404 Not Found

PATH: lib64 / llvm17 / lib / clang / 17 / include

/*===---- bmiintrin.h - BMI 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
 *
 *===-----------------------------------------------------------------------===
 */

#if !defined __X86INTRIN_H && !defined __IMMINTRIN_H
#error "Never use <bmiintrin.h> directly; include <x86intrin.h> instead."
#endif

#ifndef __BMIINTRIN_H
#define __BMIINTRIN_H

/* Allow using the tzcnt intrinsics even for non-BMI targets. Since the TZCNT
   instruction behaves as BSF on non-BMI targets, there is code that expects
   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.
///
/// \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.
static __inline__ unsigned short __RELAXED_FN_ATTRS
__tzcnt_u16(unsigned short __X)
{
  return __builtin_ia32_tzcnt_u16(__X);
}

/// Counts the number of trailing zero bits in the operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> TZCNT </c> 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
static __inline__ unsigned int __RELAXED_FN_ATTRS
__tzcnt_u32(unsigned int __X)
{
  return __builtin_ia32_tzcnt_u32(__X);
}

/// Counts the number of trailing zero bits in the operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> TZCNT </c> 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
///    the operand.
/// \see __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)))

#ifdef __x86_64__

/// Counts the number of trailing zero bits in the operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> TZCNT </c> 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
static __inline__ unsigned long long __RELAXED_FN_ATTRS
__tzcnt_u64(unsigned long long __X)
{
  return __builtin_ia32_tzcnt_u64(__X);
}

/// Counts the number of trailing zero bits in the operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> TZCNT </c> 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
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)))

#endif /* __x86_64__ */

#undef __RELAXED_FN_ATTRS

#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
    defined(__BMI__)

/* 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.
///
/// \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.
static __inline__ unsigned int __DEFAULT_FN_ATTRS
__andn_u32(unsigned int __X, unsigned int __Y)
{
  return ~__X & __Y;
}

/* 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.
///
/// \param __X
///    An unsigned integer whose bits are to be extracted.
/// \param __Y
///    An unsigned integer used to specify which bits are extracted. Bits [7:0]
///    specify the index of the least significant bit. Bits [15:8] specify the
///    number of bits to be extracted.
/// \returns An unsigned integer whose least significant bits contain the
///    extracted bits.
/// \see _bextr_u32
static __inline__ unsigned int __DEFAULT_FN_ATTRS
__bextr_u32(unsigned int __X, unsigned int __Y)
{
  return __builtin_ia32_bextr_u32(__X, __Y);
}

/* Intel-specified, single-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.
///
/// \param __X
///    An unsigned integer whose bits are to be extracted.
/// \param __Y
///    An unsigned integer used to specify the index of the least significant
///    bit for the bits to be extracted. Bits [7:0] specify the index.
/// \param __Z
///    An unsigned integer used to specify the number of bits to be extracted.
///    Bits [7:0] specify the number of bits.
/// \returns An unsigned integer whose least significant bits contain the
///    extracted bits.
/// \see __bextr_u32
static __inline__ unsigned int __DEFAULT_FN_ATTRS
_bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z)
{
  return __builtin_ia32_bextr_u32 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
}

/* Intel-specified, single-leading-underscore version of BEXTR2 */
/// 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.
///
/// \param __X
///    An unsigned integer whose bits are to be extracted.
/// \param __Y
///    An unsigned integer used to specify which bits are extracted. Bits [7:0]
///    specify the index of the least significant bit. Bits [15:8] specify the
///    number of bits to be extracted.
/// \returns An unsigned integer whose least significant bits contain the
///    extracted bits.
/// \see __bextr_u32
static __inline__ unsigned int __DEFAULT_FN_ATTRS
_bextr2_u32(unsigned int __X, unsigned int __Y) {
  return __builtin_ia32_bextr_u32(__X, __Y);
}

/// Clears all bits in the source except for the least significant bit
///    containing a value of 1 and returns the result.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> BLSI </c> 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.
static __inline__ unsigned int __DEFAULT_FN_ATTRS
__blsi_u32(unsigned int __X)
{
  return __X & -__X;
}

/// 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.
///
/// \param __X
///    An unsigned integer used to create the mask.
/// \returns An unsigned integer containing the newly created mask.
static __inline__ unsigned int __DEFAULT_FN_ATTRS
__blsmsk_u32(unsigned int __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>
///
/// This intrinsic corresponds to the <c> BLSR </c> instruction.
///
/// \param __X
///    An unsigned integer containing the operand to be cleared.
/// \returns An unsigned integer containing the result of clearing the source
///    operand.
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)))

#define _blsr_u64(a)      (__blsr_u64((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.
///
/// \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.
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
__andn_u64 (unsigned long long __X, unsigned long long __Y)
{
  return ~__X & __Y;
}

