Transformer kernel release (#242)

* Transformer kernels release

Co-authored-by: Shaden Smith <ShadenTSmith@gmail.com>
Co-authored-by: Elton Zheng <eltonz@microsoft.com>
Co-authored-by: Reza Yazdani <reyazda@microsoft.com>
Co-authored-by: RezaYazdaniAminabadi <44502768+RezaYazdaniAminabadi@users.noreply.github.com>
Co-authored-by: Tunji Ruwase <olruwase@microsoft.com>
Co-authored-by: Shaden Smith <ShadenTSmith@gmail.com>
Co-authored-by: Shaden Smith <Shaden.Smith@microsoft.com>
Co-authored-by: Samyam Rajbhandari <samyamr@microsoft.com>
Co-authored-by: Shaden Smith <ShadenTSmith@gmail.com>
Co-authored-by: Jeff Rasley <jerasley@microsoft.com>
Co-authored-by: Samyam Rajbhandari <samyamr@microsoft.com>
Co-authored-by: Shaden Smith <ShadenTSmith@gmail.com>
Co-authored-by: Elton Zheng <eltonz@microsoft.com>
Co-authored-by: Reza Yazdani <reyazda@microsoft.com>
Co-authored-by: RezaYazdaniAminabadi <44502768+RezaYazdaniAminabadi@users.noreply.github.com>
Co-authored-by: Tunji Ruwase <olruwase@microsoft.com>
Co-authored-by: Shaden Smith <Shaden.Smith@microsoft.com>
Co-authored-by: Samyam Rajbhandari <samyamr@microsoft.com>

.clang-format

@@ -0,0 +1,155 @@
+---
+# Refer to the following link for the explanation of each params:
+#   http://releases.llvm.org/8.0.0/tools/clang/docs/ClangFormatStyleOptions.html
+Language: Cpp
+# BasedOnStyle: Google
+AccessModifierOffset: -4
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlines: Left
+AlignOperands: true
+AlignTrailingComments: true
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: true
+AllowShortCaseLabelsOnASingleLine: true
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: true
+AllowShortLoopsOnASingleLine: true
+# This is deprecated
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+BinPackArguments:  false
+BinPackParameters: false
+BraceWrapping:
+  AfterClass:            false
+  AfterControlStatement: false
+  AfterEnum:             false
+  AfterFunction:         false
+  AfterNamespace:        false
+  AfterObjCDeclaration:  false
+  AfterStruct:           false
+  AfterUnion:            false
+  AfterExternBlock:      false
+  BeforeCatch:           false
+  BeforeElse:            false
+  IndentBraces:          false
+  # disabling the below splits, else, they'll just add to the vertical length of source files!
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: WebKit
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+ColumnLimit: 100
+CommentPragmas: '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+# Kept the below 2 to be the same as `IndentWidth` to keep everything uniform
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat: false
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+ForEachMacros:
+  - foreach
+  - Q_FOREACH
+  - BOOST_FOREACH
+IncludeBlocks: Preserve
+IncludeCategories:
+  - Regex:           '^<ext/.*\.h>'
+    Priority:        2
+  - Regex:           '^<.*\.h>'
+    Priority:        1
+  - Regex:           '^<.*'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IndentCaseLabels: true
+IndentPPDirectives: None
+IndentWidth:     4
+IndentWrappedFunctionNames: false
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Never
+ObjCBlockIndentWidth: 4
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: true
+PenaltyBreakAssignment: 4
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+RawStringFormats:
+  - Language: Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+  - Language: TextProto
+    Delimiters:
+      - pb
+      - PB
+      - proto
+      - PROTO
+    EnclosingFunctions:
+      - EqualsProto
+      - EquivToProto
+      - PARSE_PARTIAL_TEXT_PROTO
+      - PARSE_TEST_PROTO
+      - PARSE_TEXT_PROTO
+      - ParseTextOrDie
+      - ParseTextProtoOrDie
+    CanonicalDelimiter: ''
+    BasedOnStyle: google
+# Enabling comment reflow causes doxygen comments to be messed up in their formats!
+ReflowComments: true
+SortIncludes: true
+SortUsingDeclarations: true
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles: false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard: Cpp11
+StatementMacros:
+  - Q_UNUSED
+  - QT_REQUIRE_VERSION
+# Be consistent with indent-width, even for people who use tab for indentation!
+TabWidth: 4
+UseTab: Never

.pre-commit-config.yaml

@@ -17,3 +17,9 @@ repos:
     hooks:
     -   id: yapf
         exclude: "examples/"
+
+-   repo: https://gitlab.com/daverona/pre-commit-cpp
+    rev: 0.6.0
+    hooks:
+    -   id: clang-format  # formatter of C/C++ code based on a style guide: LLVM, Google, Chromium, Mozilla, and WebKit available
+        args: []

basic_install_test.py

@@ -18,8 +18,8 @@
     raise err
 
 try:
-    fused_lamb = importlib.import_module('fused_lamb_cuda')
-    print('deepspeed kernels successfully installed')
+    fused_lamb = importlib.import_module('deepspeed_lamb_cuda')
+    print('deepspeed fused lamb kernels successfully installed')
 except Exception as err:
     raise err
 
@@ -28,3 +28,9 @@
     print("using old-style apex")
 except ImportError:
     print("using new-style apex")
+
+try:
+    ds_transformer = importlib.import_module('deepspeed_transformer_cuda')
+    print('deepspeed transformer kernels successfully installed')
+except Exception as err:
+    raise err