Merge branch 'main' into multi_gpu_CI_jobs_for_libcudacxx

Author: pciolkosz

.clang-tidy

@@ -29,6 +29,24 @@ Checks:
   - '-modernize-return-braced-init-list'
   - '-modernize-use-auto'
   - 'clang-diagnostic-*'
+  - 'bugprone-*'
+  - '-bugprone-narrowing-conversions'
+  - '-bugprone-misplaced-widening-cast'
+  - '-bugprone-exception-escape'
+  - '-bugprone-crtp-constructor-accessibility'
+  - '-bugprone-forwarding-reference-overload'
+  - '-bugprone-branch-clone'
+  - '-bugprone-use-after-move'
+  - '-bugprone-undefined-memory-manipulation'
+  - '-bugprone-unchecked-optional-access'
+  - '-bugprone-casting-through-void'
+  - '-bugprone-integer-division'
+  - '-bugprone-move-forwarding-reference'
+  - '-bugprone-pointer-arithmetic-on-polymorphic-object'
+  - '-bugprone-argument-comment'
+  # This is just noise
+  - '-bugprone-signed-char-misuse'
+  - '-bugprone-multi-level-implicit-pointer-conversion'
   # END REMOVE ME
   # TODO(jfaibussowit):
   #
@@ -245,7 +263,6 @@ CheckOptions:
   readability-simplify-boolean-expr.ChainedConditionalReturn: 'true'
   readability-simplify-boolean-expr.ChainedConditionalAssignment: 'true'
   bugprone-dangling-handle.HandleClasses: '::cuda::std::span;::cuda::std::mdspan'
-  bugprone-misplaced-widening-cast.CheckImplicitCasts: 'true'
   bugprone-unused-return-value.AllowCastToVoid: 'true'
   readability-enum-initial-value.AllowExplicitZeroFirstInitialValue: 'false'
   readability-enum-initial-value.AllowExplicitSequentialInitialValues: 'false'
@@ -297,4 +314,5 @@ CheckOptions:
   bugprone-reserved-identifier.AllowedIdentifiers: '^_CCCL.*'
   performance-enum-size.EnumIgnoreList: '::cuda::std::.*'
   performance-unnecessary-value-param.AllowedTypes: '.*(_ref(erence)?|_ptr|pointer|(_)?[Ii]t(erator)?|IteratorT|__half(2)?|(__nv_bfloat.*)|_view)$'
+  bugprone-exception-escape.CheckMain: false
 ...

c/parallel.v2/include/cccl/c/binary_search.h

@@ -26,8 +26,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_binary_search_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler; // hostjit::JITCompiler*
   void* binary_search_fn; // int(*)(void*, ull, void*, ull, void*, void*, void*)
 } cccl_device_binary_search_build_result_t;

c/parallel.v2/include/cccl/c/for.h

@@ -26,8 +26,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_for_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler; // hostjit::JITCompiler*
   void* for_fn; // int(*)(void*, unsigned long long, void*)
 } cccl_device_for_build_result_t;

c/parallel.v2/include/cccl/c/histogram.h

@@ -27,8 +27,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_histogram_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler;
   void* histogram_fn;
   cccl_type_info counter_type;

c/parallel.v2/include/cccl/c/merge_sort.h

@@ -26,8 +26,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_merge_sort_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler;
   void* sort_fn;
   // 1 if the build compiled SortKeysCopy (no items), 0 if SortPairsCopy. The

c/parallel.v2/include/cccl/c/radix_sort.h

@@ -27,8 +27,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_radix_sort_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler; /* Owns both wrappers below — one TU, one cubin */
   void* sort_fn; /* Wrapper around CUB's copy-overload (selector always 0) */
   void* sort_fn_overwrite; /* Wrapper around CUB's DoubleBuffer overload; reports selector */

c/parallel.v2/include/cccl/c/reduce.h

@@ -26,8 +26,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_reduce_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler; // hostjit::JITCompiler*
   void* reduce_fn; // int(*)(void*, size_t*, void*, void*, unsigned long long, void*, void*, void*) — trailing void* is
                    // the CUstream

c/parallel.v2/include/cccl/c/scan.h

@@ -27,8 +27,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_scan_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler;
   void* scan_fn;
   bool force_inclusive;

c/parallel.v2/include/cccl/c/segmented_reduce.h

@@ -26,8 +26,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_segmented_reduce_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler;
   void* segmented_reduce_fn;
 } cccl_device_segmented_reduce_build_result_t;

c/parallel.v2/include/cccl/c/segmented_sort.h

@@ -27,8 +27,8 @@ CCCL_C_EXTERN_C_BEGIN
 typedef struct cccl_device_segmented_sort_build_result_t
 {
   int cc;
-  void* cubin;
-  size_t cubin_size;
+  void* payload;
+  size_t payload_size;
   void* jit_compiler; /* Owns both wrappers below — one TU, one cubin */
   void* sort_fn; /* Wrapper around CUB's copy-overload (selector always 0) */
   void* sort_fn_overwrite; /* Wrapper around CUB's DoubleBuffer overload; reports selector */