@cpp-linter/clang-tidy-win32-x64 14.0.0 → 16.0.3

package/lib/clang/16/include/amxfp16intrin.h

@@ -0,0 +1,58 @@
+/*===------------- amxfp16intrin.h - AMX_FP16 intrinsics -*- C++ -*---------===
+ *
+ * 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 <amxfp16intrin.h> directly; use <immintrin.h> instead."
+#endif /* __IMMINTRIN_H */
+
+#ifndef __AMX_FP16INTRIN_H
+#define __AMX_FP16INTRIN_H
+#ifdef __x86_64__
+
+/// Compute dot-product of FP16 (16-bit) floating-point pairs in tiles \a a
+///    and \a b, accumulating the intermediate single-precision (32-bit)
+///    floating-point elements with elements in \a dst, and store the 32-bit
+///    result back to tile \a dst.
+///
+/// \headerfile <immintrin.h>
+///
+/// \code
+/// void _tile_dpfp16ps (__tile dst, __tile a, __tile b)
+/// \endcode
+///
+/// \code{.operation}
+/// FOR m := 0 TO dst.rows - 1
+///	tmp := dst.row[m]
+///	FOR k := 0 TO (a.colsb / 4) - 1
+///		FOR n := 0 TO (dst.colsb / 4) - 1
+///			tmp.fp32[n] += FP32(a.row[m].fp16[2*k+0]) *
+///					FP32(b.row[k].fp16[2*n+0])
+///			tmp.fp32[n] += FP32(a.row[m].fp16[2*k+1]) *
+///					FP32(b.row[k].fp16[2*n+1])
+///		ENDFOR
+///	ENDFOR
+///	write_row_and_zero(dst, m, tmp, dst.colsb)
+/// ENDFOR
+/// zero_upper_rows(dst, dst.rows)
+/// zero_tileconfig_start()
+/// \endcode
+///
+/// This intrinsic corresponds to the \c TDPFP16PS instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param a
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param b
+///    The 2nd source tile. Max size is 1024 Bytes.
+#define _tile_dpfp16ps(dst, a, b)                                \
+  __builtin_ia32_tdpfp16ps(dst, a, b)
+
+#endif /* __x86_64__ */
+#endif /* __AMX_FP16INTRIN_H */

package/lib/clang/{14.0.0 → 16}/include/amxintrin.h

@@ -22,6 +22,8 @@
   __attribute__((__always_inline__, __nodebug__, __target__("amx-int8")))
 #define __DEFAULT_FN_ATTRS_BF16                                                \
   __attribute__((__always_inline__, __nodebug__, __target__("amx-bf16")))
+#define __DEFAULT_FN_ATTRS_FP16                                                \
+  __attribute__((__always_inline__, __nodebug__, __target__("amx-fp16")))
 
 /// Load tile configuration from a 64-byte memory location specified by
 /// "mem_addr". The tile configuration includes the tile type palette, the
@@ -290,6 +292,13 @@ _tile_dpbf16ps_internal(unsigned short m, unsigned short n, unsigned short k,
   return __builtin_ia32_tdpbf16ps_internal(m, n, k, dst, src1, src2);
 }
 
+/// This is internal intrinsic. C/C++ user should avoid calling it directly.
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_FP16
+_tile_dpfp16ps_internal(unsigned short m, unsigned short n, unsigned short k,
+                        _tile1024i dst, _tile1024i src1, _tile1024i src2) {
+  return __builtin_ia32_tdpfp16ps_internal(m, n, k, dst, src1, src2);
+}
+
 /// This struct pack the shape and tile data together for user. We suggest
 /// initializing the struct as early as possible, because compiler depends
 /// on the shape information to do configure. The constant value is preferred
@@ -439,8 +448,6 @@ static __inline__ void __tile_dpbuud(__tile1024i *dst, __tile1024i src0,
 ///
 /// This intrinsic corresponds to the <c> TILESTORED </c> instruction.
 ///
-/// \param dst
-///    A destination tile. Max size is 1024 Bytes.
 /// \param base
 ///    A pointer to base address.
 /// \param stride
@@ -486,9 +493,32 @@ static __inline__ void __tile_dpbf16ps(__tile1024i *dst, __tile1024i src0,
                                       src0.tile, src1.tile);
 }
 
