Bitcoin Forum

#version 120

/*
32-bit integers are represented by a vec2. GLSL 2 integers may only have up
to 16-bit precision (in portable code), and they are likely to be implemented
with floats anyway. Instead we use float-pairs, with 16-bit in each (although
floats fit 24-bit precision). A vec4 is also used instead of two vec2, where
possible.
*/

uniform vec4 data[8];		/* Second part of data */
uniform vec4 hash1[4];		/* Second part of hash1 */
uniform vec4 midstate[4];
uniform vec4 target[4];
uniform vec2 nonce_base;

/* Note: N is the width of the buffer and should only be between 1 and 2048 or
so. Preferably less -- around 128 or 256. */
uniform float N;

/* Note: offset is two independent floats, with values between 0 and N. */
varying vec2 varying_nonce_offset;

const vec4 stdstate[4] = vec4[](
	vec4 (float (0x6a09), float (0xe667), float (0xbb67), float (0xae85)),
	vec4 (float (0x3c6e), float (0xf372), float (0xa54f), float (0xf53a)),
	vec4 (float (0x510e), float (0x527f), float (0x9b05), float (0x688c)),
	vec4 (float (0x1f83), float (0xd9ab), float (0x5be0), float (0xcd19)));

const vec4 k[32] = vec4[](
	vec4 (float (0x428a), float (0x2f98), float (0x7137), float (0x4491)),
	vec4 (float (0xb5c0), float (0xfbcf), float (0xe9b5), float (0xdba5)),
	vec4 (float (0x3956), float (0xc25b), float (0x59f1), float (0x11f1)),
	vec4 (float (0x923f), float (0x82a4), float (0xab1c), float (0x5ed5)),

	vec4 (float (0xd807), float (0xaa98), float (0x1283), float (0x5b01)),
	vec4 (float (0x2431), float (0x85be), float (0x550c), float (0x7dc3)),
	vec4 (float (0x72be), float (0x5d74), float (0x80de), float (0xb1fe)),
	vec4 (float (0x9bdc), float (0x06a7), float (0xc19b), float (0xf174)),

	vec4 (float (0xe49b), float (0x69c1), float (0xefbe), float (0x4786)),
	vec4 (float (0x0fc1), float (0x9dc6), float (0x240c), float (0xa1cc)),
	vec4 (float (0x2de9), float (0x2c6f), float (0x4a74), float (0x84aa)),
	vec4 (float (0x5cb0), float (0xa9dc), float (0x76f9), float (0x88da)),

	vec4 (float (0x983e), float (0x5152), float (0xa831), float (0xc66d)),
	vec4 (float (0xb003), float (0x27c8), float (0xbf59), float (0x7fc7)),
	vec4 (float (0xc6e0), float (0x0bf3), float (0xd5a7), float (0x9147)),
	vec4 (float (0x06ca), float (0x6351), float (0x1429), float (0x2967)),

	vec4 (float (0x27b7), float (0x0a85), float (0x2e1b), float (0x2138)),
	vec4 (float (0x4d2c), float (0x6dfc), float (0x5338), float (0x0d13)),
	vec4 (float (0x650a), float (0x7354), float (0x766a), float (0x0abb)),
	vec4 (float (0x81c2), float (0xc92e), float (0x9272), float (0x2c85)),

	vec4 (float (0xa2bf), float (0xe8a1), float (0xa81a), float (0x664b)),
	vec4 (float (0xc24b), float (0x8b70), float (0xc76c), float (0x51a3)),
	vec4 (float (0xd192), float (0xe819), float (0xd699), float (0x0624)),
	vec4 (float (0xf40e), float (0x3585), float (0x106a), float (0xa070)),

	vec4 (float (0x19a4), float (0xc116), float (0x1e37), float (0x6c08)),
	vec4 (float (0x2748), float (0x774c), float (0x34b0), float (0xbcb5)),
	vec4 (float (0x391c), float (0x0cb3), float (0x4ed8), float (0xaa4a)),
	vec4 (float (0x5b9c), float (0xca4f), float (0x682e), float (0x6ff3)),

	vec4 (float (0x748f), float (0x82ee), float (0x78a5), float (0x636f)),
	vec4 (float (0x84c8), float (0x7814), float (0x8cc7), float (0x0208)),
	vec4 (float (0x90be), float (0xfffa), float (0xa450), float (0x6ceb)),
	vec4 (float (0xbef9), float (0xa3f7), float (0xc671), float (0x78f2)));

/* For rotr (>>) use division with appropriate power of 2. */

/* Do not let overflow happen with this function, or use sum_c instead! */
vec2 sum (vec2 a, vec2 b)
{
	vec2 ret;
	ret.x = a.x + b.x;
	ret.y = a.y + b.y;
	if (ret.y >= float(0x10000))
	{
		ret.y -= float(0x10000);
		ret.x += 1.0;
	}
	if (ret.x >= float(0x10000))
		ret.x -= float(0x10000);
	return ret;
}

vec2 sum_c (vec2 a, vec2 b, out float carry)
{
	vec2 ret;
	ret.x = a.x + b.x;
	ret.y = a.y + b.y;
	if (ret.y >= float(0x10000))
	{
		ret.y -= float(0x10000);
		ret.x += 1.0;
	}
	if (ret.x >= float(0x10000))
	{
		ret.x -= float(0x10000);
		carry = 1.0;
	}
	return ret;
}

vec2 prod (float a, float b)
{
	vec2 ret;
	ret.x = 0;
	ret.y = a * b;
	if (ret.y >= float(0x10000))
	{
		float c = floor (ret.y / float(0x10000));
		ret.x += c;
		ret.y -= c * float(0x10000);
	}
	return ret;
}

/* Note: shift should be a power of two, e.g. to shift 3 steps, use 2^3. */
vec2 sftr (vec2 a, float shift)
{
	vec2 ret = a / shift;
	ret = vec2 (floor (ret.x), floor (ret.y) + fract (ret.x) * float (0x10000));
	return ret;
}

/* Note: shift should be a power of two, e.g. to rotate 3 steps, use 2^3. */
vec2 rotr (vec2 a, float shift)
{
	vec2 ret = a / shift;
	ret = floor (ret) + fract (ret.yx) * float (0x10000);
	return ret;
}

float xor16 (float a, float b)
{
	float ret = 0;
	float fact = float (0x8000);
	while (fact > 0)
	{
		if ((a >= fact || b >= fact) && (a < fact || b < fact))
		ret += fact;

		if (a >= fact)
		a -= fact;
		if (b >= fact)
		b -= fact;

		fact /= 2.0;
	}
	return ret;
}

vec2 xor (vec2 a, vec2 b)
{
	return vec2 (xor16 (a.x, b.x), xor16 (a.y, b.y));
}

float and16 (float a, float b)
{
	float ret = 0;
	float fact = float (0x8000);
	while (fact > 0)
	{
		/* TODO: This still does XOR */
		if ((a >= fact || b >= fact) && (a < fact || b < fact))
		ret += fact;

		if (a >= fact)
		a -= fact;
		if (b >= fact)
		b -= fact;

		fact /= 2.0;
	}
	return ret;
}

vec2 and (vec2 a, vec2 b)
{
	return vec2 (and16 (a.x, b.x), and16 (a.y, b.y));
}

/* Logical complement ("not") */
vec2 cpl (vec2 a)
{
	return vec2 (float (0x10000), float (0x10000)) - a;
}

