From 4575c8a4d825d0d23506866e5fe90a5ecd479649 Mon Sep 17 00:00:00 2001
From: Webster Sheets <webster@web-eworks.com>
Date: Tue, 7 Nov 2023 20:54:56 -0500
Subject: [PATCH] Improve perlin noise performance

- On my machine compiled for SSE2, this provides an approximately 20% performance improvement to noise generation functions (33 -> 26 MCycles)
- Replaces simplex offset computation if statements with a 100% identical bitwise computation
- Also rearrange the gradient dot functions for better readability (no performance change)
---
 src/perlin.cpp | 88 ++++++++++++--------------------------------------
 1 file changed, 21 insertions(+), 67 deletions(-)

diff --git a/src/perlin.cpp b/src/perlin.cpp
index c18557ccc15..dbbe31bae84 100644
--- a/src/perlin.cpp
+++ b/src/perlin.cpp
@@ -132,57 +132,18 @@ double noise(const vector3d &p)
 	int i1, j1, k1; // Offsets for second corner of simplex in (i,j,k) coords
 	int i2, j2, k2; // Offsets for third corner of simplex in (i,j,k) coords
 
-	if (x0 >= y0) {
-		if (y0 >= z0) {
-			i1 = 1;
-			j1 = 0;
-			k1 = 0;
-			i2 = 1;
-			j2 = 1;
-			k2 = 0;
-		} // X Y Z order
-		else if (x0 >= z0) {
-			i1 = 1;
-			j1 = 0;
-			k1 = 0;
-			i2 = 1;
-			j2 = 0;
-			k2 = 1;
-		} // X Z Y order
-		else {
-			i1 = 0;
-			j1 = 0;
-			k1 = 1;
-			i2 = 1;
-			j2 = 0;
-			k2 = 1;
-		} // Z X Y order
-	} else { // x0<y0
-		if (y0 < z0) {
-			i1 = 0;
-			j1 = 0;
-			k1 = 1;
-			i2 = 0;
-			j2 = 1;
-			k2 = 1;
-		} // Z Y X order
-		else if (x0 < z0) {
-			i1 = 0;
-			j1 = 1;
-			k1 = 0;
-			i2 = 0;
-			j2 = 1;
-			k2 = 1;
-		} // Y Z X order
-		else {
-			i1 = 0;
-			j1 = 1;
-			k1 = 0;
-			i2 = 1;
-			j2 = 1;
-			k2 = 0;
-		} // Y X Z order
-	}
+	int x_ge_y = x0 >= y0;
+	int y_ge_z = y0 >= z0;
+	int x_ge_z = x0 >= z0;
+
+	// Compute simplex offsets - all values will be 0 or 1
+	i1 = x_ge_y & x_ge_z;
+	j1 = y_ge_z & (!x_ge_y);
+	k1 = (!x_ge_z) & (!y_ge_z);
+
+	i2 = x_ge_y | x_ge_z;
+	j2 = (!x_ge_y) | y_ge_z;
+	k2 = !(x_ge_z & y_ge_z);
 
 	// A step of (1,0,0) in (i,j,k) means a step of (1-c,-c,-c) in (x,y,z),
 	// a step of (0,1,0) in (i,j,k) means a step of (-c,1-c,-c) in (x,y,z), and
@@ -208,37 +169,30 @@ double noise(const vector3d &p)
 	const int gi3 = mod12[perm[ii + 1 + perm[jj + 1 + perm[kk + 1]]]];
 
 	// Noise contributions from the four corners
-	double n0, n1, n2, n3;
+	double n0 = 0.0, n1 = 0.0, n2 = 0.0, n3 = 0.0;
 
 	// Calculate the contribution from the four corners
 	double t0 = 0.6 - x0 * x0 - y0 * y0 - z0 * z0;
-	if (t0 < 0)
-		n0 = 0.0;
-	else {
+	double t1 = 0.6 - x1 * x1 - y1 * y1 - z1 * z1;
+	double t2 = 0.6 - x2 * x2 - y2 * y2 - z2 * z2;
+	double t3 = 0.6 - x3 * x3 - y3 * y3 - z3 * z3;
+
+	if (t0 > 0.0) {
 		t0 *= t0;
 		n0 = t0 * t0 * dot(grad3[gi0], x0, y0, z0);
 	}
 
-	double t1 = 0.6 - x1 * x1 - y1 * y1 - z1 * z1;
-	if (t1 < 0)
-		n1 = 0.0;
-	else {
+	if (t1 > 0.0) {
 		t1 *= t1;
 		n1 = t1 * t1 * dot(grad3[gi1], x1, y1, z1);
 	}
 
-	double t2 = 0.6 - x2 * x2 - y2 * y2 - z2 * z2;
-	if (t2 < 0)
-		n2 = 0.0;
-	else {
+	if (t2 > 0.0) {
 		t2 *= t2;
 		n2 = t2 * t2 * dot(grad3[gi2], x2, y2, z2);
 	}
 
-	double t3 = 0.6 - x3 * x3 - y3 * y3 - z3 * z3;
-	if (t3 < 0)
-		n3 = 0.0;
-	else {
+	if (t3 > 0.0) {
 		t3 *= t3;
 		n3 = t3 * t3 * dot(grad3[gi3], x3, y3, z3);
 	}