+/// Compute dot-product of FP16 (16-bit) floating-point pairs in tiles src0 and
+/// src1, accumulating the intermediate single-precision (32-bit) floating-point
+/// elements with elements in "dst", and store the 32-bit result back to tile
+/// "dst".
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the <c> TDPFP16PS </c> instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param src0
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param src1
+///    The 2nd source tile. Max size is 1024 Bytes.
+__DEFAULT_FN_ATTRS_FP16
+static __inline__ void __tile_dpfp16ps(__tile1024i *dst, __tile1024i src0,
+                                       __tile1024i src1) {
+  dst->tile = _tile_dpfp16ps_internal(src0.row, src1.col, src0.col, dst->tile,
+                                      src0.tile, src1.tile);
+}
+
 #undef __DEFAULT_FN_ATTRS_TILE
 #undef __DEFAULT_FN_ATTRS_INT8
 #undef __DEFAULT_FN_ATTRS_BF16
+#undef __DEFAULT_FN_ATTRS_FP16
 
 #endif /* __x86_64__ */
 #endif /* __AMXINTRIN_H */

package/lib/clang/{14.0.0 → 16}/include/arm_acle.h

@@ -64,7 +64,7 @@ static __inline__ void __attribute__((__always_inline__, __nodebug__)) __yield(v
 }
 #endif
 
-#if __ARM_32BIT_STATE
+#if defined(__ARM_32BIT_STATE) && __ARM_32BIT_STATE
 #define __dbg(t) __builtin_arm_dbg(t)
 #endif
 
@@ -82,7 +82,7 @@ __swp(uint32_t __x, volatile uint32_t *__p) {
 /* 8.6.1 Data prefetch */
 #define __pld(addr) __pldx(0, 0, 0, addr)
 
-#if __ARM_32BIT_STATE
+#if defined(__ARM_32BIT_STATE) && __ARM_32BIT_STATE
 #define __pldx(access_kind, cache_level, retention_policy, addr) \
   __builtin_arm_prefetch(addr, access_kind, 1)
 #else
@@ -93,7 +93,7 @@ __swp(uint32_t __x, volatile uint32_t *__p) {
 /* 8.6.2 Instruction prefetch */
 #define __pli(addr) __plix(0, 0, addr)
 
-#if __ARM_32BIT_STATE
+#if defined(__ARM_32BIT_STATE) && __ARM_32BIT_STATE
 #define __plix(cache_level, retention_policy, addr) \
   __builtin_arm_prefetch(addr, 0, 0)
 #else
@@ -140,17 +140,17 @@ __rorl(unsigned long __x, uint32_t __y) {
 /* CLZ */
 static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
 __clz(uint32_t __t) {
-  return __builtin_clz(__t);
+  return (uint32_t)__builtin_clz(__t);
 }
 
 static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
 __clzl(unsigned long __t) {
-  return __builtin_clzl(__t);
+  return (unsigned long)__builtin_clzl(__t);
 }
 
 static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
 __clzll(uint64_t __t) {
-  return __builtin_clzll(__t);
+  return (uint64_t)__builtin_clzll(__t);
 }
 
 /* CLS */
@@ -201,7 +201,7 @@ __rev16(uint32_t __t) {
 
 static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
 __rev16ll(uint64_t __t) {
-  return (((uint64_t)__rev16(__t >> 32)) << 32) | __rev16(__t);
+  return (((uint64_t)__rev16(__t >> 32)) << 32) | (uint64_t)__rev16((uint32_t)__t);
 }
 
 static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
@@ -216,7 +216,7 @@ __rev16l(unsigned long __t) {
 /* REVSH */
 static __inline__ int16_t __attribute__((__always_inline__, __nodebug__))
 __revsh(int16_t __t) {
-  return __builtin_bswap16(__t);
+  return (int16_t)__builtin_bswap16((uint16_t)__t);
 }
 
