/*
 * Copyright (c) 2021, 2023, Intel Corporation. All rights reserved.
 * Copyright (c) 2021 Serge Sans Paille. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.
 *
 * This code is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have any
 * questions.
 *
 */

// This implementation is based on x86-simd-sort(https://github.com/intel/x86-simd-sort)

#ifndef XSS_COMMON_INCLUDES
#define XSS_COMMON_INCLUDES
#include <algorithm>
#include <cmath>
#include <cstdint>
#include <cstring>
/*
Workaround for the bug in GCC12 (that was fixed in GCC 12.3.1).
More details are available at:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105593
*/
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
#pragma GCC diagnostic ignored "-Wuninitialized"
#include <immintrin.h>
#pragma GCC diagnostic pop
#include <limits>
#include <vector>

#define X86_SIMD_SORT_INFINITY std::numeric_limits<double>::infinity()
#define X86_SIMD_SORT_INFINITYF std::numeric_limits<float>::infinity()
#define X86_SIMD_SORT_INFINITYH 0x7c00
#define X86_SIMD_SORT_NEGINFINITYH 0xfc00
#define X86_SIMD_SORT_MAX_UINT16 std::numeric_limits<uint16_t>::max()
#define X86_SIMD_SORT_MAX_INT16 std::numeric_limits<int16_t>::max()
#define X86_SIMD_SORT_MIN_INT16 std::numeric_limits<int16_t>::min()
#define X86_SIMD_SORT_MAX_UINT32 std::numeric_limits<uint32_t>::max()
#define X86_SIMD_SORT_MAX_INT32 std::numeric_limits<int32_t>::max()
#define X86_SIMD_SORT_MIN_INT32 std::numeric_limits<int32_t>::min()
#define X86_SIMD_SORT_MAX_UINT64 std::numeric_limits<uint64_t>::max()
#define X86_SIMD_SORT_MAX_INT64 std::numeric_limits<int64_t>::max()
#define X86_SIMD_SORT_MIN_INT64 std::numeric_limits<int64_t>::min()
#define ZMM_MAX_DOUBLE _mm512_set1_pd(X86_SIMD_SORT_INFINITY)
#define ZMM_MAX_UINT64 _mm512_set1_epi64(X86_SIMD_SORT_MAX_UINT64)
#define ZMM_MAX_INT64 _mm512_set1_epi64(X86_SIMD_SORT_MAX_INT64)
#define ZMM_MAX_FLOAT _mm512_set1_ps(X86_SIMD_SORT_INFINITYF)
#define ZMM_MAX_UINT _mm512_set1_epi32(X86_SIMD_SORT_MAX_UINT32)
#define ZMM_MAX_INT _mm512_set1_epi32(X86_SIMD_SORT_MAX_INT32)
#define ZMM_MAX_HALF _mm512_set1_epi16(X86_SIMD_SORT_INFINITYH)
#define YMM_MAX_HALF _mm256_set1_epi16(X86_SIMD_SORT_INFINITYH)
#define ZMM_MAX_UINT16 _mm512_set1_epi16(X86_SIMD_SORT_MAX_UINT16)
#define ZMM_MAX_INT16 _mm512_set1_epi16(X86_SIMD_SORT_MAX_INT16)
#define SHUFFLE_MASK(a, b, c, d) (a << 6) | (b << 4) | (c << 2) | d

#define PRAGMA(x) _Pragma(#x)
#define UNUSED(x) (void)(x)

/* Compiler specific macros specific */
#if defined(__GNUC__)
#define X86_SIMD_SORT_INLINE static inline
#define X86_SIMD_SORT_FINLINE static inline __attribute__((always_inline))
#else
#define X86_SIMD_SORT_INLINE static
#define X86_SIMD_SORT_FINLINE static
#endif

#if __GNUC__ >= 8
#define X86_SIMD_SORT_UNROLL_LOOP(num) PRAGMA(GCC unroll num)
#else
#define X86_SIMD_SORT_UNROLL_LOOP(num)
#endif

typedef size_t arrsize_t;

template <typename type>
struct zmm_vector;

template <typename type>
struct ymm_vector;

template <typename type>
struct avx2_vector;

#endif // XSS_COMMON_INCLUDES