItsOwnLine: 200
 PointerAlignment: Left
 ReflowComments:  true
-SortIncludes:    true
+SortIncludes:    false
 SpaceAfterCStyleCast: false
 SpaceAfterTemplateKeyword: false
 SpaceBeforeAssignmentOperators: true
@@ -94,4 +93,3 @@ Standard:        Cpp11
 TabWidth:        8
 UseTab:          Never
 ...
-

.dockerignore

@@ -0,0 +1,35 @@
+**/.git
+/build
+/build-*
+/docs/build
+/cmake-build-*
+/third_party
+/examples/**/oneflow
+/benchmark/**/oneflow
+/.vscode
+/.idea
+/.clangd
+/dist
+/wheelhouse*
+/.DS_Store
+/tmp_wheel
+/manylinux*
+
+**/__pycache__
+**/*.pyc
+**/log
+**/.ipynb_checkpoints
+**/core.0*
+**/core.1*
+**/core.2*
+**/core.3*
+**/core.4*
+**/core.5*
+**/core.6*
+**/core.7*
+**/core.8*
+**/core.9*
+/.cache
+/oneflow-src.zip
+/distributed-tmp
+/serving-tmp

.github/CODEOWNERS

@@ -1 +1,3 @@
 * @willzhang4a58
+*test.cpp @lixinqi
+/oneflow/core/kernel/opkernel_test_case.* @lixinqi

.github/PULL_REQUEST_TEMPLATE/general_template.md

@@ -0,0 +1,11 @@
+## 概述
+
+
+## PR Checklist
+ - [ ] PR 标题语句通畅，明确表达 PR 内容，适合直接作为新版本发布时的 changelog
+ - [ ] 代码格式化 
+ - [ ] 已经本地编译通过
+ - [ ] 已本地针对改动测试
+ - [ ] 已添加 type 标签:(填写 type 标签名，如 `bug, enhancement, purge, feature, documentation`)
+ - [ ] 已添加 component 标签:(填写 component 标签名，如 `op, system, eager, build, xla, python, ci, test, tooling, onnx`)
+ - [ ] Draft 转正式 PR 前已请人 Review

.github/PULL_REQUEST_TEMPLATE/op_template.md

@@ -0,0 +1,69 @@
+## 概述
+描述 op 的功能、公式等。若参考了其它框架的接口，应列出超链接。
+
+## 功能 CheckList
+**注意** : 功能复选框均为可选项，若未选择，说明理由即可。例如：该 Op 由 Python 接口拼接而成，因此无 `SetBatchAxisInferFn` Op 注册；再比如：该 Op 无输入，因此无 `SetInputArgModifyFn`。
+
+模板中自带的复选框可留空，但是不能删除。可根据实际情况增加复选框选项。
+
+### Op
+ - [ ] Op SetBatchAxisInferFn
+ - [ ] Op SetGetSbpFn
+ - [ ] Op SetInputArgModifyFn
+ - [ ] Op 反向梯度注册
+
+### Kernel
+ - [ ] CPU in:float32 
+ - [ ] CPU in:float64
+ - [ ] CPU in:int32
+ - [ ] CPU in:int64
+ - [ ] CPU in:int8
+
+ - [ ] GPU in:float32 
+ - [ ] GPU in:float64
+ - [ ] GPU in:int32
+ - [ ] GPU in:int64
+ - [ ] GPU in:float16
+ - [ ] GPU in:int8
+
+
+### Python Wrapper
+ - [ ] Python API 参数检查及异常提示
+ - [ ] 接口注释
+ - [ ] Example 
+
+### 测试
+ - [ ] 单机单卡  CPU Test Case 
+ - [ ] 单机单卡  GPU Test Case 
+ - [ ] 单机多卡  CPU Test Case 
+ - [ ] 单机多卡  GPU Test Case
+ - [ ] 分布式  CPU Test Case  
+ - [ ] 分布式  GPU Test Case  
+
+## GPU 有效带宽
+带 GPU 的 Op，请参考 https://github.com/Oneflow-Inc/OneTeam/issues/167 测试有效带宽，并附带测试报告。
+以下是报告样例：
+
+理论带宽：
+```text
+ Device to Device Bandwidth, 1 Device(s)
+ PINNED Memory Transfers
+   Transfer Size (Bytes)	Bandwidth(MB/s)
+   33554432			250798.5
+```
+
+实际带宽：
+```
+PROFILER::KERNEL::CUDA_MEMORY_BANDWIDTH op_name: sqrt_2 elapsed(ms): 0.196064 memory_size(Byte): 50331648 bandwidth(GB/s): 239.08
+PROFILER::KERNEL::CUDA_MEMORY_BANDWIDTH op_name: sqrt_2_grad elapsed(ms): 0.29072 memory_size(Byte): 75497472 bandwidth(GB/s): 241.856
+```
+
+
+## PR Checklist
+ - [ ] PR 标题语句通畅，明确表达 PR 内容，适合直接作为新版本发布时的 changelog
+ - [ ] 代码格式化 
+ - [ ] 已经本地编译通过
+ - [ ] 已本地针对改动测试
+ - [ ] 已添加 type 标签:(填写 type 标签名，如 `bug, enhancement, purge, feature, documentation`)
+ - [ ] 已添加 component 标签:(填写 component 标签名，如 `op, system, eager, build, xla, python, ci, test, tooling, onnx`)
+ - [ ] Draft 转正式 PR 前已请人 Review