 /* RBIT */
@@ -227,7 +227,7 @@ __rbit(uint32_t __t) {
 
 static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
 __rbitll(uint64_t __t) {
-#if __ARM_32BIT_STATE
+#if defined(__ARM_32BIT_STATE) && __ARM_32BIT_STATE
   return (((uint64_t)__builtin_arm_rbit(__t)) << 32) |
          __builtin_arm_rbit(__t >> 32);
 #else
@@ -247,7 +247,7 @@ __rbitl(unsigned long __t) {
 /*
  * 9.3 16-bit multiplications
  */
-#if __ARM_FEATURE_DSP
+#if defined(__ARM_FEATURE_DSP) && __ARM_FEATURE_DSP
 static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
 __smulbb(int32_t __a, int32_t __b) {
   return __builtin_arm_smulbb(__a, __b);
@@ -277,17 +277,17 @@ __smulwt(int32_t __a, int32_t __b) {
 /*
  * 9.4 Saturating intrinsics
  *
- * FIXME: Change guard to their corrosponding __ARM_FEATURE flag when Q flag
+ * FIXME: Change guard to their corresponding __ARM_FEATURE flag when Q flag
  * intrinsics are implemented and the flag is enabled.
  */
 /* 9.4.1 Width-specified saturation intrinsics */
-#if __ARM_FEATURE_SAT
+#if defined(__ARM_FEATURE_SAT) && __ARM_FEATURE_SAT
 #define __ssat(x, y) __builtin_arm_ssat(x, y)
 #define __usat(x, y) __builtin_arm_usat(x, y)
 #endif
 
 /* 9.4.2 Saturating addition and subtraction intrinsics */
-#if __ARM_FEATURE_DSP
+#if defined(__ARM_FEATURE_DSP) && __ARM_FEATURE_DSP
 static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
 __qadd(int32_t __t, int32_t __v) {
   return __builtin_arm_qadd(__t, __v);
@@ -305,7 +305,7 @@ __qdbl(int32_t __t) {
 #endif
 
 /* 9.4.3 Accumultating multiplications */
-#if __ARM_FEATURE_DSP
+#if defined(__ARM_FEATURE_DSP) && __ARM_FEATURE_DSP
 static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
 __smlabb(int32_t __a, int32_t __b, int32_t __c) {
   return __builtin_arm_smlabb(__a, __b, __c);
@@ -334,13 +334,13 @@ __smlawt(int32_t __a, int32_t __b, int32_t __c) {
 
 
 /* 9.5.4 Parallel 16-bit saturation */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 #define __ssat16(x, y) __builtin_arm_ssat16(x, y)
 #define __usat16(x, y) __builtin_arm_usat16(x, y)
 #endif
 
 /* 9.5.5 Packing and unpacking */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 typedef int32_t int8x4_t;
 typedef int32_t int16x2_t;
 typedef uint32_t uint8x4_t;
@@ -365,7 +365,7 @@ __uxtb16(int8x4_t __a) {
 #endif
 
 /* 9.5.6 Parallel selection */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
 __sel(uint8x4_t __a, uint8x4_t __b) {
   return __builtin_arm_sel(__a, __b);
@@ -373,7 +373,7 @@ __sel(uint8x4_t __a, uint8x4_t __b) {
 #endif
 
 /* 9.5.7 Parallel 8-bit addition and subtraction */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
 __qadd8(int8x4_t __a, int8x4_t __b) {
   return __builtin_arm_qadd8(__a, __b);
@@ -425,7 +425,7 @@ __usub8(uint8x4_t __a, uint8x4_t __b) {
 #endif
 
 /* 9.5.8 Sum of 8-bit absolute differences */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
 __usad8(uint8x4_t __a, uint8x4_t __b) {
   return __builtin_arm_usad8(__a, __b);
@@ -437,7 +437,7 @@ __usada8(uint8x4_t __a, uint8x4_t __b, uint32_t __c) {
 #endif
 
 /* 9.5.9 Parallel 16-bit addition and subtraction */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
 __qadd16(int16x2_t __a, int16x2_t __b) {
   return __builtin_arm_qadd16(__a, __b);
@@ -537,7 +537,7 @@ __usub16(uint16x2_t __a, uint16x2_t __b) {
 #endif
 
 /* 9.5.10 Parallel 16-bit multiplications */
-#if __ARM_FEATURE_SIMD32
+#if defined(__ARM_FEATURE_SIMD32) && __ARM_FEATURE_SIMD32
 static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
 __smlad(int16x2_t __a, int16x2_t __b, int32_t __c) {
   return __builtin_arm_smlad(__a, __b, __c);
@@ -589,155 +589,156 @@ __smusdx(int16x2_t __a, int16x2_t __b) {
 #endif
 
