Bart/bullet3
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updated vectormath (minor fixes, including a bugfix in storeXYZ)

Browse Source
This commit is contained in:
erwin.coumans
2009-12-19 02:08:44 +00:00
parent fa778a649c
commit d68521803f
6 changed files with 956 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

297
src/BulletMultiThreaded/vectormath/scalar/cpp/vec_aos.h
View File

@@ -1,34 +1,22 @@
/*
Copyright (C) 2006, 2007 Sony Computer Entertainment Inc.
Copyright (C) 2009 Sony Computer Entertainment Inc.
All rights reserved.
Redistribution and use in source and binary forms,
with or without modification, are permitted provided that the
following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the Sony Computer Entertainment Inc nor the names
of its contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
This software is provided 'as-is', without any express or implied warranty.
In no event will the authors be held liable for any damages arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it freely,
subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not claim that you wrote the original software. If you use this software in a product, an acknowledgment in the product documentation would be appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _VECTORMATH_VEC_AOS_CPP_H
#define _VECTORMATH_VEC_AOS_CPP_H
//-----------------------------------------------------------------------------
// Constants
@@ -109,25 +97,93 @@ inline const Vector3 slerp( float t, const Vector3 & unitVec0, const Vector3 & u
return ( ( unitVec0 * scale0 ) + ( unitVec1 * scale1 ) );
}
inline void loadXYZ( Vector3 & vec, const float * quad )
inline void loadXYZ( Vector3 & vec, const float * fptr )
{
vec = Vector3( *quad );
vec = Vector3( fptr[0], fptr[1], fptr[2] );
}
inline void loadXYZW( Vector4 & vec, const float * quad )
inline void storeXYZ( const Vector3 & vec, float * fptr )
{
vec = Vector4( *quad );
fptr[0] = vec.getX();
fptr[1] = vec.getY();
fptr[2] = vec.getZ();
}
inline void storeXYZ( Vector3 vec, float * fptr )
inline void loadHalfFloats( Vector3 & vec, const unsigned short * hfptr )
{
vec = Vector3(fptr[0],fptr[1],fptr[2]);
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 3; i++) {
unsigned short fp16 = hfptr[i];
unsigned int sign = fp16 >> 15;
unsigned int exponent = (fp16 >> 10) & ((1 << 5) - 1);
unsigned int mantissa = fp16 & ((1 << 10) - 1);
if (exponent == 0) {
// zero
mantissa = 0;
} else if (exponent == 31) {
// infinity or nan -> infinity
exponent = 255;
mantissa = 0;
} else {
exponent += 127 - 15;
mantissa <<= 13;
}
Data32 d;
d.u32 = (sign << 31) | (exponent << 23) | mantissa;
vec[i] = d.f32;
}
}
inline void storeHalfFloats( const Vector3 & vec, unsigned short * hfptr )
{
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 3; i++) {
Data32 d;
d.f32 = vec[i];
unsigned int sign = d.u32 >> 31;
unsigned int exponent = (d.u32 >> 23) & ((1 << 8) - 1);
unsigned int mantissa = d.u32 & ((1 << 23) - 1);;
if (exponent == 0) {
// zero or denorm -> zero
mantissa = 0;
} else if (exponent == 255 && mantissa != 0) {
// nan -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent >= 127 - 15 + 31) {
// overflow or infinity -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent <= 127 - 15) {
// underflow -> zero
exponent = 0;
mantissa = 0;
} else {
exponent -= 127 - 15;
mantissa >>= 13;
}
hfptr[i] = (unsigned short)((sign << 15) | (exponent << 10) | mantissa);
}
}
inline Vector3 & Vector3::operator =( const Vector3 & vec )
{
@@ -399,7 +455,7 @@ inline float lengthSqr( const Vector3 & vec )
inline float length( const Vector3 & vec )
{
return sqrtf( lengthSqr( vec ) );
return ::sqrtf( lengthSqr( vec ) );
}
inline const Vector3 normalize( const Vector3 & vec )
@@ -541,6 +597,95 @@ inline const Vector4 slerp( float t, const Vector4 & unitVec0, const Vector4 & u
