@cpp-linter/clang-tidy-win32-x64 16.0.3 → 17.0.6

package/lib/clang/{16 → 17}/include/__clang_hip_math.h

@@ -182,10 +182,10 @@ __DEVICE__
 float cbrtf(float __x) { return __ocml_cbrt_f32(__x); }
 
 __DEVICE__
-float ceilf(float __x) { return __ocml_ceil_f32(__x); }
+float ceilf(float __x) { return __builtin_ceilf(__x); }
 
 __DEVICE__
-float copysignf(float __x, float __y) { return __ocml_copysign_f32(__x, __y); }
+float copysignf(float __x, float __y) { return __builtin_copysignf(__x, __y); }
 
 __DEVICE__
 float cosf(float __x) { return __ocml_cos_f32(__x); }
@@ -221,10 +221,10 @@ __DEVICE__
 float exp10f(float __x) { return __ocml_exp10_f32(__x); }
 
 __DEVICE__
-float exp2f(float __x) { return __ocml_exp2_f32(__x); }
+float exp2f(float __x) { return __builtin_exp2f(__x); }
 
 __DEVICE__
-float expf(float __x) { return __ocml_exp_f32(__x); }
+float expf(float __x) { return __builtin_expf(__x); }
 
 __DEVICE__
 float expm1f(float __x) { return __ocml_expm1_f32(__x); }
@@ -239,33 +239,25 @@ __DEVICE__
 float fdividef(float __x, float __y) { return __x / __y; }
 
 __DEVICE__
-float floorf(float __x) { return __ocml_floor_f32(__x); }
+float floorf(float __x) { return __builtin_floorf(__x); }
 
 __DEVICE__
 float fmaf(float __x, float __y, float __z) {
-  return __ocml_fma_f32(__x, __y, __z);
+  return __builtin_fmaf(__x, __y, __z);
 }
 
 __DEVICE__
-float fmaxf(float __x, float __y) { return __ocml_fmax_f32(__x, __y); }
+float fmaxf(float __x, float __y) { return __builtin_fmaxf(__x, __y); }
 
 __DEVICE__
-float fminf(float __x, float __y) { return __ocml_fmin_f32(__x, __y); }
+float fminf(float __x, float __y) { return __builtin_fminf(__x, __y); }
 
 __DEVICE__
 float fmodf(float __x, float __y) { return __ocml_fmod_f32(__x, __y); }
 
 __DEVICE__
 float frexpf(float __x, int *__nptr) {
-  int __tmp;
-#ifdef __OPENMP_AMDGCN__
-#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
-#endif
-  float __r =
-      __ocml_frexp_f32(__x, (__attribute__((address_space(5))) int *)&__tmp);
-  *__nptr = __tmp;
-
-  return __r;
+  return __builtin_frexpf(__x, __nptr);
 }
 
 __DEVICE__
@@ -275,13 +267,13 @@ __DEVICE__
 int ilogbf(float __x) { return __ocml_ilogb_f32(__x); }
 
 __DEVICE__
-__RETURN_TYPE __finitef(float __x) { return __ocml_isfinite_f32(__x); }
+__RETURN_TYPE __finitef(float __x) { return __builtin_isfinite(__x); }
 
 __DEVICE__
-__RETURN_TYPE __isinff(float __x) { return __ocml_isinf_f32(__x); }
+__RETURN_TYPE __isinff(float __x) { return __builtin_isinf(__x); }
 
 __DEVICE__
-__RETURN_TYPE __isnanf(float __x) { return __ocml_isnan_f32(__x); }
+__RETURN_TYPE __isnanf(float __x) { return __builtin_isnan(__x); }
 
 __DEVICE__
 float j0f(float __x) { return __ocml_j0_f32(__x); }
@@ -311,37 +303,37 @@ float jnf(int __n, float __x) { // TODO: we could use Ahmes multiplication
 }
 
 __DEVICE__
-float ldexpf(float __x, int __e) { return __ocml_ldexp_f32(__x, __e); }
+float ldexpf(float __x, int __e) { return __builtin_amdgcn_ldexpf(__x, __e); }
 
