16位浮点和GL_HALF_ FLOAT

16-bit floats and GL_HALF_FLOAT

本文关键字:HALF FLOAT GL 16位      更新时间:2023-10-16

我正在寻找/编写一个16位浮点数字的C++实现,用于OpenGL顶点缓冲区(纹理坐标、法线等)。到目前为止,以下是我的要求:

  • 必须是16位(显然)
  • 必须能够使用GL_HALF_FLOAT上传到OpenGL顶点缓冲区
  • 必须能够表示-1.0-+1.0以外的数字(否则我只会使用GL_SHORT规范化)
  • 必须能够转换为普通的32位浮点值或从其转换
  • 算术运算无关紧要——我只关心存储
  • 速度不是首要问题,但正确性才是首要问题

以下是迄今为止我对接口的了解:

class half
{
public:
half(void) : data(0) {}
half(const half& h) : data(h.data) {}
half(const unsigned short& s) : data(s) {}
half(const float& f) : data(fromFloat(f)) {}
half(const double& d) : data(fromDouble(d)) {}
inline operator const float() { return toFloat(data); }
inline operator const double() { return toDouble(data); }
inline const half operator=(const float& rhs) { data = fromFloat(rhs); return *this; }
inline const half operator=(const double& rhs) { data = fromDouble(rhs); return *this; }
private:
unsigned short data;
static unsigned short fromFloat(float f);
static float toFloat(short h);
inline static unsigned short fromDouble(double d) { return fromFloat((float)d); }
inline static double toDouble(short h) { return (double)toFloat(h); }
};
std::ostream& operator<<(std::ostream& os, half h) { os << (float)h; }
std::istream& operator>>(std::istream& is, half& h) { float f; is >> f; h = f; }

最终,类的真正内容在于toFloat()fromFloat()函数,这正是我需要帮助的地方。我已经找到了很多16位浮点实现的例子,但没有一个提到它们是否可以上传到OpenGL。

当上传16位浮点到OpenGL时,我应该注意哪些问题?是否有专门解决这些问题的半浮动实现?

编辑:根据流行的需求,以下是我的顶点数据的生成、上传和渲染方式。

以下是如何在WireCubeEntity类中定义数据:

VertexHalf vertices[8] = {
vec3(-1.0f, -1.0f, -1.0f),
vec3(1.0f, -1.0f, -1.0f),
vec3(1.0f, 1.0f, -1.0f),
vec3(-1.0f, 1.0f, -1.0f),
vec3(-1.0f, -1.0f, 1.0f),
vec3(1.0f, -1.0f, 1.0f),
vec3(1.0f, 1.0f, 1.0f),
vec3(-1.0f, 1.0f, 1.0f)
};
unsigned char indices[24] = {
0, 1,
1, 2,
2, 3,
3, 0,
4, 5,
5, 6,
6, 7,
7, 4,
0, 4,
1, 5,
2, 6,
3, 7
};
va.load(GL_LINES, VF_BASICHALF, 8, vertices, GL_UNSIGNED_BYTE, 24, indices);

其中CCD_ 3是VertexArray的实例。va.load定义为:

MappedBuffers VertexArray::load(GLenum primitive, VertexFormat vertexFormat, unsigned int vertexCount, void* vertices,
GLenum indexFormat, unsigned int indexCount, void* indices)
{
MappedBuffers ret;
/* Check for invalid primitive types */
if (primitive > GL_TRIANGLE_FAN)
{
error("in VertexFormat::load():n");
errormore("Invalid enum '%i' passed to 'primitive'.n", primitive);
return ret;
}
/* Clean up existing data */
clean();
/* Set up Vertex Array Object */
glGenVertexArrays(1, &vao);
bindArray();
/* Create Vertex Buffer Object */
glGenBuffers(1, &vbo);
glBindBuffer(GL_ARRAY_BUFFER, vbo);
glBufferData(GL_ARRAY_BUFFER, vertexSize(vertexFormat) * vertexCount, vertices, GL_STATIC_DRAW);
if (!vertices) ret.vmap = glMapBuffer(GL_ARRAY_BUFFER, GL_WRITE_ONLY);
/* Save variables for later usage */
prim = primitive;
vformat = vertexFormat;
vcount = vertexCount;
/* If we've been given index data, handle it */
if (indexSize(indexFormat) != 0)
{
glGenBuffers(1, &ibo);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, ibo);
glBufferData(GL_ELEMENT_ARRAY_BUFFER, indexSize(indexFormat) * indexCount, indices, GL_STATIC_DRAW);
if (!indices) ret.imap = glMapBuffer(GL_ELEMENT_ARRAY_BUFFER, GL_WRITE_ONLY);
iformat = indexFormat;
icount = indexCount;
}
/* Handle the vertex format */
switch (vformat)
{
case VF_BASIC:
/* VF_BASIC only has a position - a 3-component float vector */
glEnableVertexAttribArray(0);
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 0, (void*)0);
break;
case VF_32:
/* VF_32 has 3 components for position, 2 for texture coordinates, and 3 for a normal.
Position is at offset 0, TextureCoordinate is at offset 12, and Normal is at offset 20 */
glEnableVertexAttribArray(0);
glEnableVertexAttribArray(1);
glEnableVertexAttribArray(2);
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, vertexSize(VF_32), (void*)0);
glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, vertexSize(VF_32), (void*)12);
glVertexAttribPointer(2, 3, GL_FLOAT, GL_FALSE, vertexSize(VF_32), (void*)20);
break;
case VF_BASICHALF:
/* VF_BASICHALF is very similar to VF_BASIC, except using half-floats instead of floats. */
glEnableVertexAttribArray(0);
glVertexAttribPointer(0, 3, GL_HALF_FLOAT, GL_FALSE, 0, (void*)0);
break;
case VF_WITHTANGENTS:
/* VF_WITHTANGENTS is similar to VF_32, but with additional components for a Tangent. */
/* Tangent is at offset 32 */
glEnableVertexAttribArray(0);
glEnableVertexAttribArray(1);
glEnableVertexAttribArray(2);
glEnableVertexAttribArray(3);
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, vertexSize(VF_WITHTANGENTS), (void*)0);
glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, vertexSize(VF_WITHTANGENTS), (void*)12);
glVertexAttribPointer(2, 3, GL_FLOAT, GL_FALSE, vertexSize(VF_WITHTANGENTS), (void*)20);
glVertexAttribPointer(3, 3, GL_FLOAT, GL_FALSE, vertexSize(VF_WITHTANGENTS), (void*)32);
break;
default:
error("In VertexFormat::load():n");
errormore("Invalid enum '%i' passed to vertexFormat.n", (int)vformat);
clean();
return MappedBuffers();
}
/* Unbind the vertex array */
unbindArray();
if (vertices) ready = true;
return ret;
}

我知道,这是一项相当繁重的任务。MappedBuffers只是一个包含2个指针的结构,因此如果我将NULL数据传递到VertexArray::load()中,我可以使用这些指针将数据直接从文件加载到缓冲区(可能来自另一个线程)。vertexSize是一个函数,它返回我传入的任何顶点格式的sizeof(),或返回无效格式的0。

VertexHalf结构是:

struct VertexHalf
{
VertexHalf(void) {}
VertexHalf(vec3 _pos) :x(_pos.x), y(_pos.y), z(_pos.z) {}
VertexHalf(float _x, float _y, float _z) : x(_x), y(_y), z(_z) {}
half x, y, z, padding;
};

最后,使用我们之前加载的VertexArray渲染数据:

void VertexArray::draw(void)
{
if (ready == false)
return;
/* Bind our vertex array */
bindArray();
/* Draw it's contents */
if (ibo == 0)
glDrawArrays(prim, 0, vcount);
else
glDrawElements(prim, icount, iformat, NULL);
unbindArray();
}

