@cpp-linter/clang-tidy-darwin-x64 17.0.6 → 18.1.8

package/lib/clang/{17 → 18}/include/bmiintrin.h

@@ -19,18 +19,17 @@
    to use it as a potentially faster version of BSF. */
 #define __RELAXED_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
 
-#define _tzcnt_u16(a)     (__tzcnt_u16((a)))
-
 /// Counts the number of trailing zero bits in the operand.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
+/// This intrinsic corresponds to the \c TZCNT instruction.
 ///
 /// \param __X
 ///    An unsigned 16-bit integer whose trailing zeros are to be counted.
 /// \returns An unsigned 16-bit integer containing the number of trailing zero
 ///    bits in the operand.
+/// \see _tzcnt_u16
 static __inline__ unsigned short __RELAXED_FN_ATTRS
 __tzcnt_u16(unsigned short __X)
 {
@@ -41,13 +40,30 @@ __tzcnt_u16(unsigned short __X)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
+/// \code
+/// unsigned short _tzcnt_u16(unsigned short __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c TZCNT instruction.
+///
+/// \param __X
+///    An unsigned 16-bit integer whose trailing zeros are to be counted.
+/// \returns An unsigned 16-bit integer containing the number of trailing zero
+///    bits in the operand.
+/// \see __tzcnt_u16
+#define _tzcnt_u16 __tzcnt_u16
+
+/// Counts the number of trailing zero bits in the operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c TZCNT instruction.
 ///
 /// \param __X
 ///    An unsigned 32-bit integer whose trailing zeros are to be counted.
 /// \returns An unsigned 32-bit integer containing the number of trailing zero
 ///    bits in the operand.
-/// \see _mm_tzcnt_32
+/// \see { _mm_tzcnt_32 _tzcnt_u32 }
 static __inline__ unsigned int __RELAXED_FN_ATTRS
 __tzcnt_u32(unsigned int __X)
 {
@@ -58,20 +74,35 @@ __tzcnt_u32(unsigned int __X)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
+/// This intrinsic corresponds to the \c TZCNT instruction.
 ///
 /// \param __X
 ///    An unsigned 32-bit integer whose trailing zeros are to be counted.
-/// \returns An 32-bit integer containing the number of trailing zero bits in
+/// \returns A 32-bit integer containing the number of trailing zero bits in
 ///    the operand.
-/// \see __tzcnt_u32
+/// \see { __tzcnt_u32 _tzcnt_u32 }
 static __inline__ int __RELAXED_FN_ATTRS
 _mm_tzcnt_32(unsigned int __X)
 {
   return (int)__builtin_ia32_tzcnt_u32(__X);
 }
 
-#define _tzcnt_u32(a)     (__tzcnt_u32((a)))
+/// Counts the number of trailing zero bits in the operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned int _tzcnt_u32(unsigned int __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c TZCNT instruction.
+///
+/// \param __X
+///    An unsigned 32-bit integer whose trailing zeros are to be counted.
+/// \returns An unsigned 32-bit integer containing the number of trailing zero
+///    bits in the operand.
+/// \see { _mm_tzcnt_32 __tzcnt_u32 }
+#define _tzcnt_u32 __tzcnt_u32
 
 #ifdef __x86_64__
 
@@ -79,13 +110,13 @@ _mm_tzcnt_32(unsigned int __X)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
+/// This intrinsic corresponds to the \c TZCNT instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose trailing zeros are to be counted.
 /// \returns An unsigned 64-bit integer containing the number of trailing zero
 ///    bits in the operand.
-/// \see _mm_tzcnt_64
+/// \see { _mm_tzcnt_64 _tzcnt_u64 }
 static __inline__ unsigned long long __RELAXED_FN_ATTRS
 __tzcnt_u64(unsigned long long __X)
 {
@@ -96,20 +127,35 @@ __tzcnt_u64(unsigned long long __X)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
+/// This intrinsic corresponds to the \c TZCNT instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose trailing zeros are to be counted.
 /// \returns An 64-bit integer containing the number of trailing zero bits in
 ///    the operand.
-/// \see __tzcnt_u64
+/// \see { __tzcnt_u64 _tzcnt_u64 }
 static __inline__ long long __RELAXED_FN_ATTRS
 _mm_tzcnt_64(unsigned long long __X)
 {
   return (long long)__builtin_ia32_tzcnt_u64(__X);
 }
 