 __DEVICE__
 float lgammaf(float __x) { return __ocml_lgamma_f32(__x); }
 
 __DEVICE__
-long long int llrintf(float __x) { return __ocml_rint_f32(__x); }
+long long int llrintf(float __x) { return __builtin_rintf(__x); }
 
 __DEVICE__
-long long int llroundf(float __x) { return __ocml_round_f32(__x); }
+long long int llroundf(float __x) { return __builtin_roundf(__x); }
 
 __DEVICE__
-float log10f(float __x) { return __ocml_log10_f32(__x); }
+float log10f(float __x) { return __builtin_log10f(__x); }
 
 __DEVICE__
 float log1pf(float __x) { return __ocml_log1p_f32(__x); }
 
 __DEVICE__
-float log2f(float __x) { return __ocml_log2_f32(__x); }
+float log2f(float __x) { return __builtin_log2f(__x); }
 
 __DEVICE__
 float logbf(float __x) { return __ocml_logb_f32(__x); }
 
 __DEVICE__
-float logf(float __x) { return __ocml_log_f32(__x); }
+float logf(float __x) { return __builtin_logf(__x); }
 
 __DEVICE__
-long int lrintf(float __x) { return __ocml_rint_f32(__x); }
+long int lrintf(float __x) { return __builtin_rintf(__x); }
 
 __DEVICE__
-long int lroundf(float __x) { return __ocml_round_f32(__x); }
+long int lroundf(float __x) { return __builtin_roundf(__x); }
 
 __DEVICE__
 float modff(float __x, float *__iptr) {
@@ -377,7 +369,7 @@ float nanf(const char *__tagp __attribute__((nonnull))) {
 }
 
 __DEVICE__
-float nearbyintf(float __x) { return __ocml_nearbyint_f32(__x); }
+float nearbyintf(float __x) { return __builtin_nearbyintf(__x); }
 
 __DEVICE__
 float nextafterf(float __x, float __y) {
@@ -443,7 +435,7 @@ __DEVICE__
 float rhypotf(float __x, float __y) { return __ocml_rhypot_f32(__x, __y); }
 
 __DEVICE__
-float rintf(float __x) { return __ocml_rint_f32(__x); }
+float rintf(float __x) { return __builtin_rintf(__x); }
 
 __DEVICE__
 float rnorm3df(float __x, float __y, float __z) {
@@ -468,22 +460,22 @@ float rnormf(int __dim,
 }
 
 __DEVICE__
-float roundf(float __x) { return __ocml_round_f32(__x); }
+float roundf(float __x) { return __builtin_roundf(__x); }
 
 __DEVICE__
 float rsqrtf(float __x) { return __ocml_rsqrt_f32(__x); }
 
 __DEVICE__
 float scalblnf(float __x, long int __n) {
-  return (__n < INT_MAX) ? __ocml_scalbn_f32(__x, __n)
+  return (__n < INT_MAX) ? __builtin_amdgcn_ldexpf(__x, __n)
                          : __ocml_scalb_f32(__x, __n);
 }
 
 __DEVICE__
-float scalbnf(float __x, int __n) { return __ocml_scalbn_f32(__x, __n); }
+float scalbnf(float __x, int __n) { return __builtin_amdgcn_ldexpf(__x, __n); }
 
 __DEVICE__
-__RETURN_TYPE __signbitf(float __x) { return __ocml_signbit_f32(__x); }
+__RETURN_TYPE __signbitf(float __x) { return __builtin_signbitf(__x); }
 
 __DEVICE__
 void sincosf(float __x, float *__sinptr, float *__cosptr) {
@@ -529,7 +521,7 @@ __DEVICE__
 float tgammaf(float __x) { return __ocml_tgamma_f32(__x); }
 
 __DEVICE__
-float truncf(float __x) { return __ocml_trunc_f32(__x); }
+float truncf(float __x) { return __builtin_truncf(__x); }
 