return ( ( unitVec0 * scale0 ) + ( unitVec1 * scale1 ) );
}
inline void loadXYZW( Vector4 & vec, const float * fptr )
{
vec = Vector4( fptr[0], fptr[1], fptr[2], fptr[3] );
}
inline void storeXYZW( const Vector4 & vec, float * fptr )
{
fptr[0] = vec.getX();
fptr[1] = vec.getY();
fptr[2] = vec.getZ();
fptr[3] = vec.getW();
}
inline void loadHalfFloats( Vector4 & vec, const unsigned short * hfptr )
{
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 4; i++) {
unsigned short fp16 = hfptr[i];
unsigned int sign = fp16 >> 15;
unsigned int exponent = (fp16 >> 10) & ((1 << 5) - 1);
unsigned int mantissa = fp16 & ((1 << 10) - 1);
if (exponent == 0) {
// zero
mantissa = 0;
} else if (exponent == 31) {
// infinity or nan -> infinity
exponent = 255;
mantissa = 0;
} else {
exponent += 127 - 15;
mantissa <<= 13;
}
Data32 d;
d.u32 = (sign << 31) | (exponent << 23) | mantissa;
vec[i] = d.f32;
}
}
inline void storeHalfFloats( const Vector4 & vec, unsigned short * hfptr )
{
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 4; i++) {
Data32 d;
d.f32 = vec[i];
unsigned int sign = d.u32 >> 31;
unsigned int exponent = (d.u32 >> 23) & ((1 << 8) - 1);
unsigned int mantissa = d.u32 & ((1 << 23) - 1);;
if (exponent == 0) {
// zero or denorm -> zero
mantissa = 0;
} else if (exponent == 255 && mantissa != 0) {
// nan -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent >= 127 - 15 + 31) {
// overflow or infinity -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent <= 127 - 15) {
// underflow -> zero
exponent = 0;
mantissa = 0;
} else {
exponent -= 127 - 15;
mantissa >>= 13;
}
hfptr[i] = (unsigned short)((sign << 15) | (exponent << 10) | mantissa);
}
}
inline Vector4 & Vector4::operator =( const Vector4 & vec )
{
mX = vec.mX;
@@ -846,7 +991,7 @@ inline float lengthSqr( const Vector4 & vec )
inline float length( const Vector4 & vec )
{
return sqrtf( lengthSqr( vec ) );
return ::sqrtf( lengthSqr( vec ) );
}
inline const Vector4 normalize( const Vector4 & vec )
@@ -919,6 +1064,94 @@ inline const Point3 lerp( float t, const Point3 & pnt0, const Point3 & pnt1 )
return ( pnt0 + ( ( pnt1 - pnt0 ) * t ) );
}
inline void loadXYZ( Point3 & pnt, const float * fptr )
{
pnt = Point3( fptr[0], fptr[1], fptr[2] );
}
inline void storeXYZ( const Point3 & pnt, float * fptr )
{
fptr[0] = pnt.getX();
fptr[1] = pnt.getY();
fptr[2] = pnt.getZ();
}
inline void loadHalfFloats( Point3 & vec, const unsigned short * hfptr )
{
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 3; i++) {
unsigned short fp16 = hfptr[i];
unsigned int sign = fp16 >> 15;
unsigned int exponent = (fp16 >> 10) & ((1 << 5) - 1);
unsigned int mantissa = fp16 & ((1 << 10) - 1);
if (exponent == 0) {
// zero
mantissa = 0;
} else if (exponent == 31) {
// infinity or nan -> infinity
exponent = 255;
mantissa = 0;
} else {
exponent += 127 - 15;
mantissa <<= 13;
}
Data32 d;
d.u32 = (sign << 31) | (exponent << 23) | mantissa;
vec[i] = d.f32;
}
}
inline void storeHalfFloats( const Point3 & vec, unsigned short * hfptr )
{
union Data32 {
unsigned int u32;
float f32;
};
for (int i = 0; i < 3; i++) {
Data32 d;
d.f32 = vec[i];
unsigned int sign = d.u32 >> 31;
unsigned int exponent = (d.u32 >> 23) & ((1 << 8) - 1);
unsigned int mantissa = d.u32 & ((1 << 23) - 1);;
if (exponent == 0) {
// zero or denorm -> zero
mantissa = 0;
} else if (exponent == 255 && mantissa != 0) {
// nan -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent >= 127 - 15 + 31) {
// overflow or infinity -> infinity
exponent = 31;
mantissa = 0;
} else if (exponent <= 127 - 15) {
// underflow -> zero
exponent = 0;
mantissa = 0;
} else {
exponent -= 127 - 15;
mantissa >>= 13;
}
hfptr[i] = (unsigned short)((sign << 15) | (exponent << 10) | mantissa);
}
}
inline Point3 & Point3::operator =( const Point3 & pnt )
{
mX = pnt.mX;