.github/actions/mac-build/action.yml

@@ -0,0 +1,47 @@
+name: "Build OneFlow on macOS"
+description: ""
+runs:
+  using: "composite"
+  steps:
+    - name: Install dependencies
+      run: |
+        brew install nasm
+      shell: bash
+    - name: Set environment variables
+      run: |
+        set -x
+        cmake_flags=""
+        cmake_flags+=" -DPython3_EXECUTABLE=$(which python3)"
+        cmake_flags+=" -DRPC_BACKEND=LOCAL"
+        cmake_flags+=" -DCMAKE_BUILD_TYPE=Release"
+        cmake_flags+=" -DBUILD_CUDA=OFF"
+        echo "cmake_flags=${cmake_flags}" >> $GITHUB_ENV
+      shell: bash
+    - name: Build (third party)
+      run: |
+        mkdir -p build
+        cd build
+        cmake .. $cmake_flags -DTHIRD_PARTY=ON -DONEFLOW=OFF
+        make -j $(nproc)
+      shell: bash
+    - name: Build (of_ccobj)
+      run: |
+        mkdir -p build
+        cd build
+        cmake .. $cmake_flags -DTHIRD_PARTY=OFF -DONEFLOW=ON
+        make -j 2 of_ccobj
+      shell: bash
+    - name: Build (oneflow_internal)
+      run: |
+        mkdir -p build
+        cd build
+        cmake .. $cmake_flags -DTHIRD_PARTY=OFF -DONEFLOW=ON
+        make -j 2 oneflow_internal
+      shell: bash
+    - name: Build (generate_api)
+      run: |
+        mkdir -p build
+        cd build
+        cmake .. $cmake_flags -DTHIRD_PARTY=OFF -DONEFLOW=ON
+        make -j 2 generate_api
+      shell: bash

.github/actions/setup/action.yml

@@ -0,0 +1,14 @@
+inputs:
+  name:
+    description: 'Placeholder'
+    default: 'Placeholder'
+runs:
+  using: "composite"
+  steps:
+    - run: |
+        echo $HOSTNAME
+        rm -rf build/third_party
+        bash ci/setup_submodule.sh
+        auth_header="$(git config --local --get http.https://github.com/.extraheader)"
+        git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --recursive
+      shell: bash

.github/actions/upload_oss/action.yml

@@ -0,0 +1,31 @@
+inputs:
+  src_path:
+    required: true
+  oss_dst_path:
+    required: true
+  oss_access_key_id:
+    required: true
+  oss_access_key_secret:
+    required: true
+runs:
+  using: "composite"
+  steps:
+    - run: |
+        if [ -z "$OSS_ACCESS_KEY_ID" ]
+        then
+          exit 0
+        fi
+        if [ ! -f "$HOME/ossutil64" ]; then
+          curl http://gosspublic.alicdn.com/ossutil/1.6.19/ossutil64 -o $HOME/ossutil64
+        fi
+        chmod 755 $HOME/ossutil64
+        $HOME/ossutil64 config -e oss-cn-beijing.aliyuncs.com -i ${{ inputs.oss_access_key_id }} -k ${{ inputs.oss_access_key_secret }}  -L EN -c $HOME/.ossutilconfig
+        dir_arg=""
+        if [ -d "${{ inputs.src_path }}" ]; then
+          dir_arg="--recursive"
+        fi
+        $HOME/ossutil64 cp --update ${dir_arg} ${{ inputs.src_path }} ${{ inputs.oss_dst_path }}
+      shell: bash
+      env:
+        OSS_ACCESS_KEY_ID: ${{ inputs.oss_access_key_id }}
+        OSS_ACCESS_KEY_SECRET: ${{ inputs.oss_access_key_secret }}