 __DEVICE__
 float y0f(float __x) { return __ocml_y0_f32(__x); }
@@ -621,7 +613,7 @@ float __fmaf_rz(float __x, float __y, float __z) {
 #else
 __DEVICE__
 float __fmaf_rn(float __x, float __y, float __z) {
-  return __ocml_fma_f32(__x, __y, __z);
+  return __builtin_fmaf(__x, __y, __z);
 }
 #endif
 
@@ -654,7 +646,7 @@ float __frcp_rn(float __x) { return 1.0f / __x; }
 #endif
 
 __DEVICE__
-float __frsqrt_rn(float __x) { return __llvm_amdgcn_rsq_f32(__x); }
+float __frsqrt_rn(float __x) { return __builtin_amdgcn_rsqf(__x); }
 
 #if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
@@ -739,11 +731,11 @@ __DEVICE__
 double cbrt(double __x) { return __ocml_cbrt_f64(__x); }
 
 __DEVICE__
-double ceil(double __x) { return __ocml_ceil_f64(__x); }
+double ceil(double __x) { return __builtin_ceil(__x); }
 
 __DEVICE__
 double copysign(double __x, double __y) {
-  return __ocml_copysign_f64(__x, __y);
+  return __builtin_copysign(__x, __y);
 }
 
 __DEVICE__
@@ -795,32 +787,25 @@ __DEVICE__
 double fdim(double __x, double __y) { return __ocml_fdim_f64(__x, __y); }
 
 __DEVICE__
-double floor(double __x) { return __ocml_floor_f64(__x); }
+double floor(double __x) { return __builtin_floor(__x); }
 
 __DEVICE__
 double fma(double __x, double __y, double __z) {
-  return __ocml_fma_f64(__x, __y, __z);
+  return __builtin_fma(__x, __y, __z);
 }
 
 __DEVICE__
-double fmax(double __x, double __y) { return __ocml_fmax_f64(__x, __y); }
+double fmax(double __x, double __y) { return __builtin_fmax(__x, __y); }
 
 __DEVICE__
-double fmin(double __x, double __y) { return __ocml_fmin_f64(__x, __y); }
+double fmin(double __x, double __y) { return __builtin_fmin(__x, __y); }
 
 __DEVICE__
 double fmod(double __x, double __y) { return __ocml_fmod_f64(__x, __y); }
 
 __DEVICE__
 double frexp(double __x, int *__nptr) {
-  int __tmp;
-#ifdef __OPENMP_AMDGCN__
-#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
-#endif
-  double __r =
-      __ocml_frexp_f64(__x, (__attribute__((address_space(5))) int *)&__tmp);
-  *__nptr = __tmp;
-  return __r;
+  return __builtin_frexp(__x, __nptr);
 }
 
 __DEVICE__
@@ -830,13 +815,13 @@ __DEVICE__
 int ilogb(double __x) { return __ocml_ilogb_f64(__x); }
 
 __DEVICE__
-__RETURN_TYPE __finite(double __x) { return __ocml_isfinite_f64(__x); }
+__RETURN_TYPE __finite(double __x) { return __builtin_isfinite(__x); }
 
 __DEVICE__
-__RETURN_TYPE __isinf(double __x) { return __ocml_isinf_f64(__x); }
+__RETURN_TYPE __isinf(double __x) { return __builtin_isinf(__x); }
 
 __DEVICE__
-__RETURN_TYPE __isnan(double __x) { return __ocml_isnan_f64(__x); }
+__RETURN_TYPE __isnan(double __x) { return __builtin_isnan(__x); }
 
 __DEVICE__
 double j0(double __x) { return __ocml_j0_f64(__x); }
@@ -866,16 +851,16 @@ double jn(int __n, double __x) { // TODO: we could use Ahmes multiplication
 }
 
 __DEVICE__
-double ldexp(double __x, int __e) { return __ocml_ldexp_f64(__x, __e); }
+double ldexp(double __x, int __e) { return __builtin_amdgcn_ldexp(__x, __e); }
 
 __DEVICE__
 double lgamma(double __x) { return __ocml_lgamma_f64(__x); }
 
 __DEVICE__
-long long int llrint(double __x) { return __ocml_rint_f64(__x); }
+long long int llrint(double __x) { return __builtin_rint(__x); }
 
