#ifndef _E6103821_0B93_11d4_B033_00A40080D29C
#define _E6103821_0B93_11d4_B033_00A40080D29C

#if !defined(__cplusplus)
#error C++ compiler required.
#endif

/*#ifdef cpuid
#error cpuid already defined
#endif
#ifdef rdtsc
#error rdtsc already defined
#endif

  #define cpuid __asm __emit 0fh __asm __emit 0a2h
#define rdtsc __asm __emit 0fh __asm __emit 031h*/

namespace microtime {
	
	unsigned base_;
	
	unsigned cycles_start_low_;
	unsigned cycles_start_high_;
	
	unsigned calibrate() 
	{
		unsigned base,base_extra=0;
		unsigned cycles_low, cycles_high;
		
		__asm {
			pushad						;
			CPUID						;

			RDTSC						;
			mov		cycles_high, edx	;
			mov		cycles_low, eax		;
			popad						;
			pushad						;
			CPUID						;
			RDTSC						;
			popad						;
			
			pushad						;
			CPUID						;
			RDTSC						;
			mov		cycles_high, edx	;
			mov		cycles_low, eax		;
			popad						;
			pushad						;
			CPUID						;
			RDTSC						;
			popad						;
			
			pushad						;
			CPUID						;

			RDTSC						;
			mov     cycles_high, edx	;	
			mov		cycles_low, eax		;
			popad						;
			pushad						;
			CPUID						;

			RDTSC						;
			sub		eax, cycles_low		;
			mov		base_extra, eax		;
			popad						;
			
			pushad						;
			CPUID						;
			RDTSC						;
			mov     cycles_high, edx	;
			mov		cycles_low, eax		;
			popad						;
			pushad						;

			CPUID						;
			RDTSC						;
			sub		eax, cycles_low		;
			mov		base, eax			;
			popad						;
			
		} // End inline assembly
		
		// The following provides insurance for the above code,
		// in the instance the final test causes a miss to the 
		// instruction cache.
		if (base_extra < base)
			base = base_extra;

		base += 1;
		
		base_ = base;
		return base;
	}
	
	inline void start()
	{
		__asm {
			pushad
;
			CPUID
;
			RDTSC
;
			mov		cycles_start_high_, edx	;
			mov		cycles_start_low_, eax	;
			popad
;
		}
	}
	
	inline void stop(__int64& elapsed_clocks)
	{
		unsigned cycles_end_low;
		unsigned cycles_end_high;
		
		__asm {
			pushad
;
			CPUID
;
			RDTSC
;
			mov		cycles_end_high, edx	;
			mov		cycles_end_low, eax	;
			popad
		}
		
		__int64 cycles_start;
		__int64 cycles_end;
		
		cycles_start = __int64(cycles_start_low_) +
(__int64(cycles_start_high_) << 32);
		cycles_end = __int64(cycles_end_low) +
(__int64(cycles_end_high) << 32);
		
		elapsed_clocks = cycles_end - cycles_start - base_;
	}
	
	
};

#endif