-#define _tzcnt_u64(a)     (__tzcnt_u64((a)))
+/// Counts the number of trailing zero bits in the operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned long long _tzcnt_u64(unsigned long long __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c TZCNT instruction.
+///
+/// \param __X
+///    An unsigned 64-bit integer whose trailing zeros are to be counted.
+/// \returns An unsigned 64-bit integer containing the number of trailing zero
+///    bits in the operand.
+/// \see { _mm_tzcnt_64 __tzcnt_u64
+#define _tzcnt_u64 __tzcnt_u64
 
 #endif /* __x86_64__ */
 
@@ -121,21 +167,12 @@ _mm_tzcnt_64(unsigned long long __X)
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("bmi")))
 
-#define _andn_u32(a, b)   (__andn_u32((a), (b)))
-
-/* _bextr_u32 != __bextr_u32 */
-#define _blsi_u32(a)      (__blsi_u32((a)))
-
-#define _blsmsk_u32(a)    (__blsmsk_u32((a)))
-
-#define _blsr_u32(a)      (__blsr_u32((a)))
-
 /// Performs a bitwise AND of the second operand with the one's
 ///    complement of the first operand.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> ANDN </c> instruction.
+/// This intrinsic corresponds to the \c ANDN instruction.
 ///
 /// \param __X
 ///    An unsigned integer containing one of the operands.
@@ -143,19 +180,40 @@ _mm_tzcnt_64(unsigned long long __X)
 ///    An unsigned integer containing one of the operands.
 /// \returns An unsigned integer containing the bitwise AND of the second
 ///    operand with the one's complement of the first operand.
+/// \see _andn_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __andn_u32(unsigned int __X, unsigned int __Y)
 {
   return ~__X & __Y;
 }
 
+/// Performs a bitwise AND of the second operand with the one's
+///    complement of the first operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned int _andn_u32(unsigned int __X, unsigned int __Y);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c ANDN instruction.
+///
+/// \param __X
+///    An unsigned integer containing one of the operands.
+/// \param __Y
+///    An unsigned integer containing one of the operands.
+/// \returns An unsigned integer containing the bitwise AND of the second
+///    operand with the one's complement of the first operand.
+/// \see __andn_u32
+#define _andn_u32 __andn_u32
+
 /* AMD-specified, double-leading-underscore version of BEXTR */
 /// Extracts the specified bits from the first operand and returns them
 ///    in the least significant bits of the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned integer whose bits are to be extracted.
@@ -178,7 +236,7 @@ __bextr_u32(unsigned int __X, unsigned int __Y)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned integer whose bits are to be extracted.
@@ -203,7 +261,7 @@ _bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned integer whose bits are to be extracted.
@@ -224,69 +282,117 @@ _bextr2_u32(unsigned int __X, unsigned int __Y) {
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSI </c> instruction.
+/// This intrinsic corresponds to the \c BLSI instruction.
 ///
 /// \param __X
 ///    An unsigned integer whose bits are to be cleared.
 /// \returns An unsigned integer containing the result of clearing the bits from
 ///    the source operand.
+/// \see _blsi_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __blsi_u32(unsigned int __X)
 {
   return __X & -__X;
 }
 
