fix various linter errors

.github/config/lint/.clang-format

@@ -0,0 +1,126 @@
+---
+AccessModifierOffset: -1
+AlignAfterOpenBracket: AlwaysBreak
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlinesLeft: true
+AlignOperands:   false
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Empty
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: true
+BinPackArguments: false
+BinPackParameters: false
+BraceWrapping:
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  BeforeCatch:     false
+  BeforeElse:      false
+  IndentBraces:    false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: false
+ColumnLimit:     80
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat:   false
+ForEachMacros:
+  - FOR_EACH_RANGE
+  - FOR_EACH
+IncludeCategories:
+  - Regex:           '^<.*\.h(pp)?>'
+    Priority:        1
+  - Regex:           '^<.*'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IndentCaseLabels: true
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+Macros:
+  - >-
+    PyObject_HEAD_INIT(type)={
+        /* this is not exactly match with PyObject_HEAD_INIT in Python source code
+         * but it is enough for clang-format */
+        { 0xFFFFFFFF },
+        (type)
+    },
+  - >-
+    PyVarObject_HEAD_INIT(type, size)={
+        {
+            /* manually expand PyObject_HEAD_INIT(type) above
+             * because clang-format do not support recursive expansion */
+            { 0xFFFFFFFF },
+            (type)
+        },
+        (size)
+    },
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 2000000
+PointerAlignment: Left
+ReflowComments:  true
+SortIncludes:    true
+SpaceAfterCStyleCast: false
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeParens: ControlStatements
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles:  false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard:        c++17
+StatementMacros:
+  - C10_DEFINE_bool
+  - C10_DEFINE_int
+  - C10_DEFINE_int32
+  - C10_DEFINE_int64
+  - C10_DEFINE_string
+  - C10_DEFINE_REGISTRY_WITHOUT_WARNING
+  - C10_REGISTER_CREATOR
+  - DEFINE_BINARY
+  - PyObject_HEAD
+  - PyObject_VAR_HEAD
+  - PyException_HEAD
+  - TORCH_DECLARE_bool
+
+TabWidth:        8
+UseTab:          Never
+---
+Language: ObjC
+ColumnLimit: 120
+AlignAfterOpenBracket: Align
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: false
+...

gloo/.clang-format

@@ -0,0 +1,126 @@
+---
+AccessModifierOffset: -1
+AlignAfterOpenBracket: AlwaysBreak
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlinesLeft: true
+AlignOperands:   false
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Empty
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: true
+BinPackArguments: false
+BinPackParameters: false
+BraceWrapping:
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  BeforeCatch:     false
+  BeforeElse:      false
+  IndentBraces:    false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: false
+ColumnLimit:     80
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat:   false
+ForEachMacros:
+  - FOR_EACH_RANGE
+  - FOR_EACH
+IncludeCategories:
+  - Regex:           '^<.*\.h(pp)?>'
+    Priority:        1
+  - Regex:           '^<.*'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IndentCaseLabels: true
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+Macros:
+  - >-
+    PyObject_HEAD_INIT(type)={
+        /* this is not exactly match with PyObject_HEAD_INIT in Python source code
+         * but it is enough for clang-format */
+        { 0xFFFFFFFF },
+        (type)
+    },
+  - >-
+    PyVarObject_HEAD_INIT(type, size)={
+        {
+            /* manually expand PyObject_HEAD_INIT(type) above
+             * because clang-format do not support recursive expansion */
+            { 0xFFFFFFFF },
+            (type)
+        },
+        (size)
+    },
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 2000000
+PointerAlignment: Left
+ReflowComments:  true
+SortIncludes:    true
+SpaceAfterCStyleCast: false
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeParens: ControlStatements
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles:  false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard:        c++17
+StatementMacros:
+  - C10_DEFINE_bool
+  - C10_DEFINE_int
+  - C10_DEFINE_int32
+  - C10_DEFINE_int64
+  - C10_DEFINE_string
+  - C10_DEFINE_REGISTRY_WITHOUT_WARNING
+  - C10_REGISTER_CREATOR
+  - DEFINE_BINARY
+  - PyObject_HEAD
+  - PyObject_VAR_HEAD
+  - PyException_HEAD
+  - TORCH_DECLARE_bool
+
+TabWidth:        8
+UseTab:          Never
+---
+Language: ObjC
+ColumnLimit: 120
+AlignAfterOpenBracket: Align
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: false
+...

