diff --git a/libraries/entities-renderer/CMakeLists.txt b/libraries/entities-renderer/CMakeLists.txt
index bb90c04c95..0063f4a701 100644
--- a/libraries/entities-renderer/CMakeLists.txt
+++ b/libraries/entities-renderer/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET_NAME entities-renderer)
-AUTOSCRIBE_SHADER_LIB(gpu model render render-utils)
+AUTOSCRIBE_SHADER_LIB(gpu model procedural render render-utils)
 setup_hifi_library(Widgets Network Script)
 link_hifi_libraries(shared gpu procedural model model-networking script-engine render render-utils)
 
diff --git a/libraries/entities-renderer/src/RenderableProceduralItemShader.h b/libraries/entities-renderer/src/RenderableProceduralItemShader.h
deleted file mode 100644
index 4762f619bf..0000000000
--- a/libraries/entities-renderer/src/RenderableProceduralItemShader.h
+++ /dev/null
@@ -1,380 +0,0 @@
-//
-//  Created by Bradley Austin Davis on 2015/09/05
-//  Copyright 2013-2015 High Fidelity, Inc.
-//
-//  Distributed under the Apache License, Version 2.0.
-//  See the accompanying file LICENSE or http://www.apache.org/licenses/LICENSE-2.0.html
-//
-
-// Shader includes portions of webgl-noise:
-// Description : Array and textureless GLSL 2D/3D/4D simplex
-//               noise functions.
-//      Author : Ian McEwan, Ashima Arts.
-//  Maintainer : ijm
-//     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
-//
-
-
-const QString SHADER_COMMON = R"SHADER(
-layout(location = 0) out vec4 _fragColor0;
-layout(location = 1) out vec4 _fragColor1;
-layout(location = 2) out vec4 _fragColor2;
-
-// the alpha threshold
-uniform float alphaThreshold;
-
-vec2 signNotZero(vec2 v) {
-    return vec2((v.x >= 0.0) ? +1.0 : -1.0, (v.y >= 0.0) ? +1.0 : -1.0);
-}
-
-vec2 float32x3_to_oct(in vec3 v) {
-    vec2 p = v.xy * (1.0 / (abs(v.x) + abs(v.y) + abs(v.z)));
-    return ((v.z <= 0.0) ? ((1.0 - abs(p.yx)) * signNotZero(p)) : p);
-}
-
-
-vec3 oct_to_float32x3(in vec2 e) {
-    vec3 v = vec3(e.xy, 1.0 - abs(e.x) - abs(e.y));
-    if (v.z < 0) {
-        v.xy = (1.0 - abs(v.yx)) * signNotZero(v.xy);
-    }
-    return normalize(v);
-}
-
-vec3 snorm12x2_to_unorm8x3(vec2 f) {
-    vec2 u = vec2(round(clamp(f, -1.0, 1.0) * 2047.0 + 2047.0));
-    float t = floor(u.y / 256.0);
-
-    return floor(vec3(
-        u.x / 16.0,
-        fract(u.x / 16.0) * 256.0 + t,
-        u.y - t * 256.0
-        )) / 255.0;
-}
-
-vec2 unorm8x3_to_snorm12x2(vec3 u) {
-    u *= 255.0;
-    u.y *= (1.0 / 16.0);
-    vec2 s = vec2(  u.x * 16.0 + floor(u.y),
-                    fract(u.y) * (16.0 * 256.0) + u.z);
-    return clamp(s * (1.0 / 2047.0) - 1.0, vec2(-1.0), vec2(1.0));
-}
-
-float mod289(float x) {