+/// Clears all bits in the source except for the least significant bit
+///    containing a value of 1 and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned int _blsi_u32(unsigned int __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSI instruction.
+///
+/// \param __X
+///    An unsigned integer whose bits are to be cleared.
+/// \returns An unsigned integer containing the result of clearing the bits from
+///    the source operand.
+/// \see __blsi_u32
+#define _blsi_u32 __blsi_u32
+
 /// Creates a mask whose bits are set to 1, using bit 0 up to and
 ///    including the least significant bit that is set to 1 in the source
 ///    operand and returns the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSMSK </c> instruction.
+/// This intrinsic corresponds to the \c BLSMSK instruction.
 ///
 /// \param __X
 ///    An unsigned integer used to create the mask.
 /// \returns An unsigned integer containing the newly created mask.
+/// \see _blsmsk_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __blsmsk_u32(unsigned int __X)
 {
   return __X ^ (__X - 1);
 }
 
+/// Creates a mask whose bits are set to 1, using bit 0 up to and
+///    including the least significant bit that is set to 1 in the source
+///    operand and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned int _blsmsk_u32(unsigned int __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSMSK instruction.
+///
+/// \param __X
+///    An unsigned integer used to create the mask.
+/// \returns An unsigned integer containing the newly created mask.
+/// \see __blsmsk_u32
+#define _blsmsk_u32 __blsmsk_u32
+
 /// Clears the least significant bit that is set to 1 in the source
 ///    operand and returns the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSR </c> instruction.
+/// This intrinsic corresponds to the \c BLSR instruction.
 ///
 /// \param __X
 ///    An unsigned integer containing the operand to be cleared.
 /// \returns An unsigned integer containing the result of clearing the source
 ///    operand.
+/// \see _blsr_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __blsr_u32(unsigned int __X)
 {
   return __X & (__X - 1);
 }
 
-#ifdef __x86_64__
-
-#define _andn_u64(a, b)   (__andn_u64((a), (b)))
-
-/* _bextr_u64 != __bextr_u64 */
-#define _blsi_u64(a)      (__blsi_u64((a)))
-
-#define _blsmsk_u64(a)    (__blsmsk_u64((a)))
+/// Clears the least significant bit that is set to 1 in the source
+///    operand and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned int _bls4_u32(unsigned int __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSR instruction.
+///
+/// \param __X
+///    An unsigned integer containing the operand to be cleared.
+/// \returns An unsigned integer containing the result of clearing the source
+///    operand.
+/// \see __blsr_u32
+#define _blsr_u32 __blsr_u32
 
-#define _blsr_u64(a)      (__blsr_u64((a)))
+#ifdef __x86_64__
 
 /// Performs a bitwise AND of the second operand with the one's
 ///    complement of the first operand.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> ANDN </c> instruction.
+/// This intrinsic corresponds to the \c ANDN instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer containing one of the operands.
@@ -294,19 +400,41 @@ __blsr_u32(unsigned int __X)
 ///    An unsigned 64-bit integer containing one of the operands.
 /// \returns An unsigned 64-bit integer containing the bitwise AND of the second
 ///    operand with the one's complement of the first operand.
+/// \see _andn_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __andn_u64 (unsigned long long __X, unsigned long long __Y)
 {
   return ~__X & __Y;
 }
 
+/// Performs a bitwise AND of the second operand with the one's
+///    complement of the first operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned long long _andn_u64(unsigned long long __X,
+///                              unsigned long long __Y);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c ANDN instruction.
+///
+/// \param __X
+///    An unsigned 64-bit integer containing one of the operands.
+/// \param __Y
+///    An unsigned 64-bit integer containing one of the operands.
+/// \returns An unsigned 64-bit integer containing the bitwise AND of the second
+///    operand with the one's complement of the first operand.
+/// \see __andn_u64
+#define _andn_u64 __andn_u64
+
 /* AMD-specified, double-leading-underscore version of BEXTR */
 /// Extracts the specified bits from the first operand and returns them
 ///    in the least significant bits of the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose bits are to be extracted.
@@ -329,7 +457,7 @@ __bextr_u64(unsigned long long __X, unsigned long long __Y)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose bits are to be extracted.
@@ -354,7 +482,7 @@ _bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z)
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BEXTR </c> instruction.
+/// This intrinsic corresponds to the \c BEXTR instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose bits are to be extracted.
@@ -375,52 +503,109 @@ _bextr2_u64(unsigned long long __X, unsigned long long __Y) {
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSI </c> instruction.
+/// This intrinsic corresponds to the \c BLSI instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer whose bits are to be cleared.
 /// \returns An unsigned 64-bit integer containing the result of clearing the
 ///    bits from the source operand.
+/// \see _blsi_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __blsi_u64(unsigned long long __X)
 {
   return __X & -__X;
 }
 
