clang-format-19.1

uxlfoundation · Oct 21, 2024 · ca37c38 · ca37c38
1 parent 0f677b4
commit ca37c38
Show file tree

Hide file tree

Showing 405 changed files with 73,086 additions and 72,570 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,8 @@
+repos:
+
+- repo: https://github.com/pre-commit/mirrors-clang-format
+  rev: v19.1.0
+  hooks:
+  - id: clang-format
+    files: \.(c|cxx|cpp|h|hxx|hpp)$
+    exclude: ^deps/
diff --git a/_clang-format b/_clang-format
@@ -21,31 +21,31 @@
 Language: Cpp
 AccessModifierOffset: -4
 AlignAfterOpenBracket: Align
-AlignConsecutiveAssignments: false
-AlignConsecutiveDeclarations: false
-AlignConsecutiveMacros: true
+AlignConsecutiveAssignments:
+  Enabled: false
+AlignConsecutiveDeclarations:
+  Enabled: false
+AlignConsecutiveMacros:
+  Enabled: true
 AlignEscapedNewlines: Left
-AlignOperands: true
-AlignTrailingComments: false
+AlignOperands: Align
+AlignTrailingComments:
+  Kind: Never
 AllowAllArgumentsOnNextLine: true
-AllowAllConstructorInitializersOnNextLine: false
 AllowAllParametersOfDeclarationOnNextLine: false
-AllowShortBlocksOnASingleLine: false
+AllowShortBlocksOnASingleLine: Never
 AllowShortCaseLabelsOnASingleLine: true
 AllowShortFunctionsOnASingleLine: Empty
 AllowShortIfStatementsOnASingleLine: Never
 AllowShortLambdasOnASingleLine: Inline
 AllowShortLoopsOnASingleLine: false
-AlwaysBreakAfterDefinitionReturnType: None
-AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: false
-AlwaysBreakTemplateDeclarations: Yes
 BinPackArguments: true
 BinPackParameters: true
 BraceWrapping:
   AfterCaseLabel: false
   AfterClass: false
-  AfterControlStatement: false
+  AfterControlStatement: Never
   AfterEnum: false
   AfterFunction: false
   AfterNamespace: false
@@ -59,46 +59,33 @@ BraceWrapping:
   SplitEmptyFunction: false
   SplitEmptyRecord: false
   SplitEmptyNamespace: false
+BreakAfterReturnType: Automatic
 BreakBeforeBinaryOperators: None
 BreakBeforeBraces: Custom
 BreakBeforeTernaryOperators: true
 BreakConstructorInitializers: BeforeColon
 BreakInheritanceList: BeforeColon
 BreakStringLiterals: false
+BreakTemplateDeclarations: Yes
 ColumnLimit: 100
-CommentPragmas: '^ IWYU pragma:'
 CompactNamespaces: false
-ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 8
 ContinuationIndentWidth: 4
 Cpp11BracedListStyle: false
-DerivePointerAlignment: true
+DerivePointerAlignment: false
 DisableFormat: 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
-KeepEmptyLinesAtTheStartOfBlocks: false
-MacroBlockBegin: ''
-MacroBlockEnd:   ''
+KeepEmptyLines:
+  AtEndOfFile: false
+  AtStartOfBlock: false
+  AtStartOfFile: false
 MaxEmptyLinesToKeep: 1
 NamespaceIndentation: None
+PackConstructorInitializers: CurrentLine
 PenaltyBreakAssignment: 2
 PenaltyBreakBeforeFirstCallParameter: 1
 PenaltyBreakComment: 300
@@ -108,57 +95,24 @@ PenaltyBreakTemplateDeclaration: 10
 PenaltyExcessCharacter: 1000000
 PenaltyReturnTypeOnItsOwnLine: 200
 PointerAlignment: Left
-RawStringFormats:
-  - Language: Cpp
-    Delimiters:
-      - cc
-      - CC
-      - cpp
-      - Cpp
-      - CPP
-      - 'c++'
-      - 'C++'
-    CanonicalDelimiter: ''
-    BasedOnStyle: google
-  - 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
 ReflowComments: false
-SortIncludes: false
-SortUsingDeclarations: false
+SortIncludes: Never
+SortUsingDeclarations: Never
 SpaceAfterCStyleCast: false
 SpaceAfterLogicalNot: false
 SpaceAfterTemplateKeyword: true
 SpaceBeforeAssignmentOperators: true
+SpaceBeforeCaseColon: false
 SpaceBeforeCpp11BracedList: false
 SpaceBeforeCtorInitializerColon: true
 SpaceBeforeInheritanceColon: true
 SpaceBeforeParens: ControlStatements
 SpaceBeforeRangeBasedForLoopColon: true
-SpaceInEmptyParentheses: false
 SpacesBeforeTrailingComments: 1
-SpacesInAngles: false
+SpacesInAngles: Never
 SpacesInContainerLiterals: false
-SpacesInCStyleCastParentheses: false
-SpacesInParentheses: false
+SpacesInParens: Never
 SpacesInSquareBrackets: false
-Standard: Cpp11
-StatementMacros:
-  - Q_UNUSED
-  - QT_REQUIRE_VERSION
-TabWidth: 1
+Standard: c++17
 UseTab: Never
 ...
diff --git a/examples/blas/compile_time_dispatching/level3/gemm_usm_mklcpu_cublas.cpp b/examples/blas/compile_time_dispatching/level3/gemm_usm_mklcpu_cublas.cpp
@@ -61,7 +61,7 @@
 //
 // is performed and finally the results are post processed.
 //
-void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev) {
+void run_gemm_example(const sycl::device& cpu_dev, const sycl::device& gpu_dev) {
     //
     // Initialize data for Gemm
     //
@@ -89,11 +89,11 @@ void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev)
 
