404 Not Found

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

/*===--------------- sm4intrin.h - SM4 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 <sm4intrin.h> directly; include <immintrin.h> instead."
#endif // __IMMINTRIN_H

#ifndef __SM4INTRIN_H
#define __SM4INTRIN_H

/// This intrinsic performs four rounds of SM4 key expansion. The intrinsic
///    operates on independent 128-bit lanes. The calculated results are
///    stored in \a dst.
/// \headerfile <immintrin.h>
///
/// \code
/// __m128i _mm_sm4key4_epi32(__m128i __A, __m128i __B)
/// \endcode
///
/// This intrinsic corresponds to the \c VSM4KEY4 instruction.
///
/// \param __A
///    A 128-bit vector of [4 x int].
/// \param __B
///    A 128-bit vector of [4 x int].
/// \returns
///    A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// DEFINE ROL32(dword, n) {
/// 	count := n % 32
/// 	dest := (dword << count) | (dword >> (32-count))
/// 	RETURN dest
/// }
/// DEFINE SBOX_BYTE(dword, i) {
/// 	RETURN sbox[dword.byte[i]]
/// }
/// DEFINE lower_t(dword) {
/// 	tmp.byte[0] := SBOX_BYTE(dword, 0)
/// 	tmp.byte[1] := SBOX_BYTE(dword, 1)
/// 	tmp.byte[2] := SBOX_BYTE(dword, 2)
/// 	tmp.byte[3] := SBOX_BYTE(dword, 3)
/// 	RETURN tmp
/// }
/// DEFINE L_KEY(dword) {
/// 	RETURN dword ^ ROL32(dword, 13) ^ ROL32(dword, 23)
/// }
/// DEFINE T_KEY(dword) {
/// 	RETURN L_KEY(lower_t(dword))
/// }
/// DEFINE F_KEY(X0, X1, X2, X3, round_key) {
/// 	RETURN X0 ^ T_KEY(X1 ^ X2 ^ X3 ^ round_key)
/// }
/// FOR i:= 0 to 0
/// 	P[0] := __B.xmm[i].dword[0]
/// 	P[1] := __B.xmm[i].dword[1]
/// 	P[2] := __B.xmm[i].dword[2]
/// 	P[3] := __B.xmm[i].dword[3]
/// 	C[0] := F_KEY(P[0], P[1], P[2], P[3], __A.xmm[i].dword[0])
/// 	C[1] := F_KEY(P[1], P[2], P[3], C[0], __A.xmm[i].dword[1])
/// 	C[2] := F_KEY(P[2], P[3], C[0], C[1], __A.xmm[i].dword[2])
/// 	C[3] := F_KEY(P[3], C[0], C[1], C[2], __A.xmm[i].dword[3])
/// 	DEST.xmm[i].dword[0] := C[0]
/// 	DEST.xmm[i].dword[1] := C[1]
/// 	DEST.xmm[i].dword[2] := C[2]
/// 	DEST.xmm[i].dword[3] := C[3]
/// ENDFOR
/// DEST[MAX:128] := 0
/// \endcode
#define _mm_sm4key4_epi32(A, B)                                                \
  (__m128i) __builtin_ia32_vsm4key4128((__v4su)A, (__v4su)B)

