public void mul4f(Matrix4fBuffer leftM, Matrix4fBuffer rightM) {
	final FloatBuffer left = leftM.buffer;
	final FloatBuffer right = rightM.buffer;
	final FloatBuffer buffer = this.buffer;

	float lm00 = left.get(0);
	float rm00 = right.get(0);

	float lm10 = left.get(1);
	float rm01 = right.get(4);

	float lm20 = left.get(2);
	float rm02 = right.get(8);

	float lm30 = left.get(3);

	buffer.put(0, lm00 * rm00 + lm10 * rm01 + lm20 * rm02 + lm30 * right.get(12));

	float rm10 = right.get(1);
	float rm11 = right.get(5);
	float rm12 = right.get(9);

	buffer.put(1, lm00 * rm10 + lm10 * rm11 + lm20 * rm12 + lm30 * right.get(13));

	float rm20 = right.get(2);
	float rm21 = right.get(6);
	float rm22 = right.get(10);

	buffer.put(2, lm00 * rm20 + lm10 * rm21 + lm20 * rm22 + lm30 * right.get(14));

	float rm30 = right.get(3);
	float rm31 = right.get(7);
	float rm32 = right.get(11);

	buffer.put(3, lm00 * rm30 + lm10 * rm31 + lm20 * rm32 + lm30 * right.get(15));

	float lm01 = left.get(4);
	float lm11 = left.get(5);
	float lm21 = left.get(6);
	float lm31 = left.get(7);

	buffer.put(4, lm01 * rm00 + lm11 * rm01 + lm21 * rm02 + lm31 * right.get(12));
	buffer.put(5, lm01 * rm10 + lm11 * rm11 + lm21 * rm12 + lm31 * right.get(13));
	buffer.put(6, lm01 * rm20 + lm11 * rm21 + lm21 * rm22 + lm31 * right.get(14));
	buffer.put(7, lm01 * rm30 + lm11 * rm31 + lm21 * rm32 + lm31 * right.get(15));

	float lm02 = left.get(8);
	float lm12 = left.get(9);
	float lm22 = left.get(10);
	float lm32 = left.get(11);

	buffer.put(8, lm02 * rm00 + lm12 * rm01 + lm22 * rm02 + lm32 * right.get(12));
	buffer.put(9, lm02 * rm10 + lm12 * rm11 + lm22 * rm12 + lm32 * right.get(13));
	buffer.put(10, lm02 * rm20 + lm12 * rm21 + lm22 * rm22 + lm32 * right.get(14));
	buffer.put(11, lm02 * rm30 + lm12 * rm31 + lm22 * rm32 + lm32 * right.get(15));

	float lm03 = left.get(12);
	float lm13 = left.get(13);
	float lm23 = left.get(14);
	float lm33 = left.get(15);

	buffer.put(12, lm03 * rm00 + lm13 * rm01 + lm23 * rm02 + lm33 * right.get(12));
	buffer.put(13, lm03 * rm10 + lm13 * rm11 + lm23 * rm12 + lm33 * right.get(13));
	buffer.put(14, lm03 * rm20 + lm13 * rm21 + lm23 * rm22 + lm33 * right.get(14));
	buffer.put(15, lm03 * rm30 + lm13 * rm31 + lm23 * rm32 + lm33 * right.get(15));
}