From 77aabf61c52b0ff0ad43b9279626c396005cf107 Mon Sep 17 00:00:00 2001
From: veclav talica <veclavtalica@protonmal.com>
Date: Mon, 10 Jul 2023 18:23:11 +0500
Subject: [PATCH] hand optimized simplex page

---
 articles/2d-visibility/page.mmd       |   2 +-
 articles/hand-opt-simplex-2d/page.mmd | 116 ++++++++++++++++++++++++++
 2 files changed, 117 insertions(+), 1 deletion(-)
 create mode 100644 articles/hand-opt-simplex-2d/page.mmd

diff --git a/articles/2d-visibility/page.mmd b/articles/2d-visibility/page.mmd
index ace6222..7e43be9 100644
--- a/articles/2d-visibility/page.mmd
+++ b/articles/2d-visibility/page.mmd
@@ -8,7 +8,7 @@ CSS:    /style.css
 
 Based on [Redblobgames' visibility article and Haxe reference implementation](https://www.redblobgames.com/articles/visibility)
 
-Full usable code is [here](/articles/2d-visibility/Visiblity2D.gd.txt).
+Full usable code is [here](/articles/2d-visibility/Visibility2D.gd.txt).
 
 ### Explanation ###
 
diff --git a/articles/hand-opt-simplex-2d/page.mmd b/articles/hand-opt-simplex-2d/page.mmd
new file mode 100644
index 0000000..bc194db
--- /dev/null
+++ b/articles/hand-opt-simplex-2d/page.mmd
@@ -0,0 +1,116 @@
+Title:  Hand Optimized Simplex 2D
+Brief:  Results of messing around with moving and hoisting stuff around.
+Date:   1688995095
+Tags:   Programming, GLSL, OpenGL
+CSS:    /style.css
+
+![](/articles/hand-opt-simplex-2d/noise.png)
+
+Based on [webgl-noise repository](https://github.com/ashima/webgl-noise), which is based on [this paper](https://arxiv.org/pdf/1204.1461.pdf).
+
+Things tried:
+* Rearranging operations to reduce register pressure.
+* Calculating things as soon as possible.
+* Hand inlining.
+
+### Results ###
+For testing screen space *1024x1024* texture is generated, resulting in *1048576* fragment invocations,
+with 4 octave fractal brownian motion.
+
+Hardware: `Mobile Intel® GM45 Express Chipset`
+
+Driver: `DRI Mesa 21.2.6`
+
+Original:
+```
+Benchmark Iterations    Min(ns)    Max(ns)   Variance   Mean(ns)
+----------------------------------------------------------------
+full(0)          100  124848395  510494575 1473830605484805  129237053
+```
+
+Hand optimized:
+```
+Benchmark Iterations    Min(ns)    Max(ns)   Variance   Mean(ns)
+----------------------------------------------------------------
+full(0)          100  119354512  731397135 3705581696928414  125714847
+```
+
+Mean difference is `3ms 522µs 206ns`, min difference is `5ms 493µs 883ns`.
+
+This suggests that given driver is suboptimal in its optimizing capabilities,
+and I imagine there might be GLSL compilers a lot worse than this.
+
+Some intermediate shader representation comes to mind as a mean for
+automatic GLSL source level, profile guided and other optimizations;
+as well as polyfilling to different extensions, profiles and APIs. But welp.
+
+### Source ###
+
+```glsl
+#version 120
+
+//      Author : Ian McEwan, Ashima Arts.
+//  Maintainer : stegu
+//     Lastmod : 20110822 (ijm)
+//     License : Copyright (C) 2011 Ashima Arts. All rights reserved.
+//               Distributed under the MIT License. See LICENSE file.
+//               https://github.com/ashima/webgl-noise
+//               https://github.com/stegu/webgl-noise
+// 
+
+#define MOD289(p_x) ((p_x) - floor((p_x) * (1.0 / 289.0)) * 289.0)
+#define PERMUTE(p_result, p_x) { vec3 _temp = (((p_x) * 34.0) + 10.0) * (p_x); p_result = MOD289(_temp); }
+
+float simplex_noise_2d(in vec2 v) {
+  const vec4 C = vec4(0.211324865405187,  // (3.0-sqrt(3.0))/6.0
+                      0.366025403784439,  // 0.5*(sqrt(3.0)-1.0)
+                     -0.577350269189626,  // -1.0 + 2.0 * C.x
+                      0.024390243902439); // 1.0 / 41.0
+  // First corner
+  vec2 i  = floor(v + dot(v, C.yy));
+  vec2 x0 = v -   i + dot(i, C.xx);
+  i = MOD289(i); // Avoid truncation effects in permutation
+
+  // i1.x = step( x0.y, x0.x ); // x0.x > x0.y ? 1.0 : 0.0
+  // i1.y = 1.0 - i1.x;
+  vec2 i1 = (x0.x > x0.y) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);
+
+  // Other corners
+  // x0 = x0 - 0.0 + 0.0 * C.xx ;
+  // x1 = x0 - i1 + 1.0 * C.xx ;
+  // x2 = x0 - 1.0 + 2.0 * C.xx ;
+  vec4 x12 = x0.xyxy + C.xxzz - vec4(i1.xy, 0.0, 0.0);
+
+  // Permutations
+  vec3 pp;
+  vec3 p = i.y + vec3(0.0, i1.y, 1.0);
+  PERMUTE(pp, p);
+  pp += i.x + vec3(0.0, i1.x, 1.0);
+  PERMUTE(p, pp);
+  p = fract(p * C.www);
+
+  vec3 m = max(0.5 - vec3(dot(x0, x0), dot(x12.xy, x12.xy), dot(x12.zw, x12.zw)), 0.0);
+
+  // Gradients: 41 points uniformly over a line, mapped onto a diamond.
+  // The ring size 17*17 = 289 is close to a multiple of 41 (41*7 = 287)
+  vec3 x = 2.0 * p - 1.0;
+  vec3 a0 = x - floor(x + 0.5);
+  vec3 h = abs(x) - 0.5;
+
+  m = m * m;
+  m = m * m;
+
+  // Normalise gradients implicitly by scaling m
+  // Approximation of: m *= inversesqrt( a0*a0 + h*h );
+  m *= 1.79284291400159 - 0.85373472095314 * (a0 * a0 + h * h);
+
+  // Compute final noise value at P
+  return 130.0 * dot(m, vec3(a0.x * x0.x + h.x * x0.y, a0.yz * x12.xz + h.yz * x12.yw));
+}
+
+```
+
+### Possibilities
+[NVidia's TEGRA guide](https://docs.nvidia.com/drive/drive_os_5.1.6.1L/nvvib_docs/DRIVE_OS_Linux_SDK_Development_Guide/baggage/tegra_gles2_performance.pdf) states that uniform access is often better than constants.
+On our hardware it only degrades performance, but there's possibility of other chipsets having similar to TEGRA's preferences.
+`C` constant is legible for this.