zzh
/
fast-bwa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use native SSE2 intrinsics on i386 as well as x86-64 

Make the native SSE2 code conditional on __SSE2__, which is defined
by GCC/Clang/etc on x86-64 by default and on i386 with -msse2 etc.
This commit is contained in:
John Marshall 2022-06-27 14:15:59 +01:00
parent 50f99b6890
commit aeff0eed7a
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ksw.c
View File

@ -26,7 +26,7 @@
#include <stdlib.h> #include <stdlib.h>
#include <stdint.h> #include <stdint.h>
#include <assert.h> #include <assert.h>
#if defined __x86_64__ #if defined __SSE2__
#include <emmintrin.h> #include <emmintrin.h>
#elif defined __ARM_NEON #elif defined __ARM_NEON
#include "neon_sse.h" #include "neon_sse.h"
@ -126,7 +126,7 @@ kswr_t ksw_u8(kswq_t *q, int tlen, const uint8_t *target, int _o_del, int _e_del
__m128i zero, oe_del, e_del, oe_ins, e_ins, shift, *H0, *H1, *E, *Hmax; __m128i zero, oe_del, e_del, oe_ins, e_ins, shift, *H0, *H1, *E, *Hmax;
kswr_t r; kswr_t r;
#if defined __x86_64__ #if defined __SSE2__
#define __max_16(ret, xx) do { \ #define __max_16(ret, xx) do { \
(xx) = _mm_max_epu8((xx), _mm_srli_si128((xx), 8)); \ (xx) = _mm_max_epu8((xx), _mm_srli_si128((xx), 8)); \
(xx) = _mm_max_epu8((xx), _mm_srli_si128((xx), 4)); \ (xx) = _mm_max_epu8((xx), _mm_srli_si128((xx), 4)); \
@ -259,7 +259,7 @@ kswr_t ksw_i16(kswq_t *q, int tlen, const uint8_t *target, int _o_del, int _e_de
__m128i zero, oe_del, e_del, oe_ins, e_ins, *H0, *H1, *E, *Hmax; __m128i zero, oe_del, e_del, oe_ins, e_ins, *H0, *H1, *E, *Hmax;
kswr_t r; kswr_t r;
#if defined __x86_64__ #if defined __SSE2__
#define __max_8(ret, xx) do { \ #define __max_8(ret, xx) do { \
(xx) = _mm_max_epi16((xx), _mm_srli_si128((xx), 8)); \ (xx) = _mm_max_epi16((xx), _mm_srli_si128((xx), 8)); \
(xx) = _mm_max_epi16((xx), _mm_srli_si128((xx), 4)); \ (xx) = _mm_max_epi16((xx), _mm_srli_si128((xx), 4)); \