gloo/allreduce_bcube.h

@@ -214,8 +214,11 @@ class Group {
    * @count The total number of elements to be processed by this node
    * @return The number of elements to be processed by this group
    */
-  static int
-  computeNumElems(int step, const Node& firstNode, int peers, int count) {
+  static int computeNumElems(
+      int step,
+      const Node& firstNode,
+      int peers,
+      int count) {
     int groupCount =
         (0 == step) ? count : firstNode.getNumElemsPerStep(step - 1);
     return std::max(groupCount, peers);
@@ -226,8 +229,11 @@ class Group {
    *   group
    * @return List of ranks of nodes in the group
    */
-  std::vector<int>
-  getNodeRanks(int firstNodeRank, int peerDistance, int base, int nodes) const {
+  std::vector<int> getNodeRanks(
+      int firstNodeRank,
+      int peerDistance,
+      int base,
+      int nodes) const {
     std::vector<int> groupPeers;
     for (int i = 0; i < base; ++i) {
       int peerRank = firstNodeRank + i * peerDistance;

gloo/alltoallv.h

@@ -78,8 +78,10 @@ class AlltoallvOptions {
       size_t elementSize);
 
   // Untemplated implementation of setInput on opaque pointer.
-  void
-  setInput(void* ptr, std::vector<int64_t> elementsPerRank, size_t elementSize);
+  void setInput(
+      void* ptr,
+      std::vector<int64_t> elementsPerRank,
+      size_t elementSize);
 
   // Untemplated implementation of setOutput on unbound buffer.
   void setOutput(

gloo/common/string.h

@@ -28,8 +28,10 @@ inline void MakeStringInternal(
 }
 
 template <typename T, typename... Args>
-inline void
-MakeStringInternal(std::stringstream& ss, const T& t, const Args&... args) {
+inline void MakeStringInternal(
+    std::stringstream& ss,
+    const T& t,
+    const Args&... args) {
   MakeStringInternal(ss, t);
   MakeStringInternal(ss, args...);
 }

gloo/cuda_allreduce_bcube.h

@@ -389,16 +389,22 @@ class Group {
    * @count The total number of elements to be processed by this node
    * @return The number of elements to be processed by this group
    */
-  static int
-  computeNumElems(int step, const Node& firstNode, int peers, int count);
+  static int computeNumElems(
+      int step,
+      const Node& firstNode,
+      int peers,
+      int count);
   /**
    * Determines all the nodes in a group in a particular step
    * @param peerDistance This is the distance between rank of each peer in the
    *   group
    * @return List of ranks of nodes in the group
    */
-  std::vector<int>
-  getNodeRanks(int firstNodeRank, int peerDistance, int base, int nodes) const;
+  std::vector<int> getNodeRanks(
+      int firstNodeRank,
+      int peerDistance,
+      int base,
+      int nodes) const;
 };
 
 } // namespace bcube

gloo/math.h

@@ -98,23 +98,35 @@ inline uint32_t log2ceil(uint32_t value) {
 
 template <>
 void sum<float16>(void* c, const void* a, const void* b, size_t n);
-extern template void
-sum<float16>(void* c, const void* a, const void* b, size_t n);
+extern template void sum<float16>(
+    void* c,
+    const void* a,
+    const void* b,
+    size_t n);
 
 template <>
 void product<float16>(void* c, const void* a, const void* b, size_t n);
-extern template void
-product<float16>(void* c, const void* a, const void* b, size_t n);
+extern template void product<float16>(
+    void* c,
+    const void* a,
+    const void* b,
+    size_t n);
 
 template <>
 void max<float16>(void* c, const void* a, const void* b, size_t n);
-extern template void
-max<float16>(void* c, const void* a, const void* b, size_t n);
+extern template void max<float16>(
+    void* c,
+    const void* a,
+    const void* b,
+    size_t n);
 
 template <>
 void min<float16>(void* c, const void* a, const void* b, size_t n);
-extern template void
-min<float16>(void* c, const void* a, const void* b, size_t n);
+extern template void min<float16>(
+    void* c,
+    const void* a,
+    const void* b,
+    size_t n);
 
 #endif