@cpp-linter/clang-tidy-win32-x64 12.0.1 → 14.0.0

package/lib/clang/{12.0.1 → 14.0.0}/include/__clang_cuda_intrinsics.h

@@ -483,4 +483,36 @@ inline __device__ unsigned __funnelshift_rc(unsigned low32, unsigned high32,
 
 #endif // !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 320
 
+#if CUDA_VERSION >= 11000
+extern "C" {
+__device__ inline size_t __nv_cvta_generic_to_global_impl(const void *__ptr) {
+  return (size_t)(void __attribute__((address_space(1))) *)__ptr;
+}
+__device__ inline size_t __nv_cvta_generic_to_shared_impl(const void *__ptr) {
+  return (size_t)(void __attribute__((address_space(3))) *)__ptr;
+}
+__device__ inline size_t __nv_cvta_generic_to_constant_impl(const void *__ptr) {
+  return (size_t)(void __attribute__((address_space(4))) *)__ptr;
+}
+__device__ inline size_t __nv_cvta_generic_to_local_impl(const void *__ptr) {
+  return (size_t)(void __attribute__((address_space(5))) *)__ptr;
+}
+__device__ inline void *__nv_cvta_global_to_generic_impl(size_t __ptr) {
+  return (void *)(void __attribute__((address_space(1))) *)__ptr;
+}
+__device__ inline void *__nv_cvta_shared_to_generic_impl(size_t __ptr) {
+  return (void *)(void __attribute__((address_space(3))) *)__ptr;
+}
+__device__ inline void *__nv_cvta_constant_to_generic_impl(size_t __ptr) {
+  return (void *)(void __attribute__((address_space(4))) *)__ptr;
+}
+__device__ inline void *__nv_cvta_local_to_generic_impl(size_t __ptr) {
+  return (void *)(void __attribute__((address_space(5))) *)__ptr;
+}
+__device__ inline uint32_t __nvvm_get_smem_pointer(void *__ptr) {
+  return __nv_cvta_generic_to_shared_impl(__ptr);
+}
+} // extern "C"
+#endif // CUDA_VERSION >= 11000
+
 #endif // defined(__CLANG_CUDA_INTRINSICS_H__)

package/lib/clang/{12.0.1 → 14.0.0}/include/__clang_cuda_libdevice_declares.h

@@ -16,6 +16,7 @@ extern "C" {
 
 #if defined(__OPENMP_NVPTX__)
 #define __DEVICE__
+#pragma omp begin assumes ext_spmd_amenable no_openmp
 #elif defined(__CUDA__)
 #define __DEVICE__ __device__
 #endif
@@ -456,6 +457,11 @@ __DEVICE__ double __nv_y1(double __a);
 __DEVICE__ float __nv_y1f(float __a);
 __DEVICE__ float __nv_ynf(int __a, float __b);
 __DEVICE__ double __nv_yn(int __a, double __b);
+
+#if defined(__OPENMP_NVPTX__)
+#pragma omp end assumes ext_spmd_amenable no_openmp
+#endif
+
 #if defined(__cplusplus)
 } // extern "C"
 #endif

package/lib/clang/{12.0.1 → 14.0.0}/include/__clang_cuda_math.h

@@ -166,6 +166,8 @@ __DEVICE__ long long llrint(double __a) { return __nv_llrint(__a); }
 __DEVICE__ long long llrintf(float __a) { return __nv_llrintf(__a); }
 __DEVICE__ long long llround(double __a) { return __nv_llround(__a); }
 __DEVICE__ long long llroundf(float __a) { return __nv_llroundf(__a); }
+__DEVICE__ double round(double __a) { return __nv_round(__a); }
+__DEVICE__ float roundf(float __a) { return __nv_roundf(__a); }
 __DEVICE__ double log(double __a) { return __nv_log(__a); }
 __DEVICE__ double log10(double __a) { return __nv_log10(__a); }
 __DEVICE__ float log10f(float __a) { return __nv_log10f(__a); }
@@ -270,8 +272,6 @@ __DEVICE__ float rnorm4df(float __a, float __b, float __c, float __d) {
 __DEVICE__ float rnormf(int __dim, const float *__t) {
   return __nv_rnormf(__dim, __t);
 }
-__DEVICE__ double round(double __a) { return __nv_round(__a); }
-__DEVICE__ float roundf(float __a) { return __nv_roundf(__a); }
 __DEVICE__ double rsqrt(double __a) { return __nv_rsqrt(__a); }
 __DEVICE__ float rsqrtf(float __a) { return __nv_rsqrtf(__a); }
 __DEVICE__ double scalbn(double __a, int __b) { return __nv_scalbn(__a, __b); }
@@ -345,4 +345,4 @@ __DEVICE__ float ynf(int __a, float __b) { return __nv_ynf(__a, __b); }
 #pragma pop_macro("__DEVICE_VOID__")
 #pragma pop_macro("__FAST_OR_SLOW")
 
-#endif // __CLANG_CUDA_DEVICE_FUNCTIONS_H__
+#endif // __CLANG_CUDA_MATH_H__

package/lib/clang/{12.0.1 → 14.0.0}/include/__clang_cuda_runtime_wrapper.h

@@ -41,6 +41,7 @@
 #include <cmath>
 #include <cstdlib>
 #include <stdlib.h>
+#include <string.h>
 #undef __CUDACC__
 