#define POW_2_01 2.0
#define POW_2_02 4.0
#define POW_2_03 8.0
#define POW_2_06 64.0
#define POW_2_07 128.0
#define POW_2_09 512.0
#define POW_2_10 1024.0
#define POW_2_11 2048.0
#define POW_2_13 8192.0

vec2 blend (vec2 m16, vec2 m15, vec2 m07, vec2 m02)
{
	vec2 s0 = xor (rotr (m15   , POW_2_07), xor (rotr (m15.yx, POW_2_02), sftr (m15, POW_2_03)));
	vec2 s1 = xor (rotr (m02.yx, POW_2_01), xor (rotr (m02.yx, POW_2_03), sftr (m02, POW_2_10)));
	return sum (sum (m16, s0), sum (m07, s1));
}

vec2 e0 (vec2 a)
{
	return xor (rotr (a, POW_2_02), xor (rotr (a, POW_2_13), rotr (a.yx, POW_2_06)));
}

vec2 e1 (vec2 a)
{
	return xor (rotr (a, POW_2_06), xor (rotr (a, POW_2_11), rotr (a.yx, POW_2_09)));
}

vec2 ch (vec2 a, vec2 b, vec2 c)
{
	return xor (and (a, b), and (cpl (a), c));
}

vec2 maj (vec2 a, vec2 b, vec2 c)
{
	return xor (xor (and (a, b), and (a, c)), and (b, c));
}

void main ()
{
	vec2 nonce_offset = floor (varying_nonce_offset);
	vec2 nonce = sum (nonce_base, sum(prod(nonce_offset.y, N), vec2 (0.0, nonce_offset.x)));

	vec4 w[24];
	vec4 hash0[4];
	vec4 tmp[4];
	#define a (tmp[0].xy)
	#define b (tmp[0].zw)
	#define c (tmp[1].xy)
	#define d (tmp[1].zw)
	#define e (tmp[2].xy)
	#define f (tmp[2].zw)
	#define g (tmp[3].xy)
	#define h (tmp[3].zw)
	vec2 t1, t2;

	/* TODO: Using midstate as state, calculate hash "hash0" of data with nonce applied */
	w[0].xy = blend (data[0].xy, data[0].zw, data[4].zw, data[7].xy);
	w[0].zw = blend (data[0].zw, data[1].xy, data[5].xy, data[7].zw);
	w[1].xy = blend (data[1].xy, data[1].zw, data[5].zw,    w[0].xy);
	w[1].zw = blend (data[1].zw, data[2].xy, data[6].xy,    w[0].zw);
	w[2].xy = blend (data[2].xy, data[2].zw, data[6].zw,    w[1].xy);
	w[2].zw = blend (data[2].zw, nonce.xy,   data[7].xy,    w[1].zw);
	w[3].xy = blend (nonce.xy,   nonce.zw,   data[7].zw,    w[2].xy);
	w[3].zw = blend (nonce.zw,   data[4].xy,    w[0].xy,    w[2].zw);
	w[4].xy = blend (data[4].xy, data[4].zw,    w[0].zw,    w[3].xy);
	w[4].zw = blend (data[4].zw, data[5].xy,    w[1].xy,    w[3].zw);
	w[5].xy = blend (data[5].xy, data[5].zw,    w[1].zw,    w[4].xy);
	w[5].zw = blend (data[5].zw, data[6].xy,    w[2].xy,    w[4].zw);
	w[6].xy = blend (data[6].xy, data[6].zw,    w[2].zw,    w[5].xy);
	w[6].zw = blend (data[6].zw, data[7].xy,    w[3].xy,    w[5].zw);
	w[7].xy = blend (data[7].xy, data[7].zw,    w[3].zw,    w[6].xy);
	w[7].zw = blend (data[7].zw,	w[0].xy,    w[4].xy,    w[6].zw);
	for (int i = 8; i < 24; ++i)
	{
		w[i].xy = blend (w[i-8].xy, w[i-8].zw, w[i-4].zw, w[i-1].xy);
		w[i].zw = blend (w[i-8].zw, w[i-7].xy, w[i-3].xy, w[i-1].zw);
	}
	tmp = midstate;

	/* TODO: Add loop-unrolled of i = 0 to 3, where data is used instead of w. */
	/*for (int i = 4; i < 32; i+=4)
	{
		t1 = sum (sum (sum (sum (h, e1(e)), ch(e,f,g)), k[i+0].xy), w[i-4+0].xy);
		t2 = sum (e0(a), maj(a,b,c)); d = sum (d, t1); h = sum (t1, t2);
		t1 = sum (sum (sum (sum (g, e1(d)), ch(d,e,f)), k[i+0].zw), w[i-4+0].zw);
		t2 = sum (e0(h), maj(h,a,b)); c = sum (c, t1); g = sum (t1, t2);
		t1 = sum (sum (sum (sum (f, e1(c)), ch(c,d,e)), k[i+1].xy), w[i-4+1].xy);
		t2 = sum (e0(g), maj(g,h,a)); b = sum (b, t1); f = sum (t1, t2);
		t1 = sum (sum (sum (sum (e, e1(b)), ch(b,c,d)), k[i+1].zw), w[i-4+1].zw);
		t2 = sum (e0(f), maj(f,g,h)); a = sum (a, t1); e = sum (t1, t2);
		t1 = sum (sum (sum (sum (d, e1(a)), ch(a,b,c)), k[i+2].xy), w[i-4+2].xy);
		t2 = sum (e0(e), maj(e,f,g)); h = sum (h, t1); d = sum (t1, t2);
		t1 = sum (sum (sum (sum (c, e1(h)), ch(h,a,b)), k[i+2].zw), w[i-4+2].zw);
		t2 = sum (e0(d), maj(d,e,f)); g = sum (g, t1); c = sum (t1, t2);
		t1 = sum (sum (sum (sum (b, e1(g)), ch(g,h,a)), k[i+3].xy), w[i-4+3].xy);
		t2 = sum (e0(c), maj(c,d,e)); f = sum (f, t1); b = sum (t1, t2);
		t1 = sum (sum (sum (sum (a, e1(f)), ch(f,g,h)), k[i+3].zw), w[i-4+3].zw);
		t2 = sum (e0(b), maj(b,c,d)); e = sum (e, t1); a = sum (t1, t2);
	}*/

	/* TODO: More iterations... Copy-paste block and fix k-index and W-value. */

	for (int i = 0; i < 4; ++i)
	{
		hash0[i].xy = sum (midstate[i].xy, tmp[i].xy);
		hash0[i].zw = sum (midstate[i].zw, tmp[i].zw);
	}

	vec4 hash[4];
	/* TODO: Using stdstate as state, calculate the hash of (hash0, hash1) */

	/* TODO: Compare with target. */

	gl_FragColor.r = nonce.y / 255.0;
	if (mod (nonce.y, 2.0) == 0.0)
		gl_FragColor.r = 0;
	else
		gl_FragColor.r = 1;
}

#include <stdio.h>                      //C standard IO
#include <stdlib.h>                     //C standard lib
#include <string.h>                     //C string lib