 /* 9.7 CRC32 intrinsics */
-#if __ARM_FEATURE_CRC32
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+#if (defined(__ARM_FEATURE_CRC32) && __ARM_FEATURE_CRC32) ||                   \
+    (defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE)
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32b(uint32_t __a, uint8_t __b) {
   return __builtin_arm_crc32b(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32h(uint32_t __a, uint16_t __b) {
   return __builtin_arm_crc32h(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32w(uint32_t __a, uint32_t __b) {
   return __builtin_arm_crc32w(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32d(uint32_t __a, uint64_t __b) {
   return __builtin_arm_crc32d(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32cb(uint32_t __a, uint8_t __b) {
   return __builtin_arm_crc32cb(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32ch(uint32_t __a, uint16_t __b) {
   return __builtin_arm_crc32ch(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32cw(uint32_t __a, uint32_t __b) {
   return __builtin_arm_crc32cw(__a, __b);
 }
 
-static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__, target("crc")))
 __crc32cd(uint32_t __a, uint64_t __b) {
   return __builtin_arm_crc32cd(__a, __b);
 }
 #endif
 
 /* Armv8.3-A Javascript conversion intrinsic */
-#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_JCVT)
-static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
+#if defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE
+static __inline__ int32_t __attribute__((__always_inline__, __nodebug__, target("v8.3a")))
 __jcvt(double __a) {
   return __builtin_arm_jcvt(__a);
 }
 #endif
 
 /* Armv8.5-A FP rounding intrinsics */
-#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_FRINT)
-static __inline__ float __attribute__((__always_inline__, __nodebug__))
-__frint32zf(float __a) {
-  return __builtin_arm_frint32zf(__a);
+#if defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE
+static __inline__ float __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint32zf(float __a) {
+  return __builtin_arm_rint32zf(__a);
 }
 
-static __inline__ double __attribute__((__always_inline__, __nodebug__))
-__frint32z(double __a) {
-  return __builtin_arm_frint32z(__a);
+static __inline__ double __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint32z(double __a) {
+  return __builtin_arm_rint32z(__a);
 }
 
-static __inline__ float __attribute__((__always_inline__, __nodebug__))
-__frint64zf(float __a) {
-  return __builtin_arm_frint64zf(__a);
+static __inline__ float __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint64zf(float __a) {
+  return __builtin_arm_rint64zf(__a);
 }
 
-static __inline__ double __attribute__((__always_inline__, __nodebug__))
-__frint64z(double __a) {
-  return __builtin_arm_frint64z(__a);
+static __inline__ double __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint64z(double __a) {
+  return __builtin_arm_rint64z(__a);
 }
 
-static __inline__ float __attribute__((__always_inline__, __nodebug__))
-__frint32xf(float __a) {
-  return __builtin_arm_frint32xf(__a);
+static __inline__ float __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint32xf(float __a) {
+  return __builtin_arm_rint32xf(__a);
 }
 
-static __inline__ double __attribute__((__always_inline__, __nodebug__))
-__frint32x(double __a) {
-  return __builtin_arm_frint32x(__a);
+static __inline__ double __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint32x(double __a) {
+  return __builtin_arm_rint32x(__a);
 }
 
-static __inline__ float __attribute__((__always_inline__, __nodebug__))
-__frint64xf(float __a) {
-  return __builtin_arm_frint64xf(__a);
+static __inline__ float __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint64xf(float __a) {
+  return __builtin_arm_rint64xf(__a);
 }
 
-static __inline__ double __attribute__((__always_inline__, __nodebug__))
-__frint64x(double __a) {
-  return __builtin_arm_frint64x(__a);
+static __inline__ double __attribute__((__always_inline__, __nodebug__, target("v8.5a")))
+__rint64x(double __a) {
+  return __builtin_arm_rint64x(__a);
 }
 #endif
 
 /* Armv8.7-A load/store 64-byte intrinsics */
-#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_LS64)
+#if defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE
 typedef struct {
     uint64_t val[8];
 } data512_t;
 
