Another optimization question - can I speed up this 32 bit multiply?

Projects Programming
21

THIS one works. Why does THIS one work?

#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" \
)