 __DEVICE__
-long long int llround(double __x) { return __ocml_round_f64(__x); }
+long long int llround(double __x) { return __builtin_round(__x); }
 
 __DEVICE__
 double log(double __x) { return __ocml_log_f64(__x); }
@@ -893,10 +878,10 @@ __DEVICE__
 double logb(double __x) { return __ocml_logb_f64(__x); }
 
 __DEVICE__
-long int lrint(double __x) { return __ocml_rint_f64(__x); }
+long int lrint(double __x) { return __builtin_rint(__x); }
 
 __DEVICE__
-long int lround(double __x) { return __ocml_round_f64(__x); }
+long int lround(double __x) { return __builtin_round(__x); }
 
 __DEVICE__
 double modf(double __x, double *__iptr) {
@@ -940,7 +925,7 @@ double nan(const char *__tagp) {
 }
 
 __DEVICE__
-double nearbyint(double __x) { return __ocml_nearbyint_f64(__x); }
+double nearbyint(double __x) { return __builtin_nearbyint(__x); }
 
 __DEVICE__
 double nextafter(double __x, double __y) {
@@ -1006,7 +991,7 @@ __DEVICE__
 double rhypot(double __x, double __y) { return __ocml_rhypot_f64(__x, __y); }
 
 __DEVICE__
-double rint(double __x) { return __ocml_rint_f64(__x); }
+double rint(double __x) { return __builtin_rint(__x); }
 
 __DEVICE__
 double rnorm(int __dim,
@@ -1031,21 +1016,21 @@ double rnorm4d(double __x, double __y, double __z, double __w) {
 }
 
 __DEVICE__
-double round(double __x) { return __ocml_round_f64(__x); }
+double round(double __x) { return __builtin_round(__x); }
 
 __DEVICE__
 double rsqrt(double __x) { return __ocml_rsqrt_f64(__x); }
 
 __DEVICE__
 double scalbln(double __x, long int __n) {
-  return (__n < INT_MAX) ? __ocml_scalbn_f64(__x, __n)
+  return (__n < INT_MAX) ? __builtin_amdgcn_ldexp(__x, __n)
                          : __ocml_scalb_f64(__x, __n);
 }
 __DEVICE__
-double scalbn(double __x, int __n) { return __ocml_scalbn_f64(__x, __n); }
+double scalbn(double __x, int __n) { return __builtin_amdgcn_ldexp(__x, __n); }
 
 __DEVICE__
-__RETURN_TYPE __signbit(double __x) { return __ocml_signbit_f64(__x); }
+__RETURN_TYPE __signbit(double __x) { return __builtin_signbit(__x); }
 
 __DEVICE__
 double sin(double __x) { return __ocml_sin_f64(__x); }
@@ -1091,7 +1076,7 @@ __DEVICE__
 double tgamma(double __x) { return __ocml_tgamma_f64(__x); }
 
 __DEVICE__
-double trunc(double __x) { return __ocml_trunc_f64(__x); }
+double trunc(double __x) { return __builtin_trunc(__x); }
 
 __DEVICE__
 double y0(double __x) { return __ocml_y0_f64(__x); }
@@ -1258,7 +1243,7 @@ double __fma_rz(double __x, double __y, double __z) {
 #else
 __DEVICE__
 double __fma_rn(double __x, double __y, double __z) {
-  return __ocml_fma_f64(__x, __y, __z);
+  return __builtin_fma(__x, __y, __z);
 }
 #endif
 // END INTRINSICS
@@ -1290,16 +1275,16 @@ __DEVICE__ int max(int __arg1, int __arg2) {
 }
 
 __DEVICE__
-float max(float __x, float __y) { return fmaxf(__x, __y); }
+float max(float __x, float __y) { return __builtin_fmaxf(__x, __y); }
 
 __DEVICE__
-double max(double __x, double __y) { return fmax(__x, __y); }
+double max(double __x, double __y) { return __builtin_fmax(__x, __y); }
 
