#include <u.h>
#include <libc.h>

typedef struct Movtab Movtab;
typedef void* (*Movfn)(void*, void*, ulong);

	u32int	runtimecpuid_edx = 0x4000000;
extern	void*	runtimememmove(void*, void*, ulong);

struct Movtab {
	Movfn	f;
	char	*name;
};

uvlong	hz;
int	sztab[] = {1, 2, 4, 8, 16, 32, 64, 128, 512, 1024, 4096, 128*1024, };
uchar	buf0[128*1024];
uchar	buf1[128*1024];
Movtab	movtab[] = {memmove, "memmove",  runtimememmove, "rt·memmove", };
//Movfn	movtab[] = {memmove, runtimememmove};

uvlong
gethz(void)
{
	char buf[1024], *f[5];
	int n, fd;

	fd = open("/dev/time", OREAD);
	if(fd == -1)
		sysfatal("%s: open /dev/time: %r", argv0);
	n = pread(fd, buf, sizeof buf-1, 0);
	if(n <= 0)
		sysfatal("%s: read /dev/time: %r", argv0);

	buf[n] = 0;
	n = tokenize(buf, f, nelem(f));
	if(n < 4)
		sysfatal("%s: /dev/time: unexpected fmt", argv0);

	return strtoull(f[3], 0, 0);
}

void
inner(Movfn f, ulong sz)
{
	int i;

	for(i = 0; i < 1024; i++)
		f(buf1, buf0, sz);
}

void
main(int argc, char **argv)
{
	int i, j;
	uvlong t[2], c[nelem(movtab)][nelem(sztab)];
//	double dhz;
	Movfn f;

	ARGBEGIN{
	}ARGEND

	hz = gethz();
//	dhz = hz;

	for(i = 0; i < 2; i++){
		print("%s\n", movtab[i].name);
		f = movtab[i].f;
		for(j = 0; j < nelem(sztab); j++){
			cycles(t + 0);
			inner(f, sztab[j]);
			cycles(t + 1);
			c[i][j] = t[1] - t[0];

			print("%d	%g cycles/op\n", sztab[j], c[i][j]/1024.);
			sleep(0);
		}
		print("\n");
	}

	exits("");
}