/* 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.
///
/// \param __X
///    An unsigned 64-bit integer whose bits are to be extracted.
/// \param __Y
///    An unsigned 64-bit integer used to specify which bits are extracted. Bits
///    [7:0] specify the index of the least significant bit. Bits [15:8] specify
///    the number of bits to be extracted.
/// \returns An unsigned 64-bit integer whose least significant bits contain the
///    extracted bits.
/// \see _bextr_u64
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
__bextr_u64(unsigned long long __X, unsigned long long __Y)
{
  return __builtin_ia32_bextr_u64(__X, __Y);
}

/* Intel-specified, single-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.
///
/// \param __X
///    An unsigned 64-bit integer whose bits are to be extracted.
/// \param __Y
///    An unsigned integer used to specify the index of the least significant
///    bit for the bits to be extracted. Bits [7:0] specify the index.
/// \param __Z
///    An unsigned integer used to specify the number of bits to be extracted.
///    Bits [7:0] specify the number of bits.
/// \returns An unsigned 64-bit integer whose least significant bits contain the
///    extracted bits.
/// \see __bextr_u64
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
_bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z)
{
  return __builtin_ia32_bextr_u64 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
}

/* Intel-specified, single-leading-underscore version of BEXTR2 */
/// 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.
///
/// \param __X
///    An unsigned 64-bit integer whose bits are to be extracted.
/// \param __Y
///    An unsigned 64-bit integer used to specify which bits are extracted. Bits
///    [7:0] specify the index of the least significant bit. Bits [15:8] specify
///    the number of bits to be extracted.
/// \returns An unsigned 64-bit integer whose least significant bits contain the
///    extracted bits.
/// \see __bextr_u64
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
_bextr2_u64(unsigned long long __X, unsigned long long __Y) {
  return __builtin_ia32_bextr_u64(__X, __Y);
}

/// Clears all bits in the source except for the least significant bit
///    containing a value of 1 and returns the result.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> BLSI </c> 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.
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
__blsi_u64(unsigned long long __X)
{
  return __X & -__X;
}

/// 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.
///
/// \param __X
///    An unsigned 64-bit integer used to create the mask.
/// \returns An unsigned 64-bit integer containing the newly created mask.
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
__blsmsk_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>
///
/// This intrinsic corresponds to the <c> BLSR </c> 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.
static __inline__ unsigned long long __DEFAULT_FN_ATTRS
__blsr_u64(unsigned long long __X)
{
  return __X & (__X - 1);
}

#endif /* __x86_64__ */

#undef __DEFAULT_FN_ATTRS

#endif /* !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules)   \
          || defined(__BMI__) */

