delayMicroseconds(): added support for 1Mhz, 12Mhz and 24Mhz

1Mhz is a default clock speed on Atmega328, many users run it on the
internal 1Mhz clock to save battery power. Up until now
delayMicroseconds() function wasn't taking this frequencies into an
account.

Author: Cano

hardware/arduino/avr/cores/arduino/wiring.c

@@ -119,17 +119,41 @@ void delay(unsigned long ms)
 	}
 }
 
-/* Delay for the given number of microseconds.  Assumes a 8 or 16 MHz clock. */
+/* Delay for the given number of microseconds.  Assumes a 1, 8, 12, 16, 20 or 24 MHz clock. */
 void delayMicroseconds(unsigned int us)
 {
+  // call = 4 cycles + 2 to 4 cycles to init us(2 for constant delay, 4 for variable)
 	// calling avrlib's delay_us() function with low values (e.g. 1 or
 	// 2 microseconds) gives delays longer than desired.
 	//delay_us(us);
-#if F_CPU >= 20000000L
+#if F_CPU >= 24000000L
+	// for the 24 MHz clock for the aventurous ones, trying to overclock
+
+	// for a one-microsecond delay, simply wait 6 cycles and return. The overhead
+	// of the function call yields a delay of exactly one microsecond.
+	__asm__ __volatile__ (
+		"nop" "\n\t"
+		"nop" "\n\t"
+		"nop" "\n\t"
+		"nop" "\n\t"
+		"nop" "\n\t"
+		"nop"); //just waiting 6 cycles
+	if (--us == 0)
+		return;
+
+	// the following loop takes a 1/6 of a microsecond (4 cycles)
+	// per iteration, so execute it six times for each microsecond of
+	// delay requested.
+	us *= 6; // x6 us
+
+	// account for the time taken in the preceeding commands.
+	us -= 2;
+
+#elif F_CPU >= 20000000L
 	// for the 20 MHz clock on rare Arduino boards
 
-	// for a one-microsecond delay, simply wait 2 cycle and return. The overhead
-	// of the function call yields a delay of exactly a one microsecond.
+	// for a one-microsecond delay, simply wait 2 cycles and return. The overhead
+	// of the function call yields a delay of exactly one microsecond.
 	__asm__ __volatile__ (
 		"nop" "\n\t"
 		"nop"); //just waiting 2 cycle
@@ -152,15 +176,31 @@ void delayMicroseconds(unsigned int us)
 	if (--us == 0)
 		return;
 
-	// the following loop takes a quarter of a microsecond (4 cycles)
+	// the following loop takes 1/4 of a microsecond (4 cycles)
 	// per iteration, so execute it four times for each microsecond of
 	// delay requested.
-	us <<= 2;
+	us <<= 2; // x4 us
 
 	// account for the time taken in the preceeding commands.
 	us -= 2;
-#else
-	// for the 8 MHz internal clock on the ATmega168
+
+#elif F_CPU >= 12000000L
+	// for the 12 MHz clock if somebody is working with USB
+
+	// for a one-microsecond delay, simply return.  the overhead
+	// of the function call yields a delay of approximately 1.5 us.
+	if (--us == 0)
+		return;
+
+	// the following loop takes 1/3 of a microsecond (4 cycles)
+	// per iteration, so execute it three times for each microsecond of
+	// delay requested.
+	us = (us << 1) + us; // x3 us
+
+	// account for the time taken in the preceeding commands.
+	us -= 2;
+#elif F_CPU >= 8000000L
+	// for the 8 MHz internal clock
 
 	// for a one- or two-microsecond delay, simply return.  the overhead of
 	// the function calls takes more than two microseconds.  can't just
@@ -170,21 +210,39 @@ void delayMicroseconds(unsigned int us)
 	if (--us == 0)
 		return;
 
-	// the following loop takes half of a microsecond (4 cycles)
+	// the following loop takes 1/2 of a microsecond (4 cycles)
 	// per iteration, so execute it twice for each microsecond of
 	// delay requested.
-	us <<= 1;
+	us <<= 1; //x2 us
 
 	// partially compensate for the time taken by the preceeding commands.
 	// we can't subtract any more than this or we'd overflow w/ small delays.
 	us--;
+
+#else
+	// for the 1 MHz internal clock (default settings for common Atmega microcontrollers)
+
+	// the overhead of the function calls takes about 16 microseconds.
+	if (us <= 16) //4 cycles spent here
+		return;
+	if (us <= 22) { //4 cycles spent here
+    return;
+	}
+	
+	// compensate for the time taken by the preceeding and next commands.
+	us -= 22;
+
+	// the following loop takes 4 microseconds (4 cycles)
+	// per iteration, so execute it us/4 times
+	us >>= 2; // us div 4
 #endif
 
 	// busy wait
 	__asm__ __volatile__ (
 		"1: sbiw %0,1" "\n\t" // 2 cycles
 		"brne 1b" : "=w" (us) : "0" (us) // 2 cycles
 	);
+	// return = 4 cycles
 }
 
 void init()