 __DEVICE__
-float min(float __x, float __y) { return fminf(__x, __y); }
+float min(float __x, float __y) { return __builtin_fminf(__x, __y); }
 
 __DEVICE__
-double min(double __x, double __y) { return fmin(__x, __y); }
+double min(double __x, double __y) { return __builtin_fmin(__x, __y); }
 
 #if !defined(__HIPCC_RTC__) && !defined(__OPENMP_AMDGCN__)
 __host__ inline static int min(int __arg1, int __arg2) {

package/lib/clang/{16 → 17}/include/__clang_hip_runtime_wrapper.h

@@ -80,12 +80,25 @@ extern "C" {
 #if HIP_VERSION_MAJOR * 100 + HIP_VERSION_MINOR >= 405
 extern "C" __device__ unsigned long long __ockl_dm_alloc(unsigned long long __size);
 extern "C" __device__ void __ockl_dm_dealloc(unsigned long long __addr);
+#if __has_feature(address_sanitizer)
+extern "C" __device__ unsigned long long __asan_malloc_impl(unsigned long long __size, unsigned long long __pc);
+extern "C" __device__ void __asan_free_impl(unsigned long long __addr, unsigned long long __pc);
+__attribute__((noinline, weak)) __device__ void *malloc(__hip_size_t __size) {
+  unsigned long long __pc = (unsigned long long)__builtin_return_address(0);
+  return (void *)__asan_malloc_impl(__size, __pc);
+}
+__attribute__((noinline, weak)) __device__ void free(void *__ptr) {
+  unsigned long long __pc = (unsigned long long)__builtin_return_address(0);
+  __asan_free_impl((unsigned long long)__ptr, __pc);
+}
+#else
 __attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   return (void *) __ockl_dm_alloc(__size);
 }
 __attribute__((weak)) inline __device__ void free(void *__ptr) {
   __ockl_dm_dealloc((unsigned long long)__ptr);
 }
+#endif // __has_feature(address_sanitizer)
 #else  // HIP version check
 #if __HIP_ENABLE_DEVICE_MALLOC__
 __device__ void *__hip_malloc(__hip_size_t __size);