#include <GL/glew.h>                    //GLEW lib
#include <GL/glut.h>                    //GLUT lib


//Function from: http://www.evl.uic.edu/aej/594/code/ogl.cpp
//Read in a textfile (GLSL program)
// we need to pass it as a string to the GLSL driver
char *textFileRead(char *fn) {
  FILE *fp;
  char *content = NULL;
  
  int count=0;
  
  if (fn != NULL) {
    
    fp = fopen(fn,"rt");
    
    if (fp != NULL) {
      
      fseek(fp, 0, SEEK_END);
      count = ftell(fp);
      rewind(fp);
      
      if (count > 0) {
        content = (char *)malloc(sizeof(char) * (count+1));
        count = fread(content,sizeof(char),count,fp);
        content[count] = '\0';
      }
      fclose(fp);
      
    }
  }
  
  return content;
}

//Function from: http://www.evl.uic.edu/aej/594/code/ogl.cpp
//Read in a textfile (GLSL program)
// we can use this to write to a text file
int textFileWrite(char *fn, char *s) {
  FILE *fp;
  int status = 0;
  
  if (fn != NULL) {
    fp = fopen(fn,"w");
    
    if (fp != NULL) {                   
      if (fwrite(s,sizeof(char),strlen(s),fp) == strlen(s))
        status = 1;
      fclose(fp);
    }
  }
  return(status);
}

/**
 * Setup shaders
 */
void setShaders() {
  char *my_fragment_shader_source;
  // char * my_vertex_shader_source;
  GLenum error;

  GLenum my_program;
  // GLenum my_vertex_shader;
  GLenum my_fragment_shader;
  
  // Get Vertex And Fragment Shader Sources
  my_fragment_shader_source = textFileRead( "sha256.glsl");
  // my_vertex_shader_source = GetVertexShaderSource();

  // my_vertex_shader = glCreateShaderObjectARB(GL_VERTEX_SHADER_ARB);
  my_fragment_shader = glCreateShaderObjectARB(GL_FRAGMENT_SHADER_ARB);
 
  // Load Shader Sources
  // glShaderSourceARB(my_vertex_shader, 1, &my_vertex_shader_source, NULL);
  glShaderSourceARB( my_fragment_shader, 1, (const GLcharARB** )&my_fragment_shader_source, NULL);
 
  // Compile The Shaders
  // glCompileShaderARB(my_vertex_shader);
  glCompileShaderARB(my_fragment_shader);
  
  // Check for compile errors
  int compiled = 0;
  glGetObjectParameterivARB( my_fragment_shader, GL_OBJECT_COMPILE_STATUS_ARB, &compiled );

  if  ( !compiled ) {
    int maxLength;

    glGetShaderiv( my_fragment_shader, GL_INFO_LOG_LENGTH, &maxLength);
 
    /* The maxLength includes the NULL character */
    char *fragmentInfoLog = malloc( maxLength *sizeof(char));
    
    glGetShaderInfoLog( my_fragment_shader, maxLength, &maxLength, fragmentInfoLog);
 
    printf( "Compile error log: %s\n\n", fragmentInfoLog);

    /* Handle the error in an appropriate way such as displaying a message or writing to a log file. */
    /* In this simple program, we'll just leave */
    free( fragmentInfoLog);

    // printf( "compile error...\n" );
  }

  // Create Shader And Program Objects
  my_program = glCreateProgramObjectARB();

  if(( error=glGetError()) != GL_NO_ERROR) {
    exit( error);
  }

  // Attach The Shader Objects To The Program Object
  // glAttachObjectARB(my_program, my_vertex_shader);
  glAttachObjectARB(my_program, my_fragment_shader);
 
  // Link The Program Object
  glLinkProgramARB(my_program);
  
  // Use The Program Object Instead Of Fixed Function OpenGL
  glUseProgramObjectARB(my_program);
}

int main( int argc, char *argv[]) {

  glutInit(&argc, argv);
  //glutInitDisplayMode(GLUT_DEPTH | GLUT_DOUBLE | GLUT_RGBA);
  glutInitDisplayMode(GLUT_DOUBLE | GLUT_RGBA);
  glutInitWindowPosition(100,100);
  glutInitWindowSize(320,320);
  glutCreateWindow("GPU");
  
  //  glutDisplayFunc(renderScene);
  // glutIdleFunc(renderScene);
  // glutReshapeFunc(changeSize);
  // glutKeyboardFunc(processNormalKeys);
  
  glewInit();
  if (glewIsSupported("GL_VERSION_2_1"))
    printf("Ready for OpenGL 2.1\n");
  else {
    printf("OpenGL 2.1 not supported\n");
    exit(1);
  }
  if (GLEW_ARB_vertex_shader && GLEW_ARB_fragment_shader && GL_EXT_geometry_shader4)
    printf("Ready for GLSL - vertex, fragment, and geometry units\n");
  else {
    printf("Not totally ready :( \n");
    exit(1);
  }

  setShaders();
  
  glutMainLoop();
  
  // just for compatibiliy purposes
  return 0;

  // glDeleteObjectARB( my_program);
  // glDeleteObjectARB( my_fragment_shader);
}

PROGRAM := glslminer

SOURCES := $(wildcard *.c)

CC = gcc
CCOPTS = 
LINKEROPTS = -lGL -lGLEW -lglut

.PHONY: all
all:
        $(CC) $(CCOPTS) $(LINKEROPTS) $(SOURCES) -o $(PROGRAM)

.PHONY: clean
        rm *.o

localhost glsl # ./glslminer 
Ready for OpenGL 2.1
Ready for GLSL - vertex, fragment, and geometry units
Compile error log: 0(232) : error C1031: swizzle mask element not present in operand "zw"
0(233) : error C1031: swizzle mask element not present in operand "zw"

/**
 * Some utility functions to process integers represented as float2.
 */

/**
 * Add 2 integers represented as float2.
 *
 * Do not let overflow happen with this function, or use sum_c instead! 
 */
kernel float2 add( float2 a, float2 b) {
        float2 ret;

        ret.x = a.x + b.x;
        ret.y = a.y + b.y;

        if (ret.y >= 65536.0) {
                ret.y -= 65536.0;
                ret.x += 1.0;
        }

        if (ret.x >= 65536.0) {
                ret.x -= 65536.0;
	}

        return ret;
}

/**
 * Shift an integer represented as a float2 by log2(shift).
 * 
 * Note: shift should be a power of two, e.g. to shift 3 steps, use 2^3. 
 */
kernel float2 shiftr( float2 a, float shift) {
        float2 ret;
	
	ret.x = a.x / shift;

	ret.y = floor( a.y / shift) + frac( ret.x) * 65536.0;

	ret.x = floor( ret.x);

        return ret;
}

/**
 * Rotate an integer represented as a float2 by log2(shift).
 * 
 * Note: shift should be a power of two, e.g. to rotate 3 steps, use 2^3. 
 */
kernel float2 rotater( float2 a, float shift) {
        float2 ret;
	
	ret.x = a.x / shift;  // Shipt words and keep fractions to shift those bits later.
	ret.y = a.y / shift;

	ret.y += frac( ret.x) * 65536.0;  // Shift low bits from x into y;
	ret.x += frac( ret.y) * 65536.0;  // Rotate low bits from y into x;