+/// Clears all bits in the source except for the least significant bit
+///    containing a value of 1 and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned long long _blsi_u64(unsigned long long __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSI instruction.
+///
+/// \param __X
+///    An unsigned 64-bit integer whose bits are to be cleared.
+/// \returns An unsigned 64-bit integer containing the result of clearing the
+///    bits from the source operand.
+/// \see __blsi_u64
+#define _blsi_u64 __blsi_u64
+
 /// Creates a mask whose bits are set to 1, using bit 0 up to and
 ///    including the least significant bit that is set to 1 in the source
 ///    operand and returns the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSMSK </c> instruction.
+/// This intrinsic corresponds to the \c BLSMSK instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer used to create the mask.
 /// \returns An unsigned 64-bit integer containing the newly created mask.
+/// \see _blsmsk_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __blsmsk_u64(unsigned long long __X)
 {
   return __X ^ (__X - 1);
 }
 
+/// Creates a mask whose bits are set to 1, using bit 0 up to and
+///    including the least significant bit that is set to 1 in the source
+///    operand and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned long long _blsmsk_u64(unsigned long long __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSMSK instruction.
+///
+/// \param __X
+///    An unsigned 64-bit integer used to create the mask.
+/// \returns An unsigned 64-bit integer containing the newly created mask.
+/// \see __blsmsk_u64
+#define _blsmsk_u64 __blsmsk_u64
+
 /// Clears the least significant bit that is set to 1 in the source
 ///    operand and returns the result.
 ///
 /// \headerfile <x86intrin.h>
 ///
-/// This intrinsic corresponds to the <c> BLSR </c> instruction.
+/// This intrinsic corresponds to the \c BLSR instruction.
 ///
 /// \param __X
 ///    An unsigned 64-bit integer containing the operand to be cleared.
 /// \returns An unsigned 64-bit integer containing the result of clearing the
 ///    source operand.
+/// \see _blsr_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __blsr_u64(unsigned long long __X)
 {
   return __X & (__X - 1);
 }
 
+/// Clears the least significant bit that is set to 1 in the source
+///    operand and returns the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned long long _blsr_u64(unsigned long long __X);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c BLSR instruction.
+///
+/// \param __X
+///    An unsigned 64-bit integer containing the operand to be cleared.
+/// \returns An unsigned 64-bit integer containing the result of clearing the
+///    source operand.
+/// \see __blsr_u64
+#define _blsr_u64 __blsr_u64
+
 #endif /* __x86_64__ */
 
 #undef __DEFAULT_FN_ATTRS

package/lib/clang/{17 → 18}/include/emmintrin.h

@@ -50,11 +50,11 @@ typedef __bf16 __m128bh __attribute__((__vector_size__(16), __aligned__(16)));
 
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS                                                     \
-  __attribute__((__always_inline__, __nodebug__, __target__("sse2"),           \
-                 __min_vector_width__(128)))
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("sse2,no-evex512"), __min_vector_width__(128)))
 #define __DEFAULT_FN_ATTRS_MMX                                                 \
-  __attribute__((__always_inline__, __nodebug__, __target__("mmx,sse2"),       \
-                 __min_vector_width__(64)))
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("mmx,sse2,no-evex512"), __min_vector_width__(64)))
 