     // Catch asynchronous exceptions for CPU and GPU
     auto cpu_exception_handler = [](sycl::exception_list exceptions) {
-        for (std::exception_ptr const &e : exceptions) {
+        for (std::exception_ptr const& e : exceptions) {
             try {
                 std::rethrow_exception(e);
             }
-            catch (sycl::exception const &e) {
+            catch (sycl::exception const& e) {
                 std::cerr << "Caught asynchronous SYCL exception on CPU device during GEMM:"
                           << std::endl;
                 std::cerr << "\t" << e.what() << std::endl;
@@ -102,11 +102,11 @@ void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev)
         std::exit(2);
     };
     auto gpu_exception_handler = [](sycl::exception_list exceptions) {
-        for (std::exception_ptr const &e : exceptions) {
+        for (std::exception_ptr const& e : exceptions) {
             try {
                 std::rethrow_exception(e);
             }
-            catch (sycl::exception const &e) {
+            catch (sycl::exception const& e) {
                 std::cerr << "Caught asynchronous SYCL exception on GPU device during GEMM:"
                           << std::endl;
                 std::cerr << "\t" << e.what() << std::endl;
@@ -141,9 +141,9 @@ void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev)
     sycl::context cpu_cxt = cpu_queue.get_context();
 
     // allocate on CPU device and copy data from host to SYCL CPU device
-    float *cpu_A = sycl::malloc_device<float>(sizea * sizeof(float), cpu_queue);
-    float *cpu_B = sycl::malloc_device<float>(sizeb * sizeof(float), cpu_queue);
-    float *cpu_C = sycl::malloc_device<float>(sizec * sizeof(float), cpu_queue);
+    float* cpu_A = sycl::malloc_device<float>(sizea * sizeof(float), cpu_queue);
+    float* cpu_B = sycl::malloc_device<float>(sizeb * sizeof(float), cpu_queue);
+    float* cpu_C = sycl::malloc_device<float>(sizec * sizeof(float), cpu_queue);
     if (!cpu_A || !cpu_B || !cpu_C) {
         throw std::runtime_error("Failed to allocate USM memory.");
     }
@@ -159,9 +159,9 @@ void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev)
     sycl::context gpu_cxt = gpu_queue.get_context();
 
     // allocate on GPU device and copy data from host to SYCL GPU device
-    float *gpu_A = sycl::malloc_device<float>(sizea * sizeof(float), gpu_queue);
-    float *gpu_B = sycl::malloc_device<float>(sizeb * sizeof(float), gpu_queue);
-    float *gpu_C = sycl::malloc_device<float>(sizec * sizeof(float), gpu_queue);
+    float* gpu_A = sycl::malloc_device<float>(sizea * sizeof(float), gpu_queue);
+    float* gpu_B = sycl::malloc_device<float>(sizeb * sizeof(float), gpu_queue);
+    float* gpu_C = sycl::malloc_device<float>(sizec * sizeof(float), gpu_queue);
     if (!gpu_A || !gpu_B || !gpu_C) {
         throw std::runtime_error("Failed to allocate USM memory.");
     }
@@ -174,11 +174,11 @@ void run_gemm_example(const sycl::device &cpu_dev, const sycl::device &gpu_dev)
     //
     // add oneapi::math::blas::gemm to execution queue
     cpu_gemm_done = oneapi::math::blas::column_major::gemm(
-        oneapi::math::backend_selector<oneapi::math::backend::mklcpu>{ cpu_queue }, transA, transB, m,
-        n, k, alpha, cpu_A, ldA, cpu_B, ldB, beta, cpu_C, ldC);
+        oneapi::math::backend_selector<oneapi::math::backend::mklcpu>{ cpu_queue }, transA, transB,
+        m, n, k, alpha, cpu_A, ldA, cpu_B, ldB, beta, cpu_C, ldC);
     gpu_gemm_done = oneapi::math::blas::column_major::gemm(
-        oneapi::math::backend_selector<oneapi::math::backend::cublas>{ gpu_queue }, transA, transB, m,
-        n, k, alpha, gpu_A, ldA, gpu_B, ldB, beta, gpu_C, ldC);
+        oneapi::math::backend_selector<oneapi::math::backend::cublas>{ gpu_queue }, transA, transB,
+        m, n, k, alpha, gpu_A, ldA, gpu_B, ldB, beta, gpu_C, ldC);
 