	ret.x = floor( ret.x);  // Cut shifted bits.
	ret.y = floor( ret.y);

        return ret;
}

/**
 * Xor half of an integer, represented as a float.
 */
kernel float xor16( float a<>, float b<>) {

        float ret = 0;
        float fact = 32768.0;

        while (fact > 0) {
                if( ( ( a >= fact) || ( b >= fact)) && ( ( a < fact) || ( b < fact))) {
                  ret += fact;
		}

                if( a >= fact) {
                  a -= fact;
		}
                if (b >= fact) {
                  b -= fact;
		}

                fact /= 2.0;
        }
        return ret;
}

/**
 * Xor a complete integer represetended as a float2.
 */
kernel float2 xor( float2 a<>, float2 b<>) {
       float2 ret = { xor16( a.x, b.x), xor16( a.y, b.y) };

       return ret;
}

/**
 * And operation on half of an integer, represented as a float.
 */
kernel float and16( float a<>, float b<>) {
        float ret = 0;
        float fact = 32768.0;

        while (fact > 0) {
                if( ( a >= fact) && ( b >= fact)) {
                  ret += fact;
		}

                if( a >= fact) {
                  a -= fact;
		}
                if (b >= fact) {
                  b -= fact;
		}

                fact /= 2.0;
        }
        return ret;
}

/**
 * And operation on a full integer, represented as a float2.
 */
kernel float2 and( float2 a<>, float2 b<>) {
        float2 ret =  { and16( a.x, b.x), and16( a.y, b.y) };

        return ret;
}

/*
 * Logical complement ("not") 
 */
kernel float2 not( float2 a<>) {
       float2 ret = { 65535.0 - a.x, 65535.0 - a.y};

       return ret;
}

/**
 * Swap the 2 words of an int.
 */
kernel swapw( float2 a) {
       float2 ret;

       ret.x = a.y;
       ret.y = a.x;

       return ret;
}

kernel float2 blend( float2 m16, float2 m15, float2 m07, float2 m02) {
        float2 s0 = xor( rotater( m15, 128.0), xor( rotater( swapw( m15), 4.0), shiftr( m15, 8)));
        float2 s1 = xor( rotater( swapw( m02), 2.0), xor( rotater( swapw( m02), 8.0), shiftr( m02, 1024.0)));

        return add( add( m16, s0), add( m07, s1));
}

kernel float2 e0( float2 a) {
        return xor( rotater( a, 4.0), xor( rotater( a, 8192.0), rotater( swapw( a), 64.0)));
}

kernel float2 e1( float2 a) {
        return xor( rotater( a, 64.0), xor( rotater( a, 2048.0), rotater( swapw( a), 512.0)));
}

kernel float2 ch( float2 a, float2 b, float2 c) {
        return xor( and( a, b), and( not( a), c));
}

kernel float2 maj( float2 a, float2 b, float2 c) {
        return xor( xor( and( a, b), and( a, c)), and( b, c));
}

/**
 * Aminer - a bitcoin miner for various platforms.
 *
 * Andreas Rueckert <a_rueckert@gmx.net>
 *
 * A good part of this code is based on the GLSL sha256 code of xaci: https://bitcointalk.org/index.php?topic=4618.msg191488#msg191488
 */

/*
#pragma optionNV looplimit 32768
*/



/**
 * Some utility functions to process integers represented as float2.
 */

/**
 * Add 2 integers represented as float2.
 *
 * Do not let overflow happen with this function, or use sum_c instead! 
 */
kernel float2 add( float2 a, float2 b) {
        float2 ret;

        ret.x = a.x + b.x;
        ret.y = a.y + b.y;

        if (ret.y >= 65536.0) {
                ret.y -= 65536.0;
                ret.x += 1.0;
        }

        if (ret.x >= 65536.0) {
                ret.x -= 65536.0;
	}

        return ret;
}

/**
 * Shift an integer represented as a float2 by log2(shift).
 * 
 * Note: shift should be a power of two, e.g. to shift 3 steps, use 2^3. 
 */
kernel float2 shiftr( float2 a, float shift) {
        float2 ret;
	
	ret.x = a.x / shift;

	ret.y = floor( a.y / shift) + frac( ret.x) * 65536.0;

	ret.x = floor( ret.x);

        return ret;
}

/**
 * Rotate an integer represented as a float2 by log2(shift).
 * 
 * Note: shift should be a power of two, e.g. to rotate 3 steps, use 2^3. 
 */
kernel float2 rotater( float2 a, float shift) {
        float2 ret;
	
	ret.x = a.x / shift;  // Shipt words and keep fractions to shift those bits later.
	ret.y = a.y / shift;

	ret.y += frac( ret.x) * 65536.0;  // Shift low bits from x into y;
	ret.x += frac( ret.y) * 65536.0;  // Rotate low bits from y into x;

	ret.x = floor( ret.x);  // Cut shifted bits.
	ret.y = floor( ret.y);

        return ret;
}

/**
 * Xor half of an integer, represented as a float.
 */
kernel float xor16( float a<>, float b<>) {

        float ret = 0;
        float fact = 32768.0;

        while (fact > 0) {
                if( ( ( a >= fact) || ( b >= fact)) && ( ( a < fact) || ( b < fact))) {
                  ret += fact;
		}

                if( a >= fact) {
                  a -= fact;
		}
                if (b >= fact) {
                  b -= fact;
		}

                fact /= 2.0;
        }
        return ret;
}

/**
 * Xor a complete integer represetended as a float2.
 */
kernel float2 xor( float2 a<>, float2 b<>) {
       float2 ret = { xor16( a.x, b.x), xor16( a.y, b.y) };

       return ret;
}

/**
 * And operation on half of an integer, represented as a float.
 */
kernel float and16( float a<>, float b<>) {
        float ret = 0;
        float fact = 32768.0;

        while (fact > 0) {
                if( ( a >= fact) && ( b >= fact)) {
                  ret += fact;
		}

                if( a >= fact) {
                  a -= fact;
		}
                if (b >= fact) {
                  b -= fact;
		}

                fact /= 2.0;
        }
        return ret;
}

/**
 * And operation on a full integer, represented as a float2.
 */
kernel float2 and( float2 a<>, float2 b<>) {
        float2 ret =  { and16( a.x, b.x), and16( a.y, b.y) };

        return ret;
}

/*
 * Logical complement ("not") 
 */
kernel float2 not( float2 a<>) {
       float2 ret = { 65535.0 - a.x, 65535.0 - a.y};

       return ret;
}

/**
 * Swap the 2 words of an int.
 */
kernel swapw( float2 a) {
       float2 ret;

       ret.x = a.y;
       ret.y = a.x;

       return ret;
}

/**
 * Swap the 2 bytes in an 16-bit word.
 */
kernel float swapb( float a) {
       float ret = a / 256.0;

       ret += frac( ret) * 65536.0;

       return floor( ret);
}

/**
 * Swap the 4 bytes of a 4-byte integer;
 */
kernel float2 swapInt( float2 a) {
       float2 ret = swapw( a);

       ret.x = swapb( ret.x);
       ret.y = swapb( ret.y);

