Fix delayMicroseconds() on SAMD51 (arduino#77)

* Fix pulseIn() on SAMD51 by writing it in plain C, so that
the CM0+-specific pulse_asm won't need to be linked.
The SAMD51 is fast enough that we can time pulses with micros()
Tested with a bunch of pulse lengths from <1us to >1s

* Implement a new delayMicroseconds() function for SAMD51
This version enables the "Debug Watchpoint and Trace" module (DWT)
in startup.c and then uses the 32bit cycle counter that is part
of DWT to count cycles indepenent of instruction timing.
Tested for good accuracy with various values between 1 and 2000us.

Author: WestfW

cores/arduino/delay.c

@@ -61,6 +61,33 @@ unsigned long micros( void )
   // a runtime multiplication and shift, saving a few cycles
 }
 
+#ifdef __SAMD51__
+/*
+ * On SAMD51, use the (32bit) cycle count maintained by the DWT unit,
+ * and count exact number of cycles elapsed, rather than guessing how
+ * many cycles a loop takes, which is dangerous in the presence of
+ * cache.  The overhead of the call and internal code is "about" 20
+ * cycles.  (at 120MHz, that's about 1/6 us)
+ */
+void delayMicroseconds(unsigned int us)
+{
+  uint32_t start, elapsed;
+  uint32_t count;
+
+  if (us == 0)
+    return;
+
+  count = us * (VARIANT_MCK / 1000000) - 20;  // convert us to cycles.
+  start = DWT->CYCCNT;  //CYCCNT is 32bits, takes 37s or so to wrap.
+  while (1) {
+    elapsed = DWT->CYCCNT - start;
+    if (elapsed >= count)
+      return;
+  }
+}
+#endif
+
+
 void delay( unsigned long ms )
 {
   if ( ms == 0 )

cores/arduino/delay.h

@@ -61,28 +61,16 @@ extern void delay( unsigned long dwMs ) ;
  *
  * \param dwUs the number of microseconds to pause (uint32_t)
  */
+#if defined(__SAMD51__)
+extern void delayMicroseconds( unsigned int );
+#else
 static __inline__ void delayMicroseconds( unsigned int ) __attribute__((always_inline, unused)) ;
 static __inline__ void delayMicroseconds( unsigned int usec )
 {
   if ( usec == 0 )
   {
     return ;
   }
-
-#if defined(__SAMD51__)
-  uint32_t n = usec * (VARIANT_MCK / 1000000) / 12;
-
-  __asm__ __volatile__(
-    "1:              \n"
-    "   sub %0, #1   \n" // substract 1 from %0 (n)
-    "   cmp %0, #0   \n" // compare to 0
-    "   bne 1b       \n" // if result is not 0 jump to 1
-    : "+r" (n)           // '%0' is n variable with RW constraints
-    :                    // no input
-    :                    // no clobber
-  );
-
-#else
   /*
    *  The following loop:
    *
@@ -109,10 +97,10 @@ static __inline__ void delayMicroseconds( unsigned int usec )
     :                    // no input
     :                    // no clobber
   );
-#endif
   // https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html
   // https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html#Volatile
 }
+#endif
 
 #ifdef __cplusplus
 }

cores/arduino/startup.c

@@ -252,7 +252,14 @@ void SystemInit( void )
   CMCC->CTRL.reg = 1;
   __enable_irq();
 #endif
-  
+
+  /*---------------------------------------------------------------------
+   * Start up the "Debug Watchpoint and Trace" unit, so that we can use
+   * it's 32bit cycle counter for timing.
+   */
+  CoreDebug->DEMCR |= CoreDebug_DEMCR_TRCENA_Msk;
+  DWT->CTRL |= DWT_CTRL_CYCCNTENA_Msk;
+
 //*************** END SAMD51 *************************//
 
 #else