add missing memory barrier for Apple Silicon targets

Signed-off-by: Anjan Roy <hello@itzmeanjan.in>

src/dudect.h

@@ -77,6 +77,7 @@ extern "C" {
 #include <x86intrin.h>
 #elif defined __APPLE__
 #include <mach/mach_time.h>
+#include <stdatomic.h>
 #else
 #include <time.h>
 #endif
@@ -293,11 +294,11 @@ static inline int64_t cpucycles(void) {
 /*
   Returns current CPU cycle count from aarch64 *P*erformance *M*onitors *C*ycle Counter (PMCCNTR_EL0).
 
-  To enforce CPU to complete all pending memory access operations, appearing before PMCCTR_EL0, we issue a 
+  To enforce CPU to complete all pending memory access operations, appearing before PMCCTR_EL0, we issue a
   *D*ata *S*ynchronization *B*arrier instruction right before reading CPU cycle counter.
 
-  Note, issuing PMCCTR_EL0 instruction from the userspace will probably result in panicing with 
-  a message "illegal instruction executed". So we've to install a Linux Kernel Module. I've tested the 
+  Note, issuing PMCCTR_EL0 instruction from the userspace will probably result in panicing with
+  a message "illegal instruction executed". So we've to install a Linux Kernel Module. I've tested the
   LKM @ https://github.com/jerinjacobk/armv8_pmu_cycle_counter_el0 and it works fine.
 
   See PMCCTR_EL0 documentation @ https://developer.arm.com/documentation/ddi0595/2021-09/External-Registers/PMCCNTR-EL0--Performance-Monitors-Cycle-Counter?lang=en
@@ -315,17 +316,18 @@ static inline int64_t cpucycles(void) {
 
 /*
   Returns the number of "mach time units" elapsed since system startup, on non-x86_64 Apple targets.
-  
+
   See https://github.com/google/benchmark/blob/4682db08/src/cycleclock.h#L63-L73
 */
 static inline int64_t cpucycles(void) {
+  atomic_thread_fence(memory_order_seq_cst);
   return (int64_t)mach_absolute_time();
 }
 
 #else
 
 /*
-  Returns approximate measurement of CPU time consumed by the calling process (i.e., CPU time 
+  Returns approximate measurement of CPU time consumed by the calling process (i.e., CPU time
   consumed by all threads in the process).
 
   See https://www.man7.org/linux/man-pages/man3/clock_gettime.3.html