mirror of
https://git.code.sf.net/p/quake/quakeforge
synced 2025-02-17 09:22:43 +00:00
63db48bf42
Always setting w to 0 made it impossible to use the resulting 4d vectors in division-based operations as they would result in divide-by-zero and thus an unavoidable exception (CPUs don't like integer div-by-zero). I'll probably add similar for float and double, but they're not as critical as they'll just give inf or nan. This also increases my doubts about the value of keeping 3d vector operations.
136 lines
2.9 KiB
C
136 lines
2.9 KiB
C
/*
|
|
QF/simd/vec4i.h
|
|
|
|
Vector functions for vec4i_t (ie, int)
|
|
|
|
Copyright (C) 2022 Bill Currie <bill@taniwha.org>
|
|
|
|
This program is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU General Public License
|
|
as published by the Free Software Foundation; either version 2
|
|
of the License, or (at your option) any later version.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
|
|
See the GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program; if not, write to:
|
|
|
|
Free Software Foundation, Inc.
|
|
59 Temple Place - Suite 330
|
|
Boston, MA 02111-1307, USA
|
|
|
|
*/
|
|
|
|
#ifndef __QF_simd_vec4i_h
|
|
#define __QF_simd_vec4i_h
|
|
|
|
#include <immintrin.h>
|
|
#include <math.h>
|
|
|
|
#include "QF/simd/types.h"
|
|
|
|
GNU89INLINE inline vec4i_t vabs4i (vec4i_t v) __attribute__((const));
|
|
GNU89INLINE inline int any4i (vec4i_t v) __attribute__((const));
|
|
GNU89INLINE inline int all4i (vec4i_t v) __attribute__((const));
|
|
GNU89INLINE inline int none4i (vec4i_t v) __attribute__((const));
|
|
GNU89INLINE inline vec4i_t loadvec3i (const int *v3) __attribute__((pure));
|
|
GNU89INLINE inline vec4i_t loadvec3i1 (const int *v3) __attribute__((pure));
|
|
GNU89INLINE inline void storevec3i (int *v3, vec4i_t v4);
|
|
|
|
#ifndef IMPLEMENT_VEC4F_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
vec4i_t
|
|
vabs4i (vec4i_t v)
|
|
{
|
|
const uint32_t nan = ~0u >> 1;
|
|
const vec4i_t abs = { nan, nan, nan, nan };
|
|
return (vec4i_t) ((vec4i_t) v & abs);
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC2I_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
int
|
|
any4i (vec4i_t v)
|
|
{
|
|
return !__builtin_ia32_ptestz128 ((__v2di)v, (__v2di)v);
|
|
/*vec4i_t t = (v != (vec4i_t) {});
|
|
t = __builtin_ia32_phaddd128 (t, t);
|
|
return __builtin_ia32_phaddd128 (t, t)[0] != 0;*/
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC2I_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
int
|
|
all4i (vec4i_t v)
|
|
{
|
|
vec4i_t t = (v == (vec4i_t) {});
|
|
return __builtin_ia32_ptestz128 ((__v2di)t, (__v2di)t);
|
|
/*t = __builtin_ia32_phaddd128 (t, t);
|
|
return __builtin_ia32_phaddd128 (t, t)[0] == 0;*/
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC2I_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
int
|
|
none4i (vec4i_t v)
|
|
{
|
|
return __builtin_ia32_ptestz128 ((__v2di)v, (__v2di)v);
|
|
/*vec4i_t t = (v != (vec4i_t) {});
|
|
t = __builtin_ia32_phaddd128 (t, t);
|
|
return __builtin_ia32_phaddd128 (t, t)[0] == 0;*/
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC4F_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
vec4i_t
|
|
loadvec3i (const int *v3)
|
|
{
|
|
vec4i_t v4 = { v3[0], v3[1], v3[2], 0 };
|
|
return v4;
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC4F_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
vec4i_t
|
|
loadvec3i1 (const int *v3)
|
|
{
|
|
vec4i_t v4 = { v3[0], v3[1], v3[2], 1 };
|
|
return v4;
|
|
}
|
|
|
|
#ifndef IMPLEMENT_VEC4F_Funcs
|
|
GNU89INLINE inline
|
|
#else
|
|
VISIBLE
|
|
#endif
|
|
void
|
|
storevec3i (int *v3, vec4i_t v4)
|
|
{
|
|
v3[0] = v4[0];
|
|
v3[1] = v4[1];
|
|
v3[2] = v4[2];
|
|
}
|
|
|
|
#endif//__QF_simd_vec4i_h
|