const int emax=127;
// Input: x>=0
// Output: base 2 exponent of x if (x!=0 && !isnan(x) && !isinf(x))
// -emax if x==0
// emax+1 otherwise
int floorLog2(float x)
{
if(x==0.) return -emax;
// NOTE: there exist values of x, for which floor(log2(x)) will give wrong
// (off by one) result as compared to the one calculated with infinite precision.
// Thus we do it in a brute-force way.
for(int e=emax;e>=1-emax;--e)
if(x>=exp2(float(e))) return e;
// If we are here, x must be infinity or NaN
return emax+1;
}
// Input: any x
// Output: IEEE 754 biased exponent with bias=emax
int biasedExp(float x) { return emax+floorLog2(abs(x)); }
// Input: any x such that (!isnan(x) && !isinf(x))
// Output: significand AKA mantissa of x if !isnan(x) && !isinf(x)
// undefined otherwise
float significand(float x)
{
// converting int to float so that exp2(genType) gets correctly-typed value
float expo=float(floorLog2(abs(x)));
return abs(x)/exp2(expo);
}
// Input: x\in[0,1)
// N>=0
// Output: Nth byte as counted from the highest byte in the fraction
int part(float x,int N)
{
// All comments about exactness here assume that underflow and overflow don't occur
const float byteShift=256.;
// Multiplication is exact since it's just an increase of exponent by 8
for(int n=0;n<N;++n)
x*=byteShift;
// Cut higher bits away.
// $q \in [0,1) \cap \mathbb Q'.$
float q=fract(x);
// Shift and cut lower bits away. Cutting lower bits prevents potentially unexpected
// results of rounding by the GPU later in the pipeline when transforming to TrueColor
// the resulting subpixel value.
// $c \in [0,255] \cap \mathbb Z.$
// Multiplication is exact since it's just and increase of exponent by 8
float c=floor(byteShift*q);
return int(c);
}
// Input: any x acceptable to significand()
// Output: significand of x split to (8,8,8)-bit data vector
ivec3 significandAsIVec3(float x)
{
ivec3 result;
float sig=significand(x)/2.; // shift all bits to fractional part
result.x=part(sig,0);
result.y=part(sig,1);
result.z=part(sig,2);
return result;
}
// Input: any x such that !isnan(x)
// Output: IEEE 754 defined binary32 number, packed as ivec4(byte3,byte2,byte1,byte0)
ivec4 packIEEE754binary32(float x)
{
int e = biasedExp(x);
// sign to bit 7
int s = x<0. ? 128 : 0;
ivec4 binary32;
binary32.yzw=significandAsIVec3(x);
// clear the implicit integer bit of significand
if(binary32.y>=128) binary32.y-=128;
// put lowest bit of exponent into its position, replacing just cleared integer bit
binary32.y+=128*int(mod(float(e),2.));
// prepare high bits of exponent for fitting into their positions
e/=2;
// pack highest byte
binary32.x=e+s;
return binary32;
}
vec4 toColor(float x)
{
ivec4 binary32=packIEEE754binary32(x);
// Transform color components to [0,1] range.
// Division is inexact, but works reliably for all integers from 0 to 255 if
// the transformation to TrueColor by GPU uses rounding to nearest or upwards.
// The result will be multiplied by 255 back when transformed
// to TrueColor subpixel value by OpenGL.
return vec4(binary32)/255.;
}