-static __inline__ data512_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ data512_t __attribute__((__always_inline__, __nodebug__, target("ls64")))
 __arm_ld64b(const void *__addr) {
-    data512_t __value;
-    __builtin_arm_ld64b(__addr, __value.val);
-    return __value;
+  data512_t __value;
+  __builtin_arm_ld64b(__addr, __value.val);
+  return __value;
 }
-static __inline__ void __attribute__((__always_inline__, __nodebug__))
+static __inline__ void __attribute__((__always_inline__, __nodebug__, target("ls64")))
 __arm_st64b(void *__addr, data512_t __value) {
-    __builtin_arm_st64b(__addr, __value.val);
+  __builtin_arm_st64b(__addr, __value.val);
 }
-static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__, target("ls64")))
 __arm_st64bv(void *__addr, data512_t __value) {
-    return __builtin_arm_st64bv(__addr, __value.val);
+  return __builtin_arm_st64bv(__addr, __value.val);
 }
-static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
+static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__, target("ls64")))
 __arm_st64bv0(void *__addr, data512_t __value) {
-    return __builtin_arm_st64bv0(__addr, __value.val);
+  return __builtin_arm_st64bv0(__addr, __value.val);
 }
 #endif
 
 /* 10.1 Special register intrinsics */
 #define __arm_rsr(sysreg) __builtin_arm_rsr(sysreg)
 #define __arm_rsr64(sysreg) __builtin_arm_rsr64(sysreg)
+#define __arm_rsr128(sysreg) __builtin_arm_rsr128(sysreg)
 #define __arm_rsrp(sysreg) __builtin_arm_rsrp(sysreg)
 #define __arm_rsrf(sysreg) __builtin_bit_cast(float, __arm_rsr(sysreg))
 #define __arm_rsrf64(sysreg) __builtin_bit_cast(double, __arm_rsr64(sysreg))
 #define __arm_wsr(sysreg, v) __builtin_arm_wsr(sysreg, v)
 #define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)
+#define __arm_wsr128(sysreg, v) __builtin_arm_wsr128(sysreg, v)
 #define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)
 #define __arm_wsrf(sysreg, v) __arm_wsr(sysreg, __builtin_bit_cast(uint32_t, v))
 #define __arm_wsrf64(sysreg, v) __arm_wsr64(sysreg, __builtin_bit_cast(uint64_t, v))
 
 /* Memory Tagging Extensions (MTE) Intrinsics */
-#if __ARM_FEATURE_MEMORY_TAGGING
+#if defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE
 #define __arm_mte_create_random_tag(__ptr, __mask)  __builtin_arm_irg(__ptr, __mask)
 #define __arm_mte_increment_tag(__ptr, __tag_offset)  __builtin_arm_addg(__ptr, __tag_offset)
 #define __arm_mte_exclude_tag(__ptr, __excluded)  __builtin_arm_gmi(__ptr, __excluded)
 #define __arm_mte_get_tag(__ptr) __builtin_arm_ldg(__ptr)
 #define __arm_mte_set_tag(__ptr) __builtin_arm_stg(__ptr)
 #define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)
-#endif
 
 /* Memory Operations Intrinsics */
-#if __ARM_FEATURE_MOPS && __ARM_FEATURE_MEMORY_TAGGING
 #define __arm_mops_memset_tag(__tagged_address, __value, __size)    \
   __builtin_arm_mops_memset_tag(__tagged_address, __value, __size)
 #endif
 
 /* Transactional Memory Extension (TME) Intrinsics */
-#if __ARM_FEATURE_TME
+#if defined(__ARM_FEATURE_TME) && __ARM_FEATURE_TME
 
 #define _TMFAILURE_REASON  0x00007fffu
 #define _TMFAILURE_RTRY    0x00008000u
@@ -759,12 +760,12 @@ __arm_st64bv0(void *__addr, data512_t __value) {
 #endif /* __ARM_FEATURE_TME */
 
 /* Armv8.5-A Random number generation intrinsics */
-#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_RNG)
-static __inline__ int __attribute__((__always_inline__, __nodebug__))
+#if defined(__ARM_64BIT_STATE) && __ARM_64BIT_STATE
+static __inline__ int __attribute__((__always_inline__, __nodebug__, target("rand")))
 __rndr(uint64_t *__p) {
   return __builtin_arm_rndr(__p);
 }
-static __inline__ int __attribute__((__always_inline__, __nodebug__))
+static __inline__ int __attribute__((__always_inline__, __nodebug__, target("rand")))
 __rndrrs(uint64_t *__p) {
   return __builtin_arm_rndrrs(__p);
 }