编辑 :最明显的错误出现在您的VertexHalf结构中。你有填充元素。然而,当您指定glVertexAttribPointer时,您会在步幅中指定一个0,这表明它是紧密堆积的。因此,您可以更改VertexHalf以删除填充,也可以更改glVertexAttribPointer以具有8字节的步幅。

我将下面的类与DirectX一起用于float16支持,它运行得很好。

楼层16.h:

#ifndef THE__FLOAT_16_H_
#define THE__FLOAT_16_H_
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
extern short FloatToFloat16( float value );
extern float Float16ToFloat( short value );
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
class Float16
{
protected:
short mValue;
public:
Float16();
Float16( float value );
Float16( const Float16& value );
operator float();
operator float() const;
friend Float16 operator + ( const Float16& val1, const Float16& val2 );
friend Float16 operator - ( const Float16& val1, const Float16& val2 );
friend Float16 operator * ( const Float16& val1, const Float16& val2 );
friend Float16 operator / ( const Float16& val1, const Float16& val2 );
Float16& operator =( const Float16& val );
Float16& operator +=( const Float16& val );
Float16& operator -=( const Float16& val );
Float16& operator *=( const Float16& val );
Float16& operator /=( const Float16& val );
Float16& operator -();
};
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16::Float16()
{
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16::Float16( float value )
{
mValue  = FloatToFloat16( value );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16::Float16( const Float16 &value )
{
mValue  = value.mValue;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16::operator float()
{
return Float16ToFloat( mValue );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16::operator float() const
{
return Float16ToFloat( mValue );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator =( const Float16& val )
{
mValue  = val.mValue;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator +=( const Float16& val )
{
*this   = *this + val;
return *this;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator -=( const Float16& val )
{
*this   = *this - val;
return *this;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator *=( const Float16& val )
{
*this   = *this * val;
return *this;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator /=( const Float16& val )
{
*this   = *this / val;
return *this;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16& Float16::operator -()
{
*this   = Float16( -(float)*this );
return *this;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
/*+----+                                 Friends                                       +----+*/
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16 operator + ( const Float16& val1, const Float16& val2 )
{
return Float16( (float)val1 + (float)val2 );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16 operator - ( const Float16& val1, const Float16& val2 )
{
return Float16( (float)val1 - (float)val2 );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16 operator * ( const Float16& val1, const Float16& val2 )
{
return Float16( (float)val1 * (float)val2 );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
inline Float16 operator / ( const Float16& val1, const Float16& val2 )
{
return Float16( (float)val1 / (float)val2 );
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/

#endif

Floa16.cpp:

#include "Types/Float16.h"
//#include <d3dx9.h>
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/
short FloatToFloat16( float value )
{
short   fltInt16;
int     fltInt32;
memcpy( &fltInt32, &value, sizeof( float ) );
fltInt16    =  ((fltInt32 & 0x7fffffff) >> 13) - (0x38000000 >> 13);
fltInt16    |= ((fltInt32 & 0x80000000) >> 16);
return fltInt16;
}

/+----+----+-----+-----+----+-----+-----+-----+-----+----+--------+-----+--------+-----+--------+----+------------+-----/

float Float16ToFloat( short fltInt16 )
{
int fltInt32    =  ((fltInt16 & 0x8000) << 16);
fltInt32        |= ((fltInt16 & 0x7fff) << 13) + 0x38000000;
float fRet;
memcpy( &fRet, &fltInt32, sizeof( float ) );
return fRet;
}
/*+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+*/

GLM库支持半浮点类型。使用的前缀是"h",因此其中glm::vec3是浮点值的3元素向量,glm::hvec3是半浮点的3元素矢量。

我只知道有half实现的OpenEXR库。好处是half的实现具有您想要的功能,它甚至可以与NVIDIA CG工具包配合使用。

糟糕的是,我不知道half类型是否与你使用的opengl版本开箱即用兼容(理论上应该兼容),所以你应该在决定使用它之前做一些测试。