       return ret;
}

/**
 * Check if float2 integer a is smaller than float2 integer b.
 */
kernel float isSmaller( float2 a, float2 b) {
       if( ( a.x < b.x) || ( ( a.x == a.x) && ( a.y < b.y))) {
           return 1.0;
       } else {
           return 0.0;
       }
}

kernel float2 blend( float2 m16, float2 m15, float2 m07, float2 m02) {
        float2 s0 = xor( rotater( m15, 128.0), xor( rotater( swapw( m15), 4.0), shiftr( m15, 8)));
        float2 s1 = xor( rotater( swapw( m02), 2.0), xor( rotater( swapw( m02), 8.0), shiftr( m02, 1024.0)));

        return add( add( m16, s0), add( m07, s1));
}

kernel float2 s0( float2 a) {
        return xor( rotater( a, 4.0), xor( rotater( a, 8192.0), rotater( swapw( a), 64.0)));
}

kernel float2 s1( float2 a) {
        return xor( rotater( a, 64.0), xor( rotater( a, 2048.0), rotater( swapw( a), 512.0)));
}

kernel float2 ch( float2 a, float2 b, float2 c) {
        return xor( and( a, b), and( not( a), c));
}

kernel float2 maj( float2 a, float2 b, float2 c) {
        return xor( xor( and( a, b), and( a, c)), and( b, c));
}


/**
 * Let the kernel check a nonce for a given bitcoin block.
 * That's basically 2 rounds of sha256 and a difficulty check.
 * 
 * @param nonce The nonce to test for the given block
 * @param block_header* The block header as a set of ints, since brcc always converts constant arrays to brook::stream here.
 * @param difficulty The difficulty as a 256-bit superlong int.
 *
 * @return result Return the nonce, if it is valid. Return -nonce if not.
 */
kernel void kernelMinerCheckNonce( float2 nonce<>
      	    			   , float2 block_header0
				   , float2 block_header1
				   , float2 block_header2
				   , float2 block_header3 
				   , float2 block_header4
				   , float2 block_header5 
				   , float2 block_header6
				   , float2 block_header7
				   , float2 block_header8
				   , float2 block_header9
      	    			   , float2 block_header10
				   , float2 block_header11
				   , float2 block_header12
				   , float2 block_header13 
				   , float2 block_header14
				   , float2 block_header15 
				   , float2 block_header16
				   , float2 block_header17
				   , float2 block_header18
				   , float2 block_header19
				   , float2 decoded_difficulty0
				   , float2 decoded_difficulty1
				   , float2 decoded_difficulty2
				   , float2 decoded_difficulty3
				   , float2 decoded_difficulty4
				   , float2 decoded_difficulty5
				   , float2 decoded_difficulty6
				   , float2 decoded_difficulty7
				   , out float2 result<>) {

       // brcc seems to have problems with array alignment in fp40 model, so no arrays for now... :-(
       float2 k0,k1,k2,k3,k4,k5,k6,k7,k8,k9,k10,k11,k12,k13,k14,k15;
       float2 k16,k17,k18,k19,k20,k21,k22,k23,k24,k25,k26,k27,k28,k29,k30,k31;
       float2 k32,k33,k34,k35,k36,k37,k38,k39,k40,k41,k42,k43,k44,k45,k46,k47;
       float2 k48,k49,k50,k51,k52,k53,k54,k55,k56,k57,k58,k59,k60,k61,k62,k63;
       float2 h0,h1,h2,h3,h4,h5,h6,h7;
       float2 w0,w1,w2,w3,w4,w5,w6,w7,w8,w9,w10,w11,w12,w13,w14,w15;
       float2 w16,w17,w18,w19,w20,w21,w22,w23,w24,w25,w26,w27,w28,w29,w30,w31;
       float2 w32,w33,w34,w35,w36,w37,w38,w39,w40,w41,w42,w43,w44,w45,w46,w47;
       float2 w48,w49,w50,w51,w52,w53,w54,w55,w56,w57,w58,w59,w60,w61,w62,w63;
       float2 a,b,c,d,e,f,g,h;
       float2 t1, t2;

       // Initialize k
       // ( Code generated with the following c-program:
       /*
       #include <stdio.h>

       int main(int argc, char *agv[]) {
       	    unsigned int k[64] = { 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
	       	     	           0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
				   0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
				   0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
		        	   0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
			   	   0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
			      	   0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
			           0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 };
	    int i;

   	    for( i = 0; i < 64; ++i) {
            	 printf( "k%d.x = %5d.0; k%d.y = %5d.0;\n", i, k[i] >> 16, i, k[i] & 0xffff);
            }
       }
       */
       
       k0.x = 17034.0; k0.y = 12184.0;
       k1.x = 28983.0; k1.y = 17553.0;
       k2.x = 46528.0; k2.y = 64463.0;
       k3.x = 59829.0; k3.y = 56229.0;
       k4.x = 14678.0; k4.y = 49755.0;
       k5.x = 23025.0; k5.y =  4593.0;
       k6.x = 37439.0; k6.y = 33444.0;
       k7.x = 43804.0; k7.y = 24277.0;
       k8.x = 55303.0; k8.y = 43672.0;
       k9.x =  4739.0; k9.y = 23297.0;
       k10.x =  9265.0; k10.y = 34238.0;
       k11.x =	21772.0; k11.y = 32195.0;
       k12.x = 29374.0; k12.y = 23924.0;
       k13.x = 32990.0; k13.y = 45566.0;
       k14.x = 39900.0; k14.y =  1703.0;
       k15.x = 49563.0; k15.y = 61812.0;
       k16.x = 58523.0; k16.y = 27073.0;
       k17.x = 61374.0; k17.y = 18310.0;
       k18.x =  4033.0; k18.y = 40390.0;
       k19.x =  9228.0; k19.y = 41420.0;
       k20.x = 11753.0; k20.y = 11375.0;
       k21.x = 19060.0; k21.y = 33962.0;
       k22.x = 23728.0; k22.y = 43484.0;
       k23.x = 30457.0; k23.y = 35034.0;
       k24.x = 38974.0; k24.y = 20818.0;
       k25.x = 43057.0; k25.y = 50797.0;
       k26.x = 45059.0; k26.y = 10184.0;
       k27.x = 48985.0; k27.y = 32711.0;
       k28.x = 50912.0; k28.y =  3059.0;
       k29.x = 54695.0; k29.y = 37191.0;
       k30.x =  1738.0; k30.y = 25425.0;
       k31.x =  5161.0; k31.y = 10599.0;
       k32.x = 10167.0; k32.y =  2693.0;
       k33.x = 11803.0; k33.y =  8504.0;
       k34.x = 19756.0; k34.y = 28156.0;
       k35.x = 21304.0; k35.y =  3347.0;
       k36.x = 25866.0; k36.y = 29524.0;
       k37.x = 30314.0; k37.y =  2747.0;
       k38.x = 33218.0; k38.y = 51502.0;
       k39.x = 37490.0; k39.y = 11397.0;
       k40.x = 41663.0; k40.y = 59553.0;
       k41.x = 43034.0; k41.y = 26187.0;
       k42.x = 49739.0; k42.y = 35696.0;
       k43.x = 51052.0; k43.y = 20899.0;
       k44.x = 53650.0; k44.y = 59417.0;
       k45.x = 54937.0; k45.y =  1572.0;
       k46.x = 62478.0; k46.y = 13701.0;
       k47.x =  4202.0; k47.y = 41072.0;
       k48.x =  6564.0; k48.y = 49430.0;
       k49.x =  7735.0; k49.y = 27656.0;
       k50.x = 10056.0; k50.y = 30540.0;
       k51.x = 13488.0; k51.y = 48309.0;
       k52.x = 14620.0; k52.y =  3251.0;
       k53.x = 20184.0; k53.y = 43594.0;
       k54.x = 23452.0; k54.y = 51791.0;
       k55.x = 26670.0; k55.y = 28659.0;
       k56.x = 29839.0; k56.y = 33518.0;
       k57.x = 30885.0; k57.y = 25455.0;
       k58.x = 33992.0; k58.y = 30740.0;
       k59.x = 36039.0; k59.y =   520.0;
       k60.x = 37054.0; k60.y = 65530.0;
       k61.x = 42064.0; k61.y = 27883.0;
       k62.x = 48889.0; k62.y = 41975.0;
       k63.x = 50801.0; k63.y = 30962.0;