package/lib/clang/17/include/adxintrin.h

@@ -0,0 +1,227 @@
+/*===---- adxintrin.h - ADX intrinsics -------------------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __IMMINTRIN_H
+#error "Never use <adxintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __ADXINTRIN_H
+#define __ADXINTRIN_H
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
+
+/* Use C++ inline semantics in C++, GNU inline for C mode. */
+#if defined(__cplusplus)
+#define __INLINE __inline
+#else
+#define __INLINE static __inline
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Intrinsics that are available only if __ADX__ is defined. */
+
+/// Adds unsigned 32-bit integers \a __x and \a __y, plus 0 or 1 as indicated
+///    by the carry flag \a __cf. Stores the unsigned 32-bit sum in the memory
+///    at \a __p, and returns the 8-bit carry-out (carry flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store32(__p, __x + __y + temp)
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c ADCX instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    A 32-bit unsigned addend.
+/// \param __y
+///    A 32-bit unsigned addend.
+/// \param __p
+///    Pointer to memory for storing the sum.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char
+    __attribute__((__always_inline__, __nodebug__, __target__("adx")))
+    _addcarryx_u32(unsigned char __cf, unsigned int __x, unsigned int __y,
+                   unsigned int *__p) {
+  return __builtin_ia32_addcarryx_u32(__cf, __x, __y, __p);
+}
+
+#ifdef __x86_64__
+/// Adds unsigned 64-bit integers \a __x and \a __y, plus 0 or 1 as indicated
+///    by the carry flag \a __cf. Stores the unsigned 64-bit sum in the memory
+///    at \a __p, and returns the 8-bit carry-out (carry flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store64(__p, __x + __y + temp)
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c ADCX instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    A 64-bit unsigned addend.
+/// \param __y
+///    A 64-bit unsigned addend.
+/// \param __p
+///    Pointer to memory for storing the sum.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char
+    __attribute__((__always_inline__, __nodebug__, __target__("adx")))
+    _addcarryx_u64(unsigned char __cf, unsigned long long __x,
+                   unsigned long long __y, unsigned long long *__p) {
+  return __builtin_ia32_addcarryx_u64(__cf, __x, __y, __p);
+}
+#endif
+
+/* Intrinsics that are also available if __ADX__ is undefined. */
+
+/// Adds unsigned 32-bit integers \a __x and \a __y, plus 0 or 1 as indicated
+///    by the carry flag \a __cf. Stores the unsigned 32-bit sum in the memory
+///    at \a __p, and returns the 8-bit carry-out (carry flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store32(__p, __x + __y + temp)
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c ADC instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    A 32-bit unsigned addend.
+/// \param __y
+///    A 32-bit unsigned addend.
+/// \param __p
+///    Pointer to memory for storing the sum.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char __DEFAULT_FN_ATTRS _addcarry_u32(unsigned char __cf,
+                                                        unsigned int __x,
+                                                        unsigned int __y,
+                                                        unsigned int *__p) {
+  return __builtin_ia32_addcarryx_u32(__cf, __x, __y, __p);
+}
+
+#ifdef __x86_64__
+/// Adds unsigned 64-bit integers \a __x and \a __y, plus 0 or 1 as indicated
+///    by the carry flag \a __cf. Stores the unsigned 64-bit sum in the memory
+///    at \a __p, and returns the 8-bit carry-out (carry flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store64(__p, __x + __y + temp)
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c ADC instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    A 64-bit unsigned addend.
+/// \param __y
+///    A 64-bit unsigned addend.
+/// \param __p
+///    Pointer to memory for storing the sum.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char __DEFAULT_FN_ATTRS
+_addcarry_u64(unsigned char __cf, unsigned long long __x,
+              unsigned long long __y, unsigned long long *__p) {
+  return __builtin_ia32_addcarryx_u64(__cf, __x, __y, __p);
+}
+#endif
+
+/// Adds unsigned 32-bit integer \a __y to 0 or 1 as indicated by the carry
+///    flag \a __cf, and subtracts the result from unsigned 32-bit integer
+///    \a __x. Stores the unsigned 32-bit difference in the memory at \a __p,
+///    and returns the 8-bit carry-out (carry or overflow flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store32(__p, __x - (__y + temp))
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c SBB instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    The 32-bit unsigned minuend.
+/// \param __y
+///    The 32-bit unsigned subtrahend.
+/// \param __p
+///    Pointer to memory for storing the difference.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char __DEFAULT_FN_ATTRS _subborrow_u32(unsigned char __cf,
+                                                         unsigned int __x,
+                                                         unsigned int __y,
+                                                         unsigned int *__p) {
+  return __builtin_ia32_subborrow_u32(__cf, __x, __y, __p);
+}
+
+#ifdef __x86_64__
+/// Adds unsigned 64-bit integer \a __y to 0 or 1 as indicated by the carry
+///    flag \a __cf, and subtracts the result from unsigned 64-bit integer
+///    \a __x. Stores the unsigned 64-bit difference in the memory at \a __p,
+///    and returns the 8-bit carry-out (carry or overflow flag).
+///
+/// \code{.operation}
+/// temp := (__cf == 0) ? 0 : 1
+/// Store64(__p, __x - (__y + temp))
+/// result := CF
+/// \endcode
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the \c ADC instruction.
+///
+/// \param __cf
+///    The 8-bit unsigned carry flag; any non-zero value indicates carry.
+/// \param __x
+///    The 64-bit unsigned minuend.
+/// \param __y
+///    The 64-bit unsigned subtrahend.
+/// \param __p
+///    Pointer to memory for storing the difference.
+/// \returns The 8-bit unsigned carry-out value.
+__INLINE unsigned char __DEFAULT_FN_ATTRS
+_subborrow_u64(unsigned char __cf, unsigned long long __x,
+               unsigned long long __y, unsigned long long *__p) {
+  return __builtin_ia32_subborrow_u64(__cf, __x, __y, __p);
+}
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif /* __ADXINTRIN_H */