opencv/3rdparty/zlib-ng/arch/arm/slide_hash_neon.c
FantasqueX 85923c8f30
Merge pull request #26113 from FantasqueX:zlib-ng-2-2-1
Update zlib-ng to 2.2.1 #26113

Release: https://github.com/zlib-ng/zlib-ng/releases/tag/2.2.1
ARM diagnostics patch: https://github.com/zlib-ng/zlib-ng/pull/1774

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2024-09-12 16:05:24 +03:00

47 lines
1.3 KiB
C

/* slide_hash_neon.c -- Optimized hash table shifting for ARM with support for NEON instructions
* Copyright (C) 2017-2020 Mika T. Lindqvist
*
* Authors:
* Mika T. Lindqvist <postmaster@raasu.org>
* Jun He <jun.he@arm.com>
*
* For conditions of distribution and use, see copyright notice in zlib.h
*/
#ifdef ARM_NEON
#include "neon_intrins.h"
#include "zbuild.h"
#include "deflate.h"
/* SIMD version of hash_chain rebase */
static inline void slide_hash_chain(Pos *table, uint32_t entries, uint16_t wsize) {
Z_REGISTER uint16x8_t v;
uint16x8x4_t p0, p1;
Z_REGISTER size_t n;
size_t size = entries*sizeof(table[0]);
Assert((size % sizeof(uint16x8_t) * 8 == 0), "hash table size err");
Assert(sizeof(Pos) == 2, "Wrong Pos size");
v = vdupq_n_u16(wsize);
n = size / (sizeof(uint16x8_t) * 8);
do {
p0 = vld1q_u16_x4(table);
p1 = vld1q_u16_x4(table+32);
vqsubq_u16_x4_x1(p0, p0, v);
vqsubq_u16_x4_x1(p1, p1, v);
vst1q_u16_x4(table, p0);
vst1q_u16_x4(table+32, p1);
table += 64;
} while (--n);
}
Z_INTERNAL void slide_hash_neon(deflate_state *s) {
unsigned int wsize = s->w_size;
slide_hash_chain(s->head, HASH_SIZE, wsize);
slide_hash_chain(s->prev, wsize, wsize);
}
#endif