       // Initialize h

       h0.x = 27145.0; h0.y = 58983.0;  // 0x6a09 0xe667
       h1.x = 47975.0; h1.y = 44677.0;  // 0xbb67 0xae85
       h2.x = 15470.0; h2.y = 62322.0;  // 0x3c6e 0xf372
       h3.x = 42319.0; h3.y = 62778.0;  // 0xa54f 0xf53a
       h4.x = 20750.0; h4.y = 21119.0;  // 0x510e 0x527f
       h5.x = 39685.0; h5.y = 26764.0;  // 0x9b05 0x688c
       h6.x =  8067.0; h6.y = 55723.0;  // 0x1f83 0xd9ab
       h7.x = 23520.0; h7.y = 52505.0;  // 0x5be0 0xcd19

       // For the following algorithm, see: http://en.wikipedia.org/wiki/SHA-2#Examples_of_SHA-2_variants

       // Initialize the first 16 w values
       // ToDo? Precompute this outside of the kernel, since the nonce is not in these 16 values?

       /*
        * Process the message in successive 512-bit chunks:
	* break message into 512-bit chunks
	* for each chunk
    	*   break chunk into sixteen 32-bit big-endian words w[0..15]
	*/
	// Implementation:
	w0 = swapInt( block_header0);
	w1 = swapInt( block_header1);
	w2 = swapInt( block_header2);
	w3 = swapInt( block_header3);
	w4 = swapInt( block_header4);
	w5 = swapInt( block_header5);
	w6 = swapInt( block_header6);
	w7 = swapInt( block_header7);
	w8 = swapInt( block_header8);
	w9 = swapInt( block_header9);
	w10 = swapInt( block_header10);
	w11 = swapInt( block_header11);
	w12 = swapInt( block_header12);
	w13 = swapInt( block_header13);
	w14 = swapInt( block_header14);
	w15 = swapInt( block_header15);

	/*
         * for( i = 16; i < 64; i++) {
       	 *   w[i] = blend( w[ i - 16], w[ i - 15], w[ i -7], w[ i - 2]);
       	 * }
	 */
	// Implementation 
	// (Generated with bash script: for i in {16..63}; do echo "w$i = blend( w$((i - 16)), w$((i - 15)), w$((i -7)), w$((i - 2)));"; done ):
	w16 = blend( w0, w1, w9, w14);
	w17 = blend( w1, w2, w10, w15);
	w18 = blend( w2, w3, w11, w16);
	w19 = blend( w3, w4, w12, w17);
	w20 = blend( w4, w5, w13, w18);
	w21 = blend( w5, w6, w14, w19);
	w22 = blend( w6, w7, w15, w20);
	w23 = blend( w7, w8, w16, w21);
	w24 = blend( w8, w9, w17, w22);
	w25 = blend( w9, w10, w18, w23);
	w26 = blend( w10, w11, w19, w24);
	w27 = blend( w11, w12, w20, w25);
	w28 = blend( w12, w13, w21, w26);
	w29 = blend( w13, w14, w22, w27);
	w30 = blend( w14, w15, w23, w28);
	w31 = blend( w15, w16, w24, w29);
	w32 = blend( w16, w17, w25, w30);
	w33 = blend( w17, w18, w26, w31);
	w34 = blend( w18, w19, w27, w32);
	w35 = blend( w19, w20, w28, w33);
	w36 = blend( w20, w21, w29, w34);
	w37 = blend( w21, w22, w30, w35);
	w38 = blend( w22, w23, w31, w36);
	w39 = blend( w23, w24, w32, w37);
	w40 = blend( w24, w25, w33, w38);
	w41 = blend( w25, w26, w34, w39);
	w42 = blend( w26, w27, w35, w40);
	w43 = blend( w27, w28, w36, w41);
	w44 = blend( w28, w29, w37, w42);
	w45 = blend( w29, w30, w38, w43);
	w46 = blend( w30, w31, w39, w44);
	w47 = blend( w31, w32, w40, w45);
	w48 = blend( w32, w33, w41, w46);
	w49 = blend( w33, w34, w42, w47);
	w50 = blend( w34, w35, w43, w48);
	w51 = blend( w35, w36, w44, w49);
	w52 = blend( w36, w37, w45, w50);
	w53 = blend( w37, w38, w46, w51);
	w54 = blend( w38, w39, w47, w52);
	w55 = blend( w39, w40, w48, w53);
	w56 = blend( w40, w41, w49, w54);
	w57 = blend( w41, w42, w50, w55);
	w58 = blend( w42, w43, w51, w56);
	w59 = blend( w43, w44, w52, w57);
	w60 = blend( w44, w45, w53, w58);
	w61 = blend( w45, w46, w54, w59);
	w62 = blend( w46, w47, w55, w60);
	w63 = blend( w47, w48, w56, w61);

	/*
	 * Initialize hash value for this chunk:
    	 * a := h0
	 * b := h1
    	 * c := h2
    	 * d := h3
    	 * e := h4
    	 * f := h5
    	 * g := h6
    	 * h := h7
	 */
	// Implementation:
	a = h0;
	b = h1;
	c = h2;
	d = h3;
	e = h4;
	f = h5;
	g = h6;
	h = h7;