     // Wait until calculations are done
     cpu_gemm_done.wait_and_throw();
@@ -260,7 +260,7 @@ void print_example_banner() {
 //
 // Main entry point for example.
 //
-int main(int argc, char **argv) {
+int main(int argc, char** argv) {
     print_example_banner();
 
     try {
@@ -279,13 +279,13 @@ int main(int argc, char **argv) {
         run_gemm_example(cpu_dev, gpu_dev);
         std::cout << "BLAS GEMM USM example ran OK on MKLCPU and CUBLAS" << std::endl;
     }
-    catch (sycl::exception const &e) {
+    catch (sycl::exception const& e) {
         std::cerr << "Caught synchronous SYCL exception during GEMM:" << std::endl;
         std::cerr << "\t" << e.what() << std::endl;
         std::cerr << "\tSYCL error code: " << e.code().value() << std::endl;
         return 1;
     }
-    catch (std::exception const &e) {
+    catch (std::exception const& e) {
         std::cerr << "Caught std::exception during GEMM:";
         std::cerr << "\t" << e.what() << std::endl;
         return 1;

diff --git a/examples/blas/run_time_dispatching/level3/gemm_usm.cpp b/examples/blas/run_time_dispatching/level3/gemm_usm.cpp
@@ -136,7 +136,7 @@ void run_gemm_example(const sycl::device& dev) {
     //
     // add oneapi::math::blas::gemm to execution queue
     gemm_done = oneapi::math::blas::column_major::gemm(main_queue, transA, transB, m, n, k, alpha,
-                                                      dev_A, ldA, dev_B, ldB, beta, dev_C, ldC);
+                                                       dev_A, ldA, dev_B, ldB, beta, dev_C, ldC);
 
     // Wait until calculations are done
     main_queue.wait_and_throw();

diff --git a/examples/dft/compile_time_dispatching/complex_fwd_usm_mklcpu_cufft.cpp b/examples/dft/compile_time_dispatching/complex_fwd_usm_mklcpu_cufft.cpp
@@ -83,7 +83,7 @@ void run_example(const sycl::device& cpu_device, const sycl::device& gpu_device)
     // enabling
     // 1. create descriptors
     oneapi::math::dft::descriptor<oneapi::math::dft::precision::SINGLE,
-                                 oneapi::math::dft::domain::COMPLEX>
+                                  oneapi::math::dft::domain::COMPLEX>
         desc(static_cast<std::int64_t>(N));
 
     // 2. variadic set_value

diff --git a/examples/dft/run_time_dispatching/real_fwd_usm.cpp b/examples/dft/run_time_dispatching/real_fwd_usm.cpp
@@ -54,7 +54,7 @@ void run_example(const sycl::device& dev) {
 
     // 1. create descriptors
     oneapi::math::dft::descriptor<oneapi::math::dft::precision::SINGLE,
-                                 oneapi::math::dft::domain::REAL>
+                                  oneapi::math::dft::domain::REAL>
         desc(static_cast<std::int64_t>(N));
 
