Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

deps: fix zlib compilation for CPUs without SIMD features #32627

Closed
wants to merge 1 commit into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions deps/zlib/adler32_simd.c
Original file line number Diff line number Diff line change
Expand Up @@ -50,9 +50,13 @@
#define NMAX 5552

#if defined(ADLER32_SIMD_SSSE3)
#ifndef __GNUC__
#define __attribute__()
#endif

#include <tmmintrin.h>

__attribute__((target("ssse3")))
uint32_t ZLIB_INTERNAL adler32_simd_( /* SSSE3 */
uint32_t adler,
const unsigned char *buf,
Expand Down
4 changes: 4 additions & 0 deletions deps/zlib/crc32_simd.c
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,9 @@
#include "crc32_simd.h"

#if defined(CRC32_SIMD_SSE42_PCLMUL)
#ifndef __GNUC__
#define __attribute__()
#endif

/*
* crc32_sse42_simd_(): compute the crc32 of the buffer, where the buffer
Expand All @@ -21,6 +24,7 @@
#include <smmintrin.h>
#include <wmmintrin.h>

__attribute__((target("sse4.2,pclmul")))
uint32_t ZLIB_INTERNAL crc32_sse42_simd_( /* SSE4.2+PCLMUL */
const unsigned char *buf,
z_size_t len,
Expand Down
12 changes: 12 additions & 0 deletions deps/zlib/crc_folding.c
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,10 @@
#include <immintrin.h>
#include <wmmintrin.h>

#ifndef __GNUC__
#define __attribute__()
#endif

#define CRC_LOAD(s) \
do { \
__m128i xmm_crc0 = _mm_loadu_si128((__m128i *)s->crc0 + 0);\
Expand All @@ -39,6 +43,7 @@
_mm_storeu_si128((__m128i *)s->crc0 + 4, xmm_crc_part);\
} while (0);

__attribute__((target("sse4.2,pclmul")))
ZLIB_INTERNAL void crc_fold_init(deflate_state *const s)
{
CRC_LOAD(s)
Expand All @@ -53,6 +58,7 @@ ZLIB_INTERNAL void crc_fold_init(deflate_state *const s)
s->strm->adler = 0;
}

__attribute__((target("sse4.2,pclmul")))
local void fold_1(deflate_state *const s,
__m128i *xmm_crc0, __m128i *xmm_crc1,
__m128i *xmm_crc2, __m128i *xmm_crc3)
Expand All @@ -79,6 +85,7 @@ local void fold_1(deflate_state *const s,
*xmm_crc3 = _mm_castps_si128(ps_res);
}

__attribute__((target("sse4.2,pclmul")))
local void fold_2(deflate_state *const s,
__m128i *xmm_crc0, __m128i *xmm_crc1,
__m128i *xmm_crc2, __m128i *xmm_crc3)
Expand Down Expand Up @@ -113,6 +120,7 @@ local void fold_2(deflate_state *const s,
*xmm_crc3 = _mm_castps_si128(ps_res31);
}

__attribute__((target("sse4.2,pclmul")))
local void fold_3(deflate_state *const s,
__m128i *xmm_crc0, __m128i *xmm_crc1,
__m128i *xmm_crc2, __m128i *xmm_crc3)
Expand Down Expand Up @@ -153,6 +161,7 @@ local void fold_3(deflate_state *const s,
*xmm_crc3 = _mm_castps_si128(ps_res32);
}

__attribute__((target("sse4.2,pclmul")))
local void fold_4(deflate_state *const s,
__m128i *xmm_crc0, __m128i *xmm_crc1,
__m128i *xmm_crc2, __m128i *xmm_crc3)
Expand Down Expand Up @@ -219,6 +228,7 @@ local const unsigned zalign(32) pshufb_shf_table[60] = {
0x0201008f,0x06050403,0x0a090807,0x0e0d0c0b /* shl 1 (16 -15)/shr15*/
};

__attribute__((target("sse4.2,pclmul")))
local void partial_fold(deflate_state *const s, const size_t len,
__m128i *xmm_crc0, __m128i *xmm_crc1,
__m128i *xmm_crc2, __m128i *xmm_crc3,
Expand Down Expand Up @@ -269,6 +279,7 @@ local void partial_fold(deflate_state *const s, const size_t len,
*xmm_crc3 = _mm_castps_si128(ps_res);
}

__attribute__((target("sse4.2,pclmul")))
ZLIB_INTERNAL void crc_fold_copy(deflate_state *const s,
unsigned char *dst, const unsigned char *src, long len)
{
Expand Down Expand Up @@ -425,6 +436,7 @@ local const unsigned zalign(16) crc_mask2[4] = {
0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF
};

__attribute__((target("sse4.2,pclmul")))
unsigned ZLIB_INTERNAL crc_fold_512to32(deflate_state *const s)
{
const __m128i xmm_mask = _mm_load_si128((__m128i *)crc_mask);
Expand Down
14 changes: 0 additions & 14 deletions deps/zlib/zlib.gyp
Original file line number Diff line number Diff line change
Expand Up @@ -91,20 +91,6 @@
'x86.c',
],
'conditions': [
['OS!="win" or llvm_version!="0.0"', {
'cflags': [
'-mssse3',
'-msse4.2',
'-mpclmul',
],
'xcode_settings': {
'OTHER_CFLAGS': [
'-mssse3',
'-msse4.2',
'-mpclmul',
],
},
}],
['target_arch=="x64"', {
'defines': [ 'INFLATE_CHUNK_READ_64LE' ],
}],
Expand Down