-    return x - floor(x * (1.0 / 289.0)) * 289.0; 
-}
-
-vec2 mod289(vec2 x) {
-    return x - floor(x * (1.0 / 289.0)) * 289.0;
-}
-
-vec3 mod289(vec3 x) {
-    return x - floor(x * (1.0 / 289.0)) * 289.0;
-}
-
-vec4 mod289(vec4 x) {
-    return x - floor(x * (1.0 / 289.0)) * 289.0;
-}
-
-float permute(float x) {
-    return mod289(((x*34.0)+1.0)*x);
-}
-
-vec3 permute(vec3 x) {
-    return mod289(((x*34.0)+1.0)*x);
-}
-
-vec4 permute(vec4 x) {
-    return mod289(((x*34.0)+1.0)*x);
-}
-
-float taylorInvSqrt(float r) {
-    return 1.79284291400159 - 0.85373472095314 * r;
-}
-
-vec4 taylorInvSqrt(vec4 r) {
-    return 1.79284291400159 - 0.85373472095314 * r;
-}
-
-vec4 grad4(float j, vec4 ip) {
-    const vec4 ones = vec4(1.0, 1.0, 1.0, -1.0);
-    vec4 p, s;
-
-    p.xyz = floor(fract(vec3(j) * ip.xyz) * 7.0) * ip.z - 1.0;
-    p.w = 1.5 - dot(abs(p.xyz), ones.xyz);
-    s = vec4(lessThan(p, vec4(0.0)));
-    p.xyz = p.xyz + (s.xyz * 2.0 - 1.0) * s.www;
-
-    return p;
-}
-
-// (sqrt(5) - 1)/4 = F4, used once below
-#define F4 0.309016994374947451
-
-float snoise(vec4 v) {
-    const vec4 C = vec4(0.138196601125011,  // (5 - sqrt(5))/20  G4
-            0.276393202250021,  // 2 * G4
-            0.414589803375032,  // 3 * G4
-            -0.447213595499958); // -1 + 4 * G4
-
-    // First corner
-    vec4 i = floor(v + dot(v, vec4(F4)));
-    vec4 x0 = v - i + dot(i, C.xxxx);
-
-    // Other corners
-
-    // Rank sorting originally contributed by Bill Licea-Kane, AMD (formerly ATI)
-    vec4 i0;
-    vec3 isX = step(x0.yzw, x0.xxx);
-    vec3 isYZ = step(x0.zww, x0.yyz);
-    i0.x = isX.x + isX.y + isX.z;
-    i0.yzw = 1.0 - isX;
-    i0.y += isYZ.x + isYZ.y;
-    i0.zw += 1.0 - isYZ.xy;
-    i0.z += isYZ.z;
-    i0.w += 1.0 - isYZ.z;
-
-    // i0 now contains the unique values 0,1,2,3 in each channel
-    vec4 i3 = clamp(i0, 0.0, 1.0);
-    vec4 i2 = clamp(i0 - 1.0, 0.0, 1.0);
-    vec4 i1 = clamp(i0 - 2.0, 0.0, 1.0);
-
-    vec4 x1 = x0 - i1 + C.xxxx;
-    vec4 x2 = x0 - i2 + C.yyyy;
-    vec4 x3 = x0 - i3 + C.zzzz;
-    vec4 x4 = x0 + C.wwww;
-
-    // Permutations
-    i = mod289(i);
-    float j0 = permute(permute(permute(permute(i.w) + i.z) + i.y) + i.x);
-    vec4 j1 = permute(
-            permute(
-                    permute(
-                            permute(i.w + vec4(i1.w, i2.w, i3.w, 1.0)) + i.z
-                                    + vec4(i1.z, i2.z, i3.z, 1.0)) + i.y
-                            + vec4(i1.y, i2.y, i3.y, 1.0)) + i.x
-                    + vec4(i1.x, i2.x, i3.x, 1.0));
-
-    // Gradients: 7x7x6 points over a cube, mapped onto a 4-cross polytope
-    // 7*7*6 = 294, which is close to the ring size 17*17 = 289.