	/*
	 * Main loop:
	 * for i from 0 to 63
         *     s0 := (a rightrotate 2) xor (a rightrotate 13) xor (a rightrotate 22)
         *     maj := (a and b) xor (a and c) xor (b and c)
         *     t2 := s0 + maj
         *     s1 := (e rightrotate 6) xor (e rightrotate 11) xor (e rightrotate 25)
         *     ch := (e and f) xor ((not e) and g)
         *     t1 := h + s1 + ch + k[i] + w[i]
	 *
	 *     h := g
         *     g := f
         *     f := e
         *     e := d + t1
         *     d := c
         *     c := b
         *     b := a
         *     a := t1 + t2
	*/
	// Implementation:
	// ( Generated with bash script: 
	// for i in {0..63}; do echo "t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k$i + w$i;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;"; done
	// )
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k0 + w0;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k1 + w1;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k2 + w2;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k3 + w3;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k4 + w4;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k5 + w5;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k6 + w6;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k7 + w7;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k8 + w8;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k9 + w9;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k10 + w10;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k11 + w11;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k12 + w12;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k13 + w13;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k14 + w14;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k15 + w15;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k16 + w16;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k17 + w17;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k18 + w18;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k19 + w19;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k20 + w20;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k21 + w21;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k22 + w22;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k23 + w23;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k24 + w24;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k25 + w25;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k26 + w26;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k27 + w27;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k28 + w28;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k29 + w29;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k30 + w30;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k31 + w31;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k32 + w32;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k33 + w33;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k34 + w34;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k35 + w35;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k36 + w36;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k37 + w37;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k38 + w38;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k39 + w39;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k40 + w40;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k41 + w41;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k42 + w42;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k43 + w43;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k44 + w44;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k45 + w45;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k46 + w46;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k47 + w47;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k48 + w48;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k49 + w49;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k50 + w50;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k51 + w51;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k52 + w52;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k53 + w53;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k54 + w54;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k55 + w55;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k56 + w56;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k57 + w57;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k58 + w58;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k59 + w59;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k60 + w60;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k61 + w61;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k62 + w62;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k63 + w63;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;

	/*
	 * Add this chunk's hash to result so far:
    	 * h0 := h0 + a
    	 * h1 := h1 + b
    	 * h2 := h2 + c
    	 * h3 := h3 + d
    	 * h4 := h4 + e
    	 * h5 := h5 + f
    	 * h6 := h6 + g
    	 * h7 := h7 + h
	 */
	h0 = add( h0, a);
	h1 = add( h1, b);
	h2 = add( h2, c);
	h3 = add( h3, d);
	h4 = add( h4, e);
	h5 = add( h5, f);
	h6 = add( h6, g);
	h7 = add( h7, h);

	// The result of the first sha256 round should be now in h0..h7 as a big endian encoded int.

	// So use it as the new input for w0..w15

	// ToDo: check if the h-order should be reversed, like w0 = h15; w1 = h14; ...

	w0 = h0;  
	w1 = h1;
	w2 = h2;
	w3 = h3;
	w4 = h4;
	w5 = h5;
	w6 = h6;
	w7 = h7;
	w8.x = 0.0; w8.y = 0.0;
	w9 = w8;
	w10 = w8;
	w11 = w8;
	w12 = w8;
	w13 = w8;
	w14 = w8;
	w15 = w8;

	// Re-initialize h for the new sha256 round

        h0.x = 27145.0; h0.y = 58983.0;  // 0x6a09 0xe667
        h1.x = 47975.0; h1.y = 44677.0;  // 0xbb67 0xae85
        h2.x = 15470.0; h2.y = 62322.0;  // 0x3c6e 0xf372
        h3.x = 42319.0; h3.y = 62778.0;  // 0xa54f 0xf53a
        h4.x = 20750.0; h4.y = 21119.0;  // 0x510e 0x527f
        h5.x = 39685.0; h5.y = 26764.0;  // 0x9b05 0x688c
        h6.x =  8067.0; h6.y = 55723.0;  // 0x1f83 0xd9ab
        h7.x = 23520.0; h7.y = 52505.0;  // 0x5be0 0xcd19
	/*
         * for( i = 16; i < 64; i++) {
       	 *   w[i] = blend( w[ i - 16], w[ i - 15], w[ i -7], w[ i - 2]);
       	 * }
	 */
	// Implementation 
	// (Generated with bash script: for i in {16..63}; do echo "w$i = blend( w$((i - 16)), w$((i - 15)), w$((i -7)), w$((i - 2)));"; done ):
	w16 = blend( w0, w1, w9, w14);
	w17 = blend( w1, w2, w10, w15);
	w18 = blend( w2, w3, w11, w16);
	w19 = blend( w3, w4, w12, w17);
	w20 = blend( w4, w5, w13, w18);
	w21 = blend( w5, w6, w14, w19);
	w22 = blend( w6, w7, w15, w20);
	w23 = blend( w7, w8, w16, w21);
	w24 = blend( w8, w9, w17, w22);
	w25 = blend( w9, w10, w18, w23);
	w26 = blend( w10, w11, w19, w24);
	w27 = blend( w11, w12, w20, w25);
	w28 = blend( w12, w13, w21, w26);
	w29 = blend( w13, w14, w22, w27);
	w30 = blend( w14, w15, w23, w28);
	w31 = blend( w15, w16, w24, w29);
	w32 = blend( w16, w17, w25, w30);
	w33 = blend( w17, w18, w26, w31);
	w34 = blend( w18, w19, w27, w32);
	w35 = blend( w19, w20, w28, w33);
	w36 = blend( w20, w21, w29, w34);
	w37 = blend( w21, w22, w30, w35);
	w38 = blend( w22, w23, w31, w36);
	w39 = blend( w23, w24, w32, w37);
	w40 = blend( w24, w25, w33, w38);
	w41 = blend( w25, w26, w34, w39);
	w42 = blend( w26, w27, w35, w40);
	w43 = blend( w27, w28, w36, w41);
	w44 = blend( w28, w29, w37, w42);
	w45 = blend( w29, w30, w38, w43);
	w46 = blend( w30, w31, w39, w44);
	w47 = blend( w31, w32, w40, w45);
	w48 = blend( w32, w33, w41, w46);
	w49 = blend( w33, w34, w42, w47);
	w50 = blend( w34, w35, w43, w48);
	w51 = blend( w35, w36, w44, w49);
	w52 = blend( w36, w37, w45, w50);
	w53 = blend( w37, w38, w46, w51);
	w54 = blend( w38, w39, w47, w52);
	w55 = blend( w39, w40, w48, w53);
	w56 = blend( w40, w41, w49, w54);
	w57 = blend( w41, w42, w50, w55);
	w58 = blend( w42, w43, w51, w56);
	w59 = blend( w43, w44, w52, w57);
	w60 = blend( w44, w45, w53, w58);
	w61 = blend( w45, w46, w54, w59);
	w62 = blend( w46, w47, w55, w60);
	w63 = blend( w47, w48, w56, w61);

	/*
	 * Initialize hash value for this chunk:
    	 * a := h0
	 * b := h1
    	 * c := h2
    	 * d := h3
    	 * e := h4
    	 * f := h5
    	 * g := h6
    	 * h := h7
	 */
	// Implementation:
	a = h0;
	b = h1;
	c = h2;
	d = h3;
	e = h4;
	f = h5;
	g = h6;
	h = h7;

