4 * Copyright (C) Cavium, Inc. 2017.
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
10 * * Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * * Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in
14 * the documentation and/or other materials provided with the
16 * * Neither the name of Cavium, Inc nor the names of its
17 * contributors may be used to endorse or promote products derived
18 * from this software without specific prior written permission.
20 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
21 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
22 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
23 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
24 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
25 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
26 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
27 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
28 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
29 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
30 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
35 * This file holds all arm64 specific EFD functions
38 #ifndef __RTE_EFD_ARM64_H__
39 #define __RTE_EFD_ARM64_H__
43 static inline efd_value_t
44 efd_lookup_internal_neon(const efd_hashfunc_t *group_hash_idx,
45 const efd_lookuptbl_t *group_lookup_table,
46 const uint32_t hash_val_a, const uint32_t hash_val_b)
48 efd_value_t value = 0;
50 uint32x4_t vhash_val_a = vmovq_n_u32(hash_val_a);
51 uint32x4_t vhash_val_b = vmovq_n_u32(hash_val_b);
52 int32x4_t vshift = {0, 1, 2, 3};
53 uint32x4_t vmask = vdupq_n_u32(0x1);
54 int32x4_t vincr = vdupq_n_s32(4);
56 for (; i < RTE_EFD_VALUE_NUM_BITS; i += 4) {
57 uint32x4_t vhash_idx = vshll_n_u16(
58 vld1_u16((uint16_t const *)&group_hash_idx[i]), 0);
59 uint32x4_t vlookup_table = vshll_n_u16(
60 vld1_u16((uint16_t const *)&group_lookup_table[i]), 0);
61 uint32x4_t vhash = vaddq_u32(vhash_val_a,
62 vmulq_u32(vhash_idx, vhash_val_b));
63 int32x4_t vbucket_idx = vnegq_s32(vreinterpretq_s32_u32(
64 vshrq_n_u32(vhash, EFD_LOOKUPTBL_SHIFT)));
65 uint32x4_t vresult = vshlq_u32(vlookup_table, vbucket_idx);
67 vresult = vandq_u32(vresult, vmask);
68 vresult = vshlq_u32(vresult, vshift);
69 value |= vaddvq_u32(vresult);
70 vshift = vaddq_s32(vshift, vincr);
76 #endif /* __RTE_EFD_ARM64_H__ */