 /// Adds lower double-precision values in both operands and returns the
 ///    sum in the lower 64 bits of the result. The upper 64 bits of the result
@@ -3945,7 +3945,7 @@ static __inline__ void __DEFAULT_FN_ATTRS _mm_storel_epi64(__m128i_u *__p,
 ///    A pointer to the 128-bit aligned memory location used to store the value.
 /// \param __a
 ///    A vector of [2 x double] containing the 64-bit values to be stored.
-static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_pd(double *__p,
+static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_pd(void *__p,
                                                         __m128d __a) {
   __builtin_nontemporal_store((__v2df)__a, (__v2df *)__p);
 }
@@ -3963,7 +3963,7 @@ static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_pd(double *__p,
 ///    A pointer to the 128-bit aligned memory location used to store the value.
 /// \param __a
 ///    A 128-bit integer vector containing the values to be stored.
-static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_si128(__m128i *__p,
+static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_si128(void *__p,
                                                            __m128i __a) {
   __builtin_nontemporal_store((__v2di)__a, (__v2di *)__p);
 }
@@ -3983,8 +3983,8 @@ static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_si128(__m128i *__p,
 ///    A 32-bit integer containing the value to be stored.
 static __inline__ void
     __attribute__((__always_inline__, __nodebug__, __target__("sse2")))
-    _mm_stream_si32(int *__p, int __a) {
-  __builtin_ia32_movnti(__p, __a);
+    _mm_stream_si32(void *__p, int __a) {
+  __builtin_ia32_movnti((int *)__p, __a);
 }
 
 #ifdef __x86_64__
@@ -4003,8 +4003,8 @@ static __inline__ void
 ///    A 64-bit integer containing the value to be stored.
 static __inline__ void
     __attribute__((__always_inline__, __nodebug__, __target__("sse2")))
-    _mm_stream_si64(long long *__p, long long __a) {
-  __builtin_ia32_movnti64(__p, __a);
+    _mm_stream_si64(void *__p, long long __a) {
+  __builtin_ia32_movnti64((long long *)__p, __a);
 }
 #endif
 

package/lib/clang/{17 → 18}/include/gfniintrin.h

@@ -15,19 +15,36 @@
 #define __GFNIINTRIN_H
 
 /* Default attributes for simple form (no masking). */
-#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("gfni"), __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("gfni,no-evex512"), __min_vector_width__(128)))
 
 /* Default attributes for YMM unmasked form. */
-#define __DEFAULT_FN_ATTRS_Y __attribute__((__always_inline__, __nodebug__, __target__("avx,gfni"), __min_vector_width__(256)))
+#define __DEFAULT_FN_ATTRS_Y                                                   \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("avx,gfni,no-evex512"),                            \
+                 __min_vector_width__(256)))
 
 /* Default attributes for ZMM unmasked forms. */
-#define __DEFAULT_FN_ATTRS_Z __attribute__((__always_inline__, __nodebug__, __target__("avx512f,gfni"), __min_vector_width__(512)))
+#define __DEFAULT_FN_ATTRS_Z                                                   \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("avx512f,evex512,gfni"),                           \
+                 __min_vector_width__(512)))
 /* Default attributes for ZMM masked forms. */
-#define __DEFAULT_FN_ATTRS_Z_MASK __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,gfni"), __min_vector_width__(512)))
+#define __DEFAULT_FN_ATTRS_Z_MASK                                              \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("avx512bw,evex512,gfni"),                          \
+                 __min_vector_width__(512)))
 
 /* Default attributes for VLX masked forms. */
-#define __DEFAULT_FN_ATTRS_VL128 __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,avx512vl,gfni"), __min_vector_width__(128)))
-#define __DEFAULT_FN_ATTRS_VL256 __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,avx512vl,gfni"), __min_vector_width__(256)))
+#define __DEFAULT_FN_ATTRS_VL128                                               \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("avx512bw,avx512vl,gfni,no-evex512"),              \
+                 __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS_VL256                                               \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("avx512bw,avx512vl,gfni,no-evex512"),              \
+                 __min_vector_width__(256)))
 
 #define _mm_gf2p8affineinv_epi64_epi8(A, B, I) \
   ((__m128i)__builtin_ia32_vgf2p8affineinvqb_v16qi((__v16qi)(__m128i)(A), \