#endif /* __BMIINTRIN_H */

[+] ..
[-] riscv_ntlh.h [edit]
[-] avx512vlbitalgintrin.h [edit]
[-] avxifmaintrin.h [edit]
[-] mm_malloc.h [edit]
[-] avx512vlbf16intrin.h [edit]
[-] mwaitxintrin.h [edit]
[-] adxintrin.h [edit]
[-] arm_cmse.h [edit]
[-] __clang_cuda_intrinsics.h [edit]
[-] module.modulemap [edit]
[-] crc32intrin.h [edit]
[+] cuda_wrappers
[-] msa.h [edit]
[-] __clang_hip_stdlib.h [edit]
[-] arm_acle.h [edit]
[-] arm_neon_sve_bridge.h [edit]
[-] xsaveintrin.h [edit]
[-] velintrin_gen.h [edit]
[-] stdatomic.h [edit]
[-] hvx_hexagon_protos.h [edit]
[-] uintrintrin.h [edit]
[-] fxsrintrin.h [edit]
[-] sha512intrin.h [edit]
[-] __clang_cuda_texture_intrinsics.h [edit]
[-] iso646.h [edit]
[-] unwind.h [edit]
[-] avx512vlbwintrin.h [edit]
[-] avxvnniint8intrin.h [edit]
[-] avx512erintrin.h [edit]
[-] avxvnniintrin.h [edit]
[-] ia32intrin.h [edit]
[-] rdseedintrin.h [edit]
[-] prfchiintrin.h [edit]
[-] amxcomplexintrin.h [edit]
[-] clflushoptintrin.h [edit]
[-] htmxlintrin.h [edit]
[-] avx512fintrin.h [edit]
[-] gfniintrin.h [edit]
[-] arm_cde.h [edit]
[+] ppc_wrappers
[-] amxfp16intrin.h [edit]
[-] velintrin_approx.h [edit]
[-] avx512pfintrin.h [edit]
[-] stdarg.h [edit]
[-] cmpccxaddintrin.h [edit]
[-] avx512vlintrin.h [edit]
[-] __clang_hip_math.h [edit]
[-] vecintrin.h [edit]
[-] xtestintrin.h [edit]
[-] __wmmintrin_aes.h [edit]
[-] arm_neon.h [edit]
[-] immintrin.h [edit]
[-] ammintrin.h [edit]
[-] waitpkgintrin.h [edit]
[-] vpclmulqdqintrin.h [edit]
[-] fmaintrin.h [edit]
[-] tsxldtrkintrin.h [edit]
[-] prfchwintrin.h [edit]
[-] avx512bitalgintrin.h [edit]
[-] bmiintrin.h [edit]
[-] __wmmintrin_pclmul.h [edit]
[-] htmintrin.h [edit]
[-] mm3dnow.h [edit]
[-] __clang_cuda_builtin_vars.h [edit]
[-] __clang_hip_runtime_wrapper.h [edit]
[-] stdbool.h [edit]
[-] altivec.h [edit]
[-] wbnoinvdintrin.h [edit]
[-] keylockerintrin.h [edit]
[-] tgmath.h [edit]
[-] hexagon_circ_brev_intrinsics.h [edit]
[-] x86intrin.h [edit]
[-] pkuintrin.h [edit]
[-] avx512vbmivlintrin.h [edit]
[-] avxneconvertintrin.h [edit]
[-] __clang_hip_cmath.h [edit]
[-] sgxintrin.h [edit]
[-] f16cintrin.h [edit]
[-] opencl-c-base.h [edit]
[-] cpuid.h [edit]
[-] raointintrin.h [edit]
[-] builtins.h [edit]
[-] emmintrin.h [edit]
[-] smmintrin.h [edit]
[-] vaesintrin.h [edit]
[-] larchintrin.h [edit]
[-] avx512ifmaintrin.h [edit]
[-] intrin.h [edit]
[-] avx512vlvp2intersectintrin.h [edit]
[-] fma4intrin.h [edit]
[-] pmmintrin.h [edit]
[-] __clang_hip_libdevice_declares.h [edit]
[-] limits.h [edit]
[-] clwbintrin.h [edit]
[-] rtmintrin.h [edit]
[-] mmintrin.h [edit]
[-] stddef.h [edit]
[-] invpcidintrin.h [edit]
[-] avx512vp2intersectintrin.h [edit]
[-] cet.h [edit]
[-] xopintrin.h [edit]
[-] avx512vlvnniintrin.h [edit]
[-] avx512vlfp16intrin.h [edit]
[-] stdint.h [edit]
[-] arm64intr.h [edit]
[-] sm4intrin.h [edit]
[-] avx512vnniintrin.h [edit]
[-] avx2intrin.h [edit]
[-] movdirintrin.h [edit]
[-] tbmintrin.h [edit]
[-] arm_mve.h [edit]
[-] avx512ifmavlintrin.h [edit]
[-] amxintrin.h [edit]
[-] opencl-c.h [edit]
[-] stdalign.h [edit]
[-] __clang_cuda_device_functions.h [edit]
[-] pconfigintrin.h [edit]
[-] avx512fp16intrin.h [edit]
[-] inttypes.h [edit]
[-] arm_bf16.h [edit]
[-] __clang_cuda_math_forward_declares.h [edit]
[-] vadefs.h [edit]
[-] shaintrin.h [edit]
[-] hexagon_protos.h [edit]
[-] ptwriteintrin.h [edit]
[-] xsaveoptintrin.h [edit]
[-] enqcmdintrin.h [edit]
[-] x86gprintrin.h [edit]
[-] tmmintrin.h [edit]
[-] stdnoreturn.h [edit]
[-] avx512bf16intrin.h [edit]
[-] varargs.h [edit]
[-] s390intrin.h [edit]
[-] avx512vbmiintrin.h [edit]
[+] openmp_wrappers
[-] wmmintrin.h [edit]
[-] __clang_cuda_cmath.h [edit]
[-] clzerointrin.h [edit]
[-] xsavesintrin.h [edit]
[-] __clang_cuda_libdevice_declares.h [edit]
[-] nmmintrin.h [edit]
[-] wasm_simd128.h [edit]
[-] xsavecintrin.h [edit]
[-] avx512dqintrin.h [edit]
[-] lwpintrin.h [edit]
[-] serializeintrin.h [edit]
[-] arm_sme_draft_spec_subject_to_change.h [edit]
[-] avxintrin.h [edit]
[-] __stddef_max_align_t.h [edit]
[-] sm3intrin.h [edit]
[-] velintrin.h [edit]
[-] __clang_cuda_complex_builtins.h [edit]
[-] armintr.h [edit]
[-] avx512cdintrin.h [edit]
[-] float.h [edit]
[-] avx512vbmi2intrin.h [edit]
[-] lzcntintrin.h [edit]
[-] sifive_vector.h [edit]
[-] rdpruintrin.h [edit]
[-] arm_sve.h [edit]
[-] avx512vpopcntdqintrin.h [edit]
[-] xmmintrin.h [edit]
[-] hresetintrin.h [edit]
[-] bmi2intrin.h [edit]
[-] hexagon_types.h [edit]
[-] avx512bwintrin.h [edit]
[-] cetintrin.h [edit]
[-] __clang_cuda_math.h [edit]
[-] avx512vlvbmi2intrin.h [edit]
[-] arm_fp16.h [edit]
[-] avx512vpopcntdqvlintrin.h [edit]
[-] avxvnniint16intrin.h [edit]
[+] llvm_libc_wrappers
[-] __clang_cuda_runtime_wrapper.h [edit]
[-] cldemoteintrin.h [edit]
[-] avx512vldqintrin.h [edit]
[-] avx512vlcdintrin.h [edit]
[-] popcntintrin.h [edit]