short unsigned int heightcolor(float z, float z_min, float z_max) {
float frac = ((z-z_min)/(z_max-z_min));
//color!
float r = (0.25f)-frac;
float g = (0.5f)-frac;
float b = (0.75f)-frac;
//calculate the R/G/B values
r = (r>0.f)?r:-r; g = (g>0.f)?g:-g; b = (b>0.f)?b:-b; //absolute value
r = (0.25f)-r; g = (1.f/3.f)-g; b = (0.25f)-b; //invert
r = (r>0.f)?(6.f*r):0.f; g = (g>0.f)?(6.f*g):0.f; b = (b>0.f)?(6.f*b):0.f; //scale the chromatic triangles
r = (r>1.f)?1.f:r; g = (g>1.f)?1.f:g; b = (b>1.f)?1.f:b; //clip the top of the chromatic triangles
if (frac < 0.25f) r = (r+1.f)/2.f; //adjust the bottom end of the scale so that z_min is red, not black
if (frac > 0.75f) b = (b+1.f)/2.f; //adjust the top end of the scale so that z_max is blue, not black
return (short unsigned int)(0x0000ffff & (((int)(31.f*r) << 11) | ((int)(63.f*g) << 5) | ((int)(31.f*b)))); //put the bits together
}
It fit into my program really well and I barely had to change anything: https://img.ourl.ca/rfg/mandelbrot-kerm-color.png 
/* Awesome color routine from Kerm!! */
private Color getColor(float z, float z_min, float z_max) {
float frac = ((z-z_min)/(z_max-z_min));
//color!
float r = (0.25f)-frac;
float g = (0.5f)-frac;
float b = (0.75f)-frac;
//calculate the R/G/B values
r = (r>0.f)?r:-r; g = (g>0.f)?g:-g; b = (b>0.f)?b:-b; //absolute value
r = (0.25f)-r; g = (1.f/3.f)-g; b = (0.25f)-b; //invert
r = (r>0.f)?(6.f*r):0.f; g = (g>0.f)?(6.f*g):0.f; b = (b>0.f)?(6.f*b):0.f; //scale the chromatic triangles
r = (r>1.f)?1.f:r; g = (g>1.f)?1.f:g; b = (b>1.f)?1.f:b; //clip the top of the chromatic triangles
if (frac < 0.25f) r = (r+1.f)/2.f; //adjust the bottom end of the scale so that z_min is red, not black
if (frac > 0.75f) b = (b+1.f)/2.f; //adjust the top end of the scale so that z_max is blue, not black
return new Color(r, g, b);
//return (short unsigned int)(0x0000ffff & (((int)(31.f*r) << 11) | ((int)(63.f*g) << 5) | ((int)(31.f*b)))); //put the bits together
}return getColor((float)iteration, (float)0, 200.0f);unsigned short int palette[4] = {COLOR_BLACK, COLOR_BLUEVIOLET, COLOR_RED, COLOR_WHITE};
CopySpriteMasked2bit(mysprite, 5, 70, 32, 32, palette);
CopySprite2bit(mysprite, 5, 70, 32, 32, palette);void CopySpriteMasked2bit(const unsigned char* data, int x, int y, int width, int height, short unsigned int* palette) {
short unsigned int* VRAM = (short unsigned int*)0xA8000000;
VRAM += (LCD_WIDTH_PX*y + x);
int offset = 0;
unsigned char buf;
for(int j=y; j<y+height; j++) {
int availbits = 0;
for(int i=x; i<x+width; i++) {
if (!availbits) {
buf = data[offset++];
availbits = 8;
}
char this = ((buf&0xC0)>>6);
if (this != 0x02)
*VRAM = palette[(int)this];
VRAM++;
buf<<=2;
availbits-=2;
}
VRAM += (LCD_WIDTH_PX-width);
}
}void CopySprite2bit(const unsigned char* data, int x, int y, int width, int height, short unsigned int* palette) {
short unsigned int* VRAM = (short unsigned int*)0xA8000000;
VRAM += (LCD_WIDTH_PX*y + x);
int offset = 0;
unsigned char buf;
for(int j=y; j<y+height; j++) {
int availbits = 0;
for(int i=x; i<x+width; i++) {
if (!availbits) {
buf = data[offset++];
availbits = 8;
}
char this = ((buf&0xC0)>>6);
*VRAM = palette[(int)this];
VRAM++;
buf<<=2;
availbits-=2;
}
VRAM += (LCD_WIDTH_PX-width);
}
}
int _g_strcmp(char *a, char *b)
{
const char* p1 = a - 1;
const char* p2 = b - 1;
while (*++p2 == *++p1)
if (!*p2 || !*p1)
break;
if (*p2 > *p1)
return (-1);
else if (*p1 > *p2)
return (1);
return (0);
}
It took me quite a while to work up the motivation to write it, but once I started, it actually was surprisingly fast to complete it. 
