diff --git a/uint256.go b/uint256.go
index 493f44a..7b93ee9 100644
--- a/uint256.go
+++ b/uint256.go
@@ -369,9 +369,9 @@ func umul(x, y *Int, res *[8]uint64) {
 func (z *Int) Mul(x, y *Int) *Int {
 	var (
 		carry0, carry1, carry2 uint64
-		res1, res2 uint64
-		x0, x1, x2, x3 = x[0], x[1], x[2], x[3]
-		y0, y1, y2, y3 = y[0], y[1], y[2], y[3]
+		res1, res2             uint64
+		x0, x1, x2, x3         = x[0], x[1], x[2], x[3]
+		y0, y1, y2, y3         = y[0], y[1], y[2], y[3]
 	)
 
 	carry0, z[0] = bits.Mul64(x0, y0)
@@ -1283,14 +1283,14 @@ func (z *Int) Sqrt(x *Int) *Int {
 	if x.IsUint64() {
 		var (
 			x0 uint64 = x.Uint64()
-			z1 uint64 = 1 << ((bits.Len64(x0)+1)/2)
+			z1 uint64 = 1 << ((bits.Len64(x0) + 1) / 2)
 			z2 uint64
 		)
 		if x0 < 2 {
 			return z.SetUint64(x0)
 		}
 		for {
-			z2 = (z1 + x0 / z1) >> 1
+			z2 = (z1 + x0/z1) >> 1
 			if z2 >= z1 {
 				return z.SetUint64(z1)
 			}
@@ -1306,27 +1306,24 @@ func (z *Int) Sqrt(x *Int) *Int {
 
 	// We can do the first division outside the loop
 	z2.Rsh(x, uint(x.BitLen()+1)/2) // The first div is equal to a right shift
-	first := true
 
 	for {
-		// z2.Div(x, z1) -- x > MaxUint64, x > z1 > 0
-		if !first { // first division was done outside the loop
-			z2.Clear()
-			udivrem(z2[:], x[:], z1, nil)
-		}
-		first = false
 		z2.Add(z2, z1)
-		
+
 		// z2 = z2.Rsh(z2, 1) -- the code below does a 1-bit rsh faster
-		z2[0] = (z2[0] >> 1) | z2[1] << 63
-		z2[1] = (z2[1] >> 1) | z2[2] << 63
-		z2[2] = (z2[2] >> 1) | z2[3] << 63
+		z2[0] = (z2[0] >> 1) | z2[1]<<63
+		z2[1] = (z2[1] >> 1) | z2[2]<<63
+		z2[2] = (z2[2] >> 1) | z2[3]<<63
 		z2[3] >>= 1
 
 		if !z2.Lt(z1) {
 			return z.Set(z1)
 		}
 		z1.Set(z2)
+		// Next iteration of the loop
+		// z2.Div(x, z1) -- x > MaxUint64, x > z1 > 0
+		z2.Clear()
+		udivrem(z2[:], x[:], z1, nil)
 	}
 }