// guest openmusiclabs 6.8.11
// taken from http://mekonik.wordpress.com/2009/03/18/arduino-avr-gcc-multiplication/

// longRes = intIn1 * intIn2
#define MultiU16X16to32(longRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"movw %A0, r0 \n\t" \
"mul %B1, %B2 \n\t" \
"movw %C0, r0 \n\t" \
"mul %B2, %A1 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"mul %B1, %A2 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (longRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26" \
) 

// intRes = intIn1 * intIn2 >> 16
// uses:
// r26 to store 0
// r27 to store the byte 1 of the 32bit result
#define MultiU16X16toH16(intRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"mov r27, r1 \n\t" \
"mul %B1, %B2 \n\t" \
"movw %A0, r0 \n\t" \
"mul %B2, %A1 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"mul %B1, %A2 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (intRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26" , "r27" \
) 

// intRes = intIn1 * intIn2 >> 16 + round
// uses:
// r26 to store 0
// r27 to store the byte 1 of the 32bit result
// 21 cycles
#define MultiU16X16toH16Round(intRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"mov r27, r1 \n\t" \
"mul %B1, %B2 \n\t" \
"movw %A0, r0 \n\t" \
"mul %B2, %A1 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"mul %B1, %A2 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"lsl r27 \n\t" \
"adc %A0, r26 \n\t" \
"adc %B0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (intRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26" , "r27" \
) 


// signed16 * signed16
// 22 cycles
#define MultiS16X16to32(longRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"movw %A0, r0 \n\t" \
"muls %B1, %B2 \n\t" \
"movw %C0, r0 \n\t" \
"mulsu %B2, %A1 \n\t" \
"sbc %D0, r26 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"mulsu %B1, %A2 \n\t" \
"sbc %D0, r26 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (longRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26" \
)


// signed16 * signed 16 >> 16
#define MultiS16X16toH16(intRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"mov r27, r1 \n\t" \
"muls %B1, %B2 \n\t" \
"movw %A0, r0 \n\t" \
"mulsu %B2, %A1 \n\t" \
"sbc %B0, r26 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"mulsu %B1, %A2 \n\t" \
"sbc %B0, r26 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (intRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26", "r27" \
)

// multiplies a signed and unsigned 16 bit ints with a 32 bit result
#define MultiSU16X16to32(longRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"movw %A0, r0 \n\t" \
"mulsu %B1, %B2 \n\t" \
"movw %C0, r0 \n\t" \
"mul %B2, %A1 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"mulsu %B1, %A2 \n\t" \
"sbc %D0, r26 \n\t" \
"add %B0, r0 \n\t" \
"adc %C0, r1 \n\t" \
"adc %D0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (longRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26" \
)

// multiplies signed x unsigned int and returns the highest 16 bits of the result
#define MultiSU16X16toH16(intRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"mov r27, r1 \n\t" \
"mulsu %B1, %B2 \n\t" \
"movw %A0, r0 \n\t" \
"mul %B2, %A1 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"mulsu %B1, %A2 \n\t" \
"sbc %B0, r26 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (intRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26", "r27" \
)

// multiplies signed x unsigned int and returns the highest 16 bits of the result
// rounds the result based on the MSB of the lower 16 bits
// 22 cycles
#define MultiSU16X16toH16Round(intRes, intIn1, intIn2) \
asm volatile ( \
"clr r26 \n\t" \
"mul %A1, %A2 \n\t" \
"mov r27, r1 \n\t" \
"mulsu %B1, %B2 \n\t" \
"movw %A0, r0 \n\t" \
"mul %A1, %B2 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"mulsu %B1, %A2 \n\t" \
"sbc %B0, r26 \n\t" \
"add r27, r0 \n\t" \
"adc %A0, r1 \n\t" \
"adc %B0, r26 \n\t" \
"lsl r27 \n\t" \
"adc %A0, r26 \n\t" \
"adc %B0, r26 \n\t" \
"clr r1 \n\t" \
: \
"=&r" (intRes) \
: \
"a" (intIn1), \
"a" (intIn2) \
: \
"r26", "r27" \
)