/// This intrinsic performs four rounds of SM4 key expansion. The intrinsic
///    operates on independent 128-bit lanes. The calculated results are
///    stored in \a dst.
/// \headerfile <immintrin.h>
///
/// \code
/// __m256i _mm256_sm4key4_epi32(__m256i __A, __m256i __B)
/// \endcode
///
/// This intrinsic corresponds to the \c VSM4KEY4 instruction.
///
/// \param __A
///    A 256-bit vector of [8 x int].
/// \param __B
///    A 256-bit vector of [8 x int].
/// \returns
///    A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// DEFINE ROL32(dword, n) {
/// 	count := n % 32
/// 	dest := (dword << count) | (dword >> (32-count))
/// 	RETURN dest
/// }
/// DEFINE SBOX_BYTE(dword, i) {
/// 	RETURN sbox[dword.byte[i]]
/// }
/// DEFINE lower_t(dword) {
/// 	tmp.byte[0] := SBOX_BYTE(dword, 0)
/// 	tmp.byte[1] := SBOX_BYTE(dword, 1)
/// 	tmp.byte[2] := SBOX_BYTE(dword, 2)
/// 	tmp.byte[3] := SBOX_BYTE(dword, 3)
/// 	RETURN tmp
/// }
/// DEFINE L_KEY(dword) {
/// 	RETURN dword ^ ROL32(dword, 13) ^ ROL32(dword, 23)
/// }
/// DEFINE T_KEY(dword) {
/// 	RETURN L_KEY(lower_t(dword))
/// }
/// DEFINE F_KEY(X0, X1, X2, X3, round_key) {
/// 	RETURN X0 ^ T_KEY(X1 ^ X2 ^ X3 ^ round_key)
/// }
/// FOR i:= 0 to 1
/// 	P[0] := __B.xmm[i].dword[0]
/// 	P[1] := __B.xmm[i].dword[1]
/// 	P[2] := __B.xmm[i].dword[2]
/// 	P[3] := __B.xmm[i].dword[3]
/// 	C[0] := F_KEY(P[0], P[1], P[2], P[3], __A.xmm[i].dword[0])
/// 	C[1] := F_KEY(P[1], P[2], P[3], C[0], __A.xmm[i].dword[1])
/// 	C[2] := F_KEY(P[2], P[3], C[0], C[1], __A.xmm[i].dword[2])
/// 	C[3] := F_KEY(P[3], C[0], C[1], C[2], __A.xmm[i].dword[3])
/// 	DEST.xmm[i].dword[0] := C[0]
/// 	DEST.xmm[i].dword[1] := C[1]
/// 	DEST.xmm[i].dword[2] := C[2]
/// 	DEST.xmm[i].dword[3] := C[3]
/// ENDFOR
/// DEST[MAX:256] := 0
/// \endcode
#define _mm256_sm4key4_epi32(A, B)                                             \
  (__m256i) __builtin_ia32_vsm4key4256((__v8su)A, (__v8su)B)

/// This intrinisc performs four rounds of SM4 encryption. The intrinisc
///    operates on independent 128-bit lanes. The calculated results are
///    stored in \a dst.
/// \headerfile <immintrin.h>
///
/// \code
/// __m128i _mm_sm4rnds4_epi32(__m128i __A, __m128i __B)
/// \endcode
///
/// This intrinsic corresponds to the \c VSM4RNDS4 instruction.
///
/// \param __A
///    A 128-bit vector of [4 x int].
/// \param __B
///    A 128-bit vector of [4 x int].
/// \returns
///    A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// DEFINE ROL32(dword, n) {
/// 	count := n % 32
/// 	dest := (dword << count) | (dword >> (32-count))
/// 	RETURN dest
/// }
/// DEFINE lower_t(dword) {
/// 	tmp.byte[0] := SBOX_BYTE(dword, 0)
/// 	tmp.byte[1] := SBOX_BYTE(dword, 1)
/// 	tmp.byte[2] := SBOX_BYTE(dword, 2)
/// 	tmp.byte[3] := SBOX_BYTE(dword, 3)
/// 	RETURN tmp
/// }
/// DEFINE L_RND(dword) {
/// 	tmp := dword
/// 	tmp := tmp ^ ROL32(dword, 2)
/// 	tmp := tmp ^ ROL32(dword, 10)
/// 	tmp := tmp ^ ROL32(dword, 18)
/// 	tmp := tmp ^ ROL32(dword, 24)
///   RETURN tmp
/// }
/// DEFINE T_RND(dword) {
/// 	RETURN L_RND(lower_t(dword))
/// }
/// DEFINE F_RND(X0, X1, X2, X3, round_key) {
/// 	RETURN X0 ^ T_RND(X1 ^ X2 ^ X3 ^ round_key)
/// }
/// FOR i:= 0 to 0
/// 	P[0] := __B.xmm[i].dword[0]
/// 	P[1] := __B.xmm[i].dword[1]
/// 	P[2] := __B.xmm[i].dword[2]
/// 	P[3] := __B.xmm[i].dword[3]
/// 	C[0] := F_RND(P[0], P[1], P[2], P[3], __A.xmm[i].dword[0])
/// 	C[1] := F_RND(P[1], P[2], P[3], C[0], __A.xmm[i].dword[1])
/// 	C[2] := F_RND(P[2], P[3], C[0], C[1], __A.xmm[i].dword[2])
/// 	C[3] := F_RND(P[3], C[0], C[1], C[2], __A.xmm[i].dword[3])
/// 	DEST.xmm[i].dword[0] := C[0]
/// 	DEST.xmm[i].dword[1] := C[1]
/// 	DEST.xmm[i].dword[2] := C[2]
/// 	DEST.xmm[i].dword[3] := C[3]
/// ENDFOR
/// DEST[MAX:128] := 0
/// \endcode
#define _mm_sm4rnds4_epi32(A, B)                                               \
  (__m128i) __builtin_ia32_vsm4rnds4128((__v4su)A, (__v4su)B)

