4 * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
11 * * Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * * Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in
15 * the documentation and/or other materials provided with the
17 * * Neither the name of Intel Corporation nor the names of its
18 * contributors may be used to endorse or promote products derived
19 * from this software without specific prior written permission.
21 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 #ifndef _RTE_ACL_VECT_H_
35 #define _RTE_ACL_VECT_H_
40 * RTE ACL SSE/AVX related header.
47 #define MM_ADD16(a, b) _mm_add_epi16(a, b)
48 #define MM_ADD32(a, b) _mm_add_epi32(a, b)
49 #define MM_ALIGNR8(a, b, c) _mm_alignr_epi8(a, b, c)
50 #define MM_AND(a, b) _mm_and_si128(a, b)
51 #define MM_ANDNOT(a, b) _mm_andnot_si128(a, b)
52 #define MM_BLENDV8(a, b, c) _mm_blendv_epi8(a, b, c)
53 #define MM_CMPEQ16(a, b) _mm_cmpeq_epi16(a, b)
54 #define MM_CMPEQ32(a, b) _mm_cmpeq_epi32(a, b)
55 #define MM_CMPEQ8(a, b) _mm_cmpeq_epi8(a, b)
56 #define MM_CMPGT32(a, b) _mm_cmpgt_epi32(a, b)
57 #define MM_CMPGT8(a, b) _mm_cmpgt_epi8(a, b)
58 #define MM_CVT(a) _mm_cvtsi32_si128(a)
59 #define MM_CVT32(a) _mm_cvtsi128_si32(a)
60 #define MM_CVTU32(a) _mm_cvtsi32_si128(a)
61 #define MM_INSERT16(a, c, b) _mm_insert_epi16(a, c, b)
62 #define MM_INSERT32(a, c, b) _mm_insert_epi32(a, c, b)
63 #define MM_LOAD(a) _mm_load_si128(a)
64 #define MM_LOADH_PI(a, b) _mm_loadh_pi(a, b)
65 #define MM_LOADU(a) _mm_loadu_si128(a)
66 #define MM_MADD16(a, b) _mm_madd_epi16(a, b)
67 #define MM_MADD8(a, b) _mm_maddubs_epi16(a, b)
68 #define MM_MOVEMASK8(a) _mm_movemask_epi8(a)
69 #define MM_OR(a, b) _mm_or_si128(a, b)
70 #define MM_SET1_16(a) _mm_set1_epi16(a)
71 #define MM_SET1_32(a) _mm_set1_epi32(a)
72 #define MM_SET1_64(a) _mm_set1_epi64(a)
73 #define MM_SET1_8(a) _mm_set1_epi8(a)
74 #define MM_SET32(a, b, c, d) _mm_set_epi32(a, b, c, d)
75 #define MM_SHUFFLE32(a, b) _mm_shuffle_epi32(a, b)
76 #define MM_SHUFFLE8(a, b) _mm_shuffle_epi8(a, b)
77 #define MM_SHUFFLEPS(a, b, c) _mm_shuffle_ps(a, b, c)
78 #define MM_SIGN8(a, b) _mm_sign_epi8(a, b)
79 #define MM_SLL64(a, b) _mm_sll_epi64(a, b)
80 #define MM_SRL128(a, b) _mm_srli_si128(a, b)
81 #define MM_SRL16(a, b) _mm_srli_epi16(a, b)
82 #define MM_SRL32(a, b) _mm_srli_epi32(a, b)
83 #define MM_STORE(a, b) _mm_store_si128(a, b)
84 #define MM_STOREU(a, b) _mm_storeu_si128(a, b)
85 #define MM_TESTZ(a, b) _mm_testz_si128(a, b)
86 #define MM_XOR(a, b) _mm_xor_si128(a, b)
88 #define MM_SET16(a, b, c, d, e, f, g, h) \
89 _mm_set_epi16(a, b, c, d, e, f, g, h)
91 #define MM_SET8(c0, c1, c2, c3, c4, c5, c6, c7, \
92 c8, c9, cA, cB, cC, cD, cE, cF) \
93 _mm_set_epi8(c0, c1, c2, c3, c4, c5, c6, c7, \
94 c8, c9, cA, cB, cC, cD, cE, cF)
96 #ifdef RTE_ARCH_X86_64
98 #define MM_CVT64(a) _mm_cvtsi128_si64(a)
102 #define MM_CVT64(a) ({ \
108 #endif /*RTE_ARCH_X86_64 */
111 * Prior to version 12.1 icc doesn't support _mm_set_epi64x.
113 #if (defined(__ICC) && __ICC < 1210)
115 #define MM_SET64(a, b) ({ \
124 #define MM_SET64(a, b) _mm_set_epi64x(a, b)
126 #endif /* (defined(__ICC) && __ICC < 1210) */
132 #endif /* _RTE_ACL_VECT_H_ */