// compile with: dmd test.d -inline -O -release -w

import std.stdio;
import std.string;
import std.c.windows.windows;    

struct Vector3f {
	float x, y, z;

	void opAddAssign(ref Vector3f v) {
		x += v.x;
		y += v.y;
		z += v.z;
	}

	Vector3f opMul(float s) {
		return Vector3f(x * s, y * s, z * s);
	}
}

int main(char[][] args) {
	long start, end, freq;
	QueryPerformanceFrequency(&freq);
	Vector3f v1 = {1.0f, 2.0f, 3.0f};
	Vector3f v2 = {4.0f, 5.0f, 6.0f};

/*	float t;
	asm {
		movss	XMM1, t;
	}*/

	QueryPerformanceCounter(&start);
	for (int i=0; i<0x40FFFFFF; i++) {
		// do something nontrivial...
		v2 += v1 * 3.0f;
	}
	QueryPerformanceCounter(&end);
	writefln("%.3fs", (end - start) / cast(float)freq);

	// to ensure that the compiler doesn't eliminate/optimize the inner loop
	writefln("(", v1.x, " ", v1.y, " ", v1.z, ") (", v2.x, " ", v2.y, " ", v2.z, ")"); 
	return 0;
}