#define PLL_24x 0b010111 // 87 MHz
#define PLL_18x 0b010001 // 65.25 MHz
#define PLL_16x 0b001111 // 58 MHz (NORMAL SPEED)
#define PLL_15x 0b001110 // 54.37 MHz
#define PLL_12x 0b001011 // 43.5 MHz
#define PLL_8x 0b000111 // 29 MHz
#define PLL_6x 0b000101 // 21.75 MHz
#define PLL_4x 0b000011 // 14.5 MHz
#define PLL_3x 0b000010 // 10.8 MHz
#define PLL_2x 0b000001 // 7.25 MHz
#define PLL_1x 0b000000 // 3.6 MHz
__attribute__ ((noinline)) void change_freq(int mult) {
__asm__(
"mov r4, r0\n\t"
"and #0x3F, r0\n\t"
"shll16 r0\n\t"
"shll8 r0\n\t"
"mov.l frqcr, r1\n\t"
"mov.l pll_mask, r3\n\t"
"mov.l @r1, r2\n\t"
"and r3, r2\n\t"
"or r0, r2\n\t"
"mov.l r2, @r1\n\t"
"mov.l frqcr_kick_bit, r0\n\t"
"mov.l @r1, r2\n\t"
"or r0, r2\n\t"
"rts\n\t"
"mov.l r2, @r1\n\t"
".align 4\n\t"
"frqcr_kick_bit: .long 0x80000000\n\t"
"pll_mask: .long 0xC0FFFFFF\n\t"
"frqcr: .long 0xA4150000\n\t"
);
}
void change_freq(uint8_t mult) {
volatile uint32_t * const frqcr = 0xA4150000;
uin32_t cr = *frqcr;
cr &= ~(0x3F << 24);
cr |= (mult & 0x3F) << 24;
frqcr = cr;
frqcr |= 0x80000000;
}
#define PLL_24x 0b010111 // 87 MHz
#define PLL_18x 0b010001 // 65.25 MHz
#define PLL_16x 0b001111 // 58 MHz (NORMAL SPEED)
#define PLL_15x 0b001110 // 54.37 MHz
#define PLL_12x 0b001011 // 43.5 MHz
#define PLL_8x 0b000111 // 29 MHz
#define PLL_6x 0b000101 // 21.75 MHz
#define PLL_4x 0b000011 // 14.5 MHz
#define PLL_3x 0b000010 // 10.8 MHz
#define PLL_2x 0b000001 // 7.25 MHz
#define PLL_1x 0b000000 // 3.6 MHz
void change_freq(int mult) {
__asm__(
"mov #26, r0\n\t"
"shld r0, r4\n\t"
"shlr2 r4\n\t"
"mov.l frqcr, r1\n\t"
"mov.l pll_mask, r3\n\t"
"mov.l @r1, r2\n\t"
"and r3, r2\n\t"
"or r4, r2\n\t"
"mov.l r2, @r1\n\t"
"mov #1, r0\n\t"
"rotr r0\n\t"
"or r0, r2\n\t"
"rts\n\t"
"mov.l r2, @r1\n\t"
".align 4\n\t"
"pll_mask: .long 0xC0FFFFFF\n\t"
"frqcr: .long 0xA4150000\n\t"
);
}
(and in my case, the point of learning SH assembly) The C version should be fine; and of course, this routine in particular doesn't need to be optimized, since you won't be using it in a main game render loop. Advertisement