-    vec4 ip = vec4(1.0 / 294.0, 1.0 / 49.0, 1.0 / 7.0, 0.0);
-
-    vec4 p0 = grad4(j0, ip);
-    vec4 p1 = grad4(j1.x, ip);
-    vec4 p2 = grad4(j1.y, ip);
-    vec4 p3 = grad4(j1.z, ip);
-    vec4 p4 = grad4(j1.w, ip);
-
-    // Normalise gradients
-    vec4 norm = taylorInvSqrt(
-            vec4(dot(p0, p0), dot(p1, p1), dot(p2, p2), dot(p3, p3)));
-    p0 *= norm.x;
-    p1 *= norm.y;
-    p2 *= norm.z;
-    p3 *= norm.w;
-    p4 *= taylorInvSqrt(dot(p4, p4));
-
-    // Mix contributions from the five corners
-    vec3 m0 = max(0.6 - vec3(dot(x0, x0), dot(x1, x1), dot(x2, x2)), 0.0);
-    vec2 m1 = max(0.6 - vec2(dot(x3, x3), dot(x4, x4)), 0.0);
-    m0 = m0 * m0;
-    m1 = m1 * m1;
-    return 49.0
-            * (dot(m0 * m0, vec3(dot(p0, x0), dot(p1, x1), dot(p2, x2)))
-                    + dot(m1 * m1, vec2(dot(p3, x3), dot(p4, x4))));
-
-}
-
-float snoise(vec3 v) {
-    const vec2 C = vec2(1.0 / 6.0, 1.0 / 3.0);
-    const vec4 D = vec4(0.0, 0.5, 1.0, 2.0);
-
-    // First corner
-    vec3 i = floor(v + dot(v, C.yyy));
-    vec3 x0 = v - i + dot(i, C.xxx);
-
-    // Other corners
-    vec3 g = step(x0.yzx, x0.xyz);
-    vec3 l = 1.0 - g;
-    vec3 i1 = min(g.xyz, l.zxy);
-    vec3 i2 = max(g.xyz, l.zxy);
-
-    vec3 x1 = x0 - i1 + C.xxx;
-    vec3 x2 = x0 - i2 + C.yyy; // 2.0*C.x = 1/3 = C.y
-    vec3 x3 = x0 - D.yyy;      // -1.0+3.0*C.x = -0.5 = -D.y
-
-    // Permutations
-    i = mod289(i);
-    vec4 p = permute(
-            permute(
-                    permute(i.z + vec4(0.0, i1.z, i2.z, 1.0)) + i.y
-                            + vec4(0.0, i1.y, i2.y, 1.0)) + i.x
-                    + vec4(0.0, i1.x, i2.x, 1.0));
-
-    // Gradients: 7x7 points over a square, mapped onto an octahedron.
-    // The ring size 17*17 = 289 is close to a multiple of 49 (49*6 = 294)
-    float n_ = 0.142857142857; // 1.0/7.0
-    vec3 ns = n_ * D.wyz - D.xzx;
-
-    vec4 j = p - 49.0 * floor(p * ns.z * ns.z);  //  mod(p,7*7)
-
-    vec4 x_ = floor(j * ns.z);
-    vec4 y_ = floor(j - 7.0 * x_);    // mod(j,N)
-
-    vec4 x = x_ * ns.x + ns.yyyy;
-    vec4 y = y_ * ns.x + ns.yyyy;
-    vec4 h = 1.0 - abs(x) - abs(y);
-
-    vec4 b0 = vec4(x.xy, y.xy);
-    vec4 b1 = vec4(x.zw, y.zw);
-
-    //vec4 s0 = vec4(lessThan(b0,0.0))*2.0 - 1.0;
-    //vec4 s1 = vec4(lessThan(b1,0.0))*2.0 - 1.0;
-    vec4 s0 = floor(b0) * 2.0 + 1.0;
-    vec4 s1 = floor(b1) * 2.0 + 1.0;
-    vec4 sh = -step(h, vec4(0.0));
-
-    vec4 a0 = b0.xzyw + s0.xzyw * sh.xxyy;
-    vec4 a1 = b1