 // Preserve common macros that will be changed below by us or by CUDA
@@ -64,9 +65,9 @@
 #endif
 
 // Make largest subset of device functions available during host
-// compilation -- SM_35 for the time being.
+// compilation.
 #ifndef __CUDA_ARCH__
-#define __CUDA_ARCH__ 350
+#define __CUDA_ARCH__ 9999
 #endif
 
 #include "__clang_cuda_builtin_vars.h"
@@ -205,11 +206,6 @@ inline __host__ double __signbitd(double x) {
 #endif
 
 #if CUDA_VERSION >= 9000
-// CUDA-9.2 needs host-side memcpy for some host functions in
-// device_functions.hpp
-#if CUDA_VERSION >= 9020
-#include <string.h>
-#endif
 #include "crt/math_functions.hpp"
 #else
 #include "math_functions.hpp"
@@ -275,7 +271,38 @@ static inline __device__ void __brkpt(int __c) { __brkpt(); }
 #undef __CUDABE__
 #endif
 #include "sm_20_atomic_functions.hpp"
+// Predicate functions used in `__builtin_assume` need to have no side effect.
+// However, sm_20_intrinsics.hpp doesn't define them with neither pure nor
+// const attribute. Rename definitions from sm_20_intrinsics.hpp and re-define
+// them as pure ones.
+#pragma push_macro("__isGlobal")
+#pragma push_macro("__isShared")
+#pragma push_macro("__isConstant")
+#pragma push_macro("__isLocal")
+#define __isGlobal __ignored_cuda___isGlobal
+#define __isShared __ignored_cuda___isShared
+#define __isConstant __ignored_cuda___isConstant
+#define __isLocal __ignored_cuda___isLocal
 #include "sm_20_intrinsics.hpp"
+#pragma pop_macro("__isGlobal")
+#pragma pop_macro("__isShared")
+#pragma pop_macro("__isConstant")
+#pragma pop_macro("__isLocal")
+#pragma push_macro("__DEVICE__")
+#define __DEVICE__ static __device__ __forceinline__ __attribute__((const))
+__DEVICE__ unsigned int __isGlobal(const void *p) {
+  return __nvvm_isspacep_global(p);
+}
+__DEVICE__ unsigned int __isShared(const void *p) {
+  return __nvvm_isspacep_shared(p);
+}
+__DEVICE__ unsigned int __isConstant(const void *p) {
+  return __nvvm_isspacep_const(p);
+}
+__DEVICE__ unsigned int __isLocal(const void *p) {
+  return __nvvm_isspacep_local(p);
+}
+#pragma pop_macro("__DEVICE__")
 #include "sm_32_atomic_functions.hpp"
 
 // Don't include sm_30_intrinsics.h and sm_32_intrinsics.h.  These define the
@@ -330,6 +357,34 @@ static inline __device__ void __brkpt(int __c) { __brkpt(); }
 
 #pragma pop_macro("__host__")
 
+// __clang_cuda_texture_intrinsics.h must be included first in order to provide
+// implementation for __nv_tex_surf_handler that CUDA's headers depend on.
+// The implementation requires c++11 and only works with CUDA-9 or newer.
+#if __cplusplus >= 201103L && CUDA_VERSION >= 9000
+// clang-format off
+#include <__clang_cuda_texture_intrinsics.h>
+// clang-format on
+#else
+#if CUDA_VERSION >= 9000
+// Provide a hint that texture support needs C++11.
+template <typename T> struct __nv_tex_needs_cxx11 {
+  const static bool value = false;
+};
+template <class T>
+__host__ __device__ void __nv_tex_surf_handler(const char *name, T *ptr,
+                                               cudaTextureObject_t obj,
+                                               float x) {
+  _Static_assert(__nv_tex_needs_cxx11<T>::value,
+                 "Texture support requires C++11");
+}
+#else
+// Textures in CUDA-8 and older are not supported by clang.There's no
+// convenient way to intercept texture use in these versions, so we can't
+// produce a meaningful error. The source code that attempts to use textures
+// will continue to fail as it does now.
+#endif // CUDA_VERSION
+#endif // __cplusplus >= 201103L && CUDA_VERSION >= 9000
+#include "texture_fetch_functions.h"
 #include "texture_indirect_functions.h"
 
 // Restore state of __CUDA_ARCH__ and __THROW we had on entry.
@@ -349,9 +404,14 @@ extern "C" {
 __device__ int vprintf(const char *, const char *);
 __device__ void free(void *) __attribute((nothrow));
 __device__ void *malloc(size_t) __attribute((nothrow)) __attribute__((malloc));
+
+// __assertfail() used to have a `noreturn` attribute. Unfortunately that
+// contributed to triggering the longstanding bug in ptxas when assert was used
+// in sufficiently convoluted code. See
+// https://bugs.llvm.org/show_bug.cgi?id=27738 for the details.
 __device__ void __assertfail(const char *__message, const char *__file,
                              unsigned __line, const char *__function,
-                             size_t __charSize) __attribute__((noreturn));
+                             size_t __charSize);
 
 // In order for standard assert() macro on linux to work we need to
 // provide device-side __assert_fail()