	/*
	 * Main loop:
	 * for i from 0 to 63
         *     s0 := (a rightrotate 2) xor (a rightrotate 13) xor (a rightrotate 22)
         *     maj := (a and b) xor (a and c) xor (b and c)
         *     t2 := s0 + maj
         *     s1 := (e rightrotate 6) xor (e rightrotate 11) xor (e rightrotate 25)
         *     ch := (e and f) xor ((not e) and g)
         *     t1 := h + s1 + ch + k[i] + w[i]
	 *
	 *     h := g
         *     g := f
         *     f := e
         *     e := d + t1
         *     d := c
         *     c := b
         *     b := a
         *     a := t1 + t2
	*/
	// Implementation:
	// ( Generated with bash script: 
	// for i in {0..63}; do echo "t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k$i + w$i;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;"; done
	// )
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k0 + w0;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k1 + w1;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k2 + w2;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k3 + w3;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k4 + w4;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k5 + w5;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k6 + w6;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k7 + w7;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k8 + w8;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k9 + w9;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k10 + w10;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k11 + w11;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k12 + w12;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k13 + w13;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k14 + w14;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k15 + w15;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k16 + w16;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k17 + w17;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k18 + w18;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k19 + w19;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k20 + w20;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k21 + w21;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k22 + w22;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k23 + w23;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k24 + w24;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k25 + w25;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k26 + w26;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k27 + w27;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k28 + w28;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k29 + w29;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k30 + w30;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k31 + w31;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k32 + w32;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k33 + w33;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k34 + w34;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k35 + w35;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k36 + w36;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k37 + w37;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k38 + w38;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k39 + w39;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k40 + w40;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k41 + w41;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k42 + w42;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k43 + w43;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k44 + w44;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k45 + w45;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k46 + w46;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k47 + w47;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k48 + w48;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k49 + w49;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k50 + w50;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k51 + w51;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k52 + w52;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k53 + w53;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k54 + w54;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k55 + w55;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k56 + w56;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k57 + w57;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k58 + w58;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k59 + w59;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k60 + w60;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k61 + w61;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k62 + w62;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;
	t2 = s0( a) + maj( a, b, c); t1 = h + s1( e) + ch( e, f, g) + k63 + w63;  h = g; g = f; f = e; e = d + t1; d = c; c = b; b = a; a = t1 + t2;

	/*
	 * Add this chunk's hash to result so far:
    	 * h0 := h0 + a
    	 * h1 := h1 + b
    	 * h2 := h2 + c
    	 * h3 := h3 + d
    	 * h4 := h4 + e
    	 * h5 := h5 + f
    	 * h6 := h6 + g
    	 * h7 := h7 + h
	 */
	h0 = add( h0, a);
	h1 = add( h1, b);
	h2 = add( h2, c);
	h3 = add( h3, d);
	h4 = add( h4, e);
	h5 = add( h5, f);
	h6 = add( h6, g);
	h7 = add( h7, h);	

	// Compare the nonce with the decoded difficulty.

	// ToDo: check for endianess!!!

	if( isSmaller( h7, decoded_difficulty7) 
	    + isSmaller( h6, decoded_difficulty6) 
	    + isSmaller( h5, decoded_difficulty5) 
	    + isSmaller( h4, decoded_difficulty4)
	    + isSmaller( h3, decoded_difficulty3) 
	    + isSmaller( h2, decoded_difficulty2) 
	    + isSmaller( h1, decoded_difficulty1) 
	    + isSmaller( h0, decoded_difficulty0) == 8.0) {
	    result = nonce;  // Found a valid nonce!
	} else {
	    result.x = -nonce.x;  // Return -nonce to indicate, that this nonce was not valid...
	    result.y = -nonce.y;
	}

}

#version 130
#pragma optionNV(unroll all)

uint ROTLEFT(in uint a, in int b) { return (a << b) | (a >> (32-b)); }
uint ROTRIGHT(in uint a, in int b) { return (a >> b) | (a << (32-b)); }

uint CH(in uint x,in uint y,in uint z) { return (x & y) ^ (~x & z); }
uint MAJ(in uint x,in uint y,in uint z) { return (x & y) ^ (x & z) ^ (y & z); }
uint EP0(in uint x) { return ROTRIGHT(x,2) ^ ROTRIGHT(x,13) ^ ROTRIGHT(x,22); }
uint EP1(in uint x) { return ROTRIGHT(x,6) ^ ROTRIGHT(x,11) ^ ROTRIGHT(x,25); }
uint SIG0(in uint x) { return ROTRIGHT(x,7) ^ ROTRIGHT(x,18) ^ (x >> 3); }
uint SIG1(in uint x) { return ROTRIGHT(x,17) ^ ROTRIGHT(x,19) ^ (x >> 10); }

uint k[64] = uint[64](
	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5,0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5,
	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3,0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174,
	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc,0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da,
	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7,0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967,
	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13,0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85,
	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3,0xd192e819,0xd6990624,0xf40e3585,0x106aa070,
	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5,0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3,
	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208,0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
);

uniform uint midstate[8];
uniform uint text[16];

void main() {

	uint a,b,c,d,e,f,g,h,t1,t2,m[64];
	uint ee,eee,eeee;
	int i;

	a = midstate[0];
	b = midstate[1];
	c = midstate[2];
	d = midstate[3];
	e = midstate[4];
	f = midstate[5];
	g = midstate[6];
	h = midstate[7];

	for (i = 0;  i < 16; i++) m[i] = text[i];

	for (; i < 64; i++) m[i] = SIG1(m[i-2]) + m[i-7] + SIG0(m[i-15]) + m[i-16];

	for (i = 0; i < 64; i++) {
		t1 = h + EP1(e) + CH(e,f,g) + k[i] + m[i];
		t2 = EP0(a) + MAJ(a,b,c);
		h = g;
		g = f;
		f = e;
		e = d + t1;
		d = c;
		c = b;
		b = a;
		a = t1 + t2;
	}

	m[0] = midstate[0] + a;
	m[1] = midstate[1] + b;
	m[2] = midstate[2] + c;
	m[3] = midstate[3] + d;
	m[4] = midstate[4] + e;
	m[5] = midstate[5] + f;
	m[6] = midstate[6] + g;
	m[7] = midstate[7] + h;

	a = 0x6a09e667U;
	b = 0xbb67ae85U;
	c = 0x3c6ef372U;
	d = 0xa54ff53aU;
	e = 0x510e527fU;
	f = 0x9b05688cU;
	g = 0x1f83d9abU;
	h = 0x5be0cd19U;

	m[8]  = 0x80000000U;
	m[9]  = 0x00U;
	m[10] = 0x00U;
	m[11] = 0x00U;
	m[12] = 0x00U;
	m[13] = 0x00U;
	m[14] = 0x00U;
	m[15] = 0x100U;

	for (i = 16; i < 64; i++) m[i] = SIG1(m[i-2]) + m[i-7] + SIG0(m[i-15]) + m[i-16];

	for (i = 0; i < 57; i++) {
		t1 = h + EP1(e) + CH(e,f,g) + k[i] + m[i];
		t2 = EP0(a) + MAJ(a,b,c);
		h = g;
		g = f;
		f = e;
		e = d + t1;
		d = c;
		c = b;
		b = a;
		a = t1 + t2;
	}

	eeee = d + h + EP1(e) + CH(e,f,g) + 0x78a5636fU + m[57];
	eee = c + g + EP1(eeee) + CH(eeee,e,f) + 0x84c87814U + m[58];
	ee = b + f + EP1(eee) + CH(eee,eeee,e) + 0x8cc70208U + m[59];
	h = a + e + EP1(ee) + CH(ee,eee,eeee) + 0x90befffaU + m[60];

	if (0x5be0cd19U + h == 0x00U) {
		gl_FragColor=vec4(0.0,1.0,0.0,1.0);
	} else { gl_FragColor=vec4(1.0,0.0,0.0,1.0); }
}