cudnn prerelease_2:

Improvements over prerelease 1:
[Feature] Added missing python bindings for several pointwise ops.

[Feature] SDPA flash attention feature parity with the backend API.

[Bug fixes] Shape inferencing fixes for dgrad, wgrad where the output
dimension cannot be computed deterministically.

Under investigation and development:
- We are still working on additional features for SDPA back prop.
- CPU overhead when using the python bindings are under investigation.
- Better error messages and logging

Miscelleanous updates to the v0.x API:

[Bug fix] Some tests were failing on Ampere GPUs because no plans with 0
size were available. This has been fixed.

[Bug fix] Median of three sampling was incorrectly sorting the results,
when cudnnFind was used. This has been fixed.

[Feature] Layer Norm API has been added. And can be used with the v0.x
API.

Note: This pre-release is experimental

Author: Anerudhan

.clang-format

@@ -0,0 +1,94 @@
+---
+Language:        Cpp
+# BasedOnStyle:  Google
+AccessModifierOffset: -1
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: true
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlinesLeft: true
+AlignOperands:   true
+AlignTrailingComments: true
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: true
+AllowShortLoopsOnASingleLine: true
+AlwaysBreakAfterDefinitionReturnType: All
+AlwaysBreakAfterReturnType: All
+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
+ColumnLimit:     120
+CommentPragmas:  '^ IWYU pragma:'
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: true
+DisableFormat:   false
+ExperimentalAutoDetectBinPacking: false
+ForEachMacros:   [ foreach, Q_FOREACH, BOOST_FOREACH ]
+IncludeCategories: 
+  - Regex:           '^<.*\.h>'
+    Priority:        1
+  - Regex:           '^<.*'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IndentCaseLabels: true
+IndentWidth:     4
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: false
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+ReflowComments:  true
+SortIncludes:    false
+SpaceAfterCStyleCast: false
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeParens: ControlStatements
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles:  false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard:        Auto
+TabWidth:        4
+UseTab:          Never
+---
+Language: Json
+# Don't format .json files.
+DisableFormat: true
+...
+

CMakeLists.txt

@@ -1,8 +1,17 @@
 cmake_minimum_required(VERSION 3.17)
 
-project(cudnn_frontend VERSION 0.9)
+project(cudnn_frontend VERSION 1.0.0)
 
 option(CUDNN_FRONTEND_BUILD_SAMPLES "Defines if samples are built or not." ON)
+option(CUDNN_FRONTEND_BUILD_UNIT_TESTS "Defines if unittests are built or not." OFF)
+
+if(MSVC OR MSYS OR MINGW)
+    option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." OFF)
+    add_compile_options(/W4 /WX)
+else()
+    option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." ON)
+    add_compile_options(-Wall -Wextra -Wpedantic -Werror -Wno-error=attributes -Wno-attributes -Wno-error=unused-function -Wno-unused-function)
+endif()
 
 add_library(cudnn_frontend INTERFACE)
 
@@ -12,8 +21,16 @@ target_include_directories(
     $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>
 )
 
-target_compile_features(cudnn_frontend INTERFACE cxx_std_11)
+target_compile_features(cudnn_frontend INTERFACE cxx_std_17)
+
+if (CUDNN_FRONTEND_BUILD_SAMPLES)
+    add_subdirectory(samples)
+endif()
+
+if (CUDNN_FRONTEND_BUILD_UNIT_TESTS)
+    add_subdirectory(test)
+endif()
 
-if (${CUDNN_FRONTEND_BUILD_SAMPLES})
-add_subdirectory(samples)
+if (CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS)
+    add_subdirectory(python_bindings)
 endif()