     // 2. variadic set_value

diff --git a/examples/include/example_helper.hpp b/examples/include/example_helper.hpp
@@ -88,7 +88,7 @@ fp rand_scalar() {
 }
 
 template <typename vec>
-void rand_matrix(vec &M, oneapi::math::transpose trans, int m, int n, int ld) {
+void rand_matrix(vec& M, oneapi::math::transpose trans, int m, int n, int ld) {
     using fp = typename vec::value_type;
 
     if (trans == oneapi::math::transpose::nontrans) {
@@ -104,7 +104,7 @@ void rand_matrix(vec &M, oneapi::math::transpose trans, int m, int n, int ld) {
 }
 
 template <typename fp, typename intType>
-intType generate_sparse_matrix(const intType nx, intType *ia, intType *ja, fp *a,
+intType generate_sparse_matrix(const intType nx, intType* ia, intType* ja, fp* a,
                                const intType index = 0) {
     intType nz = nx, ny = nx;
     intType nnz = 0;
@@ -172,7 +172,7 @@ bool check_result(fp res, fp ref, intType nFlops, intType index) {
 }
 
 template <typename T>
-void free_vec(std::vector<T *> &ptr_vec, sycl::queue queue) {
+void free_vec(std::vector<T*>& ptr_vec, sycl::queue queue) {
     for (auto ptr : ptr_vec) {
         sycl::free(ptr, queue);
     }

diff --git a/examples/lapack/compile_time_dispatching/getrs_usm_mklcpu_cusolver.cpp b/examples/lapack/compile_time_dispatching/getrs_usm_mklcpu_cusolver.cpp
@@ -178,8 +178,8 @@ void run_getrs_example(const sycl::device& cpu_device, const sycl::device& gpu_d
     std::int64_t gpu_getrf_scratchpad_size = oneapi::math::lapack::getrf_scratchpad_size<float>(
         oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, m, n, lda);
     std::int64_t gpu_getrs_scratchpad_size = oneapi::math::lapack::getrs_scratchpad_size<float>(
-        oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, trans, n, nrhs,
-        lda, ldb);
+        oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, trans, n,
+        nrhs, lda, ldb);
     float* gpu_getrf_scratchpad = sycl::malloc_device<float>(
         gpu_getrf_scratchpad_size * sizeof(float), gpu_device, gpu_context);
     float* gpu_getrs_scratchpad = sycl::malloc_device<float>(
@@ -197,8 +197,8 @@ void run_getrs_example(const sycl::device& cpu_device, const sycl::device& gpu_d
     //
 
     cpu_getrf_done = oneapi::math::lapack::getrf(
-        oneapi::math::backend_selector<oneapi::math::backend::mklcpu>{ cpu_queue }, m, n, cpu_A, lda,
-        cpu_ipiv, cpu_getrf_scratchpad, cpu_getrf_scratchpad_size);
+        oneapi::math::backend_selector<oneapi::math::backend::mklcpu>{ cpu_queue }, m, n, cpu_A,
+        lda, cpu_ipiv, cpu_getrf_scratchpad, cpu_getrf_scratchpad_size);
     cpu_getrs_done = oneapi::math::lapack::getrs(
         oneapi::math::backend_selector<oneapi::math::backend::mklcpu>{ cpu_queue }, trans, n, nrhs,
         cpu_A, lda, cpu_ipiv, cpu_B, ldb, cpu_getrs_scratchpad, cpu_getrs_scratchpad_size,
@@ -207,8 +207,8 @@ void run_getrs_example(const sycl::device& cpu_device, const sycl::device& gpu_d
         oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, m, n, gpu_A,
         lda, gpu_ipiv, gpu_getrf_scratchpad, gpu_getrf_scratchpad_size);
     gpu_getrs_done = oneapi::math::lapack::getrs(
-        oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, trans, n, nrhs,
-        gpu_A, lda, gpu_ipiv, gpu_B, ldb, gpu_getrs_scratchpad, gpu_getrs_scratchpad_size,
+        oneapi::math::backend_selector<oneapi::math::backend::cusolver>{ gpu_queue }, trans, n,
+        nrhs, gpu_A, lda, gpu_ipiv, gpu_B, ldb, gpu_getrs_scratchpad, gpu_getrs_scratchpad_size,
         { gpu_getrf_done });
 
     // Wait until calculations are done

diff --git a/examples/lapack/run_time_dispatching/getrs_usm.cpp b/examples/lapack/run_time_dispatching/getrs_usm.cpp
@@ -146,10 +146,10 @@ void run_getrs_example(const sycl::device& device) {
 
     // Execute on device
     getrf_done = oneapi::math::lapack::getrf(queue, m, n, dev_A, lda, dev_ipiv, getrf_scratchpad,
-                                            getrf_scratchpad_size);
+                                             getrf_scratchpad_size);
     getrs_done =
         oneapi::math::lapack::getrs(queue, trans, n, nrhs, dev_A, lda, dev_ipiv, dev_B, ldb,
-                                   getrs_scratchpad, getrs_scratchpad_size, { getrf_done });
+                                    getrs_scratchpad, getrs_scratchpad_size, { getrf_done });
 
     // Wait until calculations are done
     queue.wait_and_throw();