.github/actions/upload_ssh/action.yml

@@ -0,0 +1,26 @@
+name: "Upload via ssh"
+description: ""
+inputs:
+  src_path:
+    required: true
+    description: ""
+  dst_host:
+    required: true
+    description: ""
+  dst_path:
+    required: true
+    description: ""
+runs:
+  using: "composite"
+  steps:
+    - run: |
+        set -x
+        dir_arg=""
+        if [ -d "${{ inputs.src_path }}" ]; then
+          dir_arg="-r"
+        fi
+        parent_dir=$(dirname ${{ inputs.dst_path }})
+        ssh -o StrictHostKeyChecking=no ${{ inputs.dst_host }} mkdir -p $parent_dir
+        ssh ${{ inputs.dst_host }} rm -rf ${{ inputs.dst_path }}
+        scp ${dir_arg} ${{ inputs.src_path }} ${{ inputs.dst_host }}:${{ inputs.dst_path }}
+      shell: bash

.github/actions/whl/action.yml

@@ -0,0 +1,36 @@
+inputs:
+  tmp_dir:
+    description: "tmp dir"
+    required: true
+  cuda_version:
+    description: "cuda_version"
+    default: "10.2"
+  python_version:
+    description: "python_version"
+    default: "3.6"
+  extra_flags:
+    description: "flags like --xla"
+    default: ""
+  extra_docker_args:
+    description: ""
+    default: ""
+runs:
+  using: "composite"
+  steps:
+    - run: |
+        set -x
+        src_dir=${PWD}
+        tmp_dir="${{ inputs.tmp_dir }}"
+        mkdir -p ${tmp_dir}
+        cd ${tmp_dir}
+        docker run --rm -v $PWD:/p -w $PWD:/p busybox rm -rf /p/wheelhouse
+        python3 ${src_dir}/docker/package/manylinux/build_wheel.py \
+            --cuda_version=${{ inputs.cuda_version }} \
+            --python_version=${{ inputs.python_version }} \
+            --use_tuna --use_system_proxy --use_aliyun_mirror \
+            --wheel_house_dir=${tmp_dir}/wheelhouse \
+            --oneflow_src_dir=${src_dir} ${{ inputs.extra_flags }} \
+            --retry=1 \
+            --skip_img \
+            --extra_docker_args "${extra_docker_args}"
+      shell: bash

.github/workflows/pr.yml

@@ -0,0 +1,19 @@
+name: Check PR
+
+on:
+  pull_request:
+    types: [opened, labeled, unlabeled, synchronize]
+
+jobs:
+  check_labels:
+    runs-on: ubuntu-18.04
+    name: Labels
+    steps:
+      - name: Check type labels 'bug, enhancement, purge, feature, documentation'
+        if: (contains(github.event.pull_request.labels.*.name, 'bug') || contains(github.event.pull_request.labels.*.name, 'enhancement') || contains(github.event.pull_request.labels.*.name, 'purge') || contains(github.event.pull_request.labels.*.name, 'feature') || contains(github.event.pull_request.labels.*.name, 'documentation')) == false
+        run: |
+          exit 1
+      - name: Check component labels 'op, system, eager, build, xla, python, ci, test, tooling, onnx'
+        if: (contains(github.event.pull_request.labels.*.name, 'op') || contains(github.event.pull_request.labels.*.name, 'system') || contains(github.event.pull_request.labels.*.name, 'eager') || contains(github.event.pull_request.labels.*.name, 'build') || contains(github.event.pull_request.labels.*.name, 'xla') || contains(github.event.pull_request.labels.*.name, 'python') || contains(github.event.pull_request.labels.*.name, 'ci') || contains(github.event.pull_request.labels.*.name, 'test') || contains(github.event.pull_request.labels.*.name, 'tooling') || contains(github.event.pull_request.labels.*.name, 'onnx')) == false
+        run: |
+          exit 2