/// This intrinisc performs four rounds of SM4 encryption. The intrinisc
///    operates on independent 128-bit lanes. The calculated results are
///    stored in \a dst.
/// \headerfile <immintrin.h>
///
/// \code
/// __m256i _mm256_sm4rnds4_epi32(__m256i __A, __m256i __B)
/// \endcode
///
/// This intrinsic corresponds to the \c VSM4RNDS4 instruction.
///
/// \param __A
///    A 256-bit vector of [8 x int].
/// \param __B
///    A 256-bit vector of [8 x int].
/// \returns
///    A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// DEFINE ROL32(dword, n) {
/// 	count := n % 32
/// 	dest := (dword << count) | (dword >> (32-count))
/// 	RETURN dest
/// }
/// DEFINE lower_t(dword) {
/// 	tmp.byte[0] := SBOX_BYTE(dword, 0)
/// 	tmp.byte[1] := SBOX_BYTE(dword, 1)
/// 	tmp.byte[2] := SBOX_BYTE(dword, 2)
/// 	tmp.byte[3] := SBOX_BYTE(dword, 3)
/// 	RETURN tmp
/// }
/// DEFINE L_RND(dword) {
/// 	tmp := dword
/// 	tmp := tmp ^ ROL32(dword, 2)
/// 	tmp := tmp ^ ROL32(dword, 10)
/// 	tmp := tmp ^ ROL32(dword, 18)
/// 	tmp := tmp ^ ROL32(dword, 24)
///   RETURN tmp
/// }
/// DEFINE T_RND(dword) {
/// 	RETURN L_RND(lower_t(dword))
/// }
/// DEFINE F_RND(X0, X1, X2, X3, round_key) {
/// 	RETURN X0 ^ T_RND(X1 ^ X2 ^ X3 ^ round_key)
/// }
/// FOR i:= 0 to 0
/// 	P[0] := __B.xmm[i].dword[0]
/// 	P[1] := __B.xmm[i].dword[1]
/// 	P[2] := __B.xmm[i].dword[2]
/// 	P[3] := __B.xmm[i].dword[3]
/// 	C[0] := F_RND(P[0], P[1], P[2], P[3], __A.xmm[i].dword[0])
/// 	C[1] := F_RND(P[1], P[2], P[3], C[0], __A.xmm[i].dword[1])
/// 	C[2] := F_RND(P[2], P[3], C[0], C[1], __A.xmm[i].dword[2])
/// 	C[3] := F_RND(P[3], C[0], C[1], C[2], __A.xmm[i].dword[3])
/// 	DEST.xmm[i].dword[0] := C[0]
/// 	DEST.xmm[i].dword[1] := C[1]
/// 	DEST.xmm[i].dword[2] := C[2]
/// 	DEST.xmm[i].dword[3] := C[3]
/// ENDFOR
/// DEST[MAX:256] := 0
/// \endcode
#define _mm256_sm4rnds4_epi32(A, B)                                            \
  (__m256i) __builtin_ia32_vsm4rnds4256((__v8su)A, (__v8su)B)

#endif // __SM4INTRIN_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]