4 * Copyright(c) 2016-2017 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.
35 * This file holds all x86 specific EFD functions
37 #include <immintrin.h>
39 #if (RTE_EFD_VALUE_NUM_BITS == 8 || RTE_EFD_VALUE_NUM_BITS == 16 || \
40 RTE_EFD_VALUE_NUM_BITS == 24 || RTE_EFD_VALUE_NUM_BITS == 32)
41 #define EFD_LOAD_SI128(val) _mm_load_si128(val)
43 #define EFD_LOAD_SI128(val) _mm_lddqu_si128(val)
46 static inline efd_value_t
47 efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
48 const efd_lookuptbl_t *group_lookup_table,
49 const uint32_t hash_val_a, const uint32_t hash_val_b)
51 #ifdef RTE_MACHINE_CPUFLAG_AVX2
52 efd_value_t value = 0;
54 __m256i vhash_val_a = _mm256_set1_epi32(hash_val_a);
55 __m256i vhash_val_b = _mm256_set1_epi32(hash_val_b);
57 for (; i < RTE_EFD_VALUE_NUM_BITS; i += 8) {
59 _mm256_cvtepu16_epi32(EFD_LOAD_SI128(
60 (__m128i const *) &group_hash_idx[i]));
61 __m256i vlookup_table = _mm256_cvtepu16_epi32(
62 EFD_LOAD_SI128((__m128i const *)
63 &group_lookup_table[i]));
64 __m256i vhash = _mm256_add_epi32(vhash_val_a,
65 _mm256_mullo_epi32(vhash_idx, vhash_val_b));
66 __m256i vbucket_idx = _mm256_srli_epi32(vhash,
68 __m256i vresult = _mm256_srlv_epi32(vlookup_table,
71 value |= (_mm256_movemask_ps(
72 (__m256) _mm256_slli_epi32(vresult, 31))
73 & ((1 << (RTE_EFD_VALUE_NUM_BITS - i)) - 1)) << i;
78 RTE_SET_USED(group_hash_idx);
79 RTE_SET_USED(group_lookup_table);
80 RTE_SET_USED(hash_val_a);
81 RTE_SET_USED(hash_val_b);
82 /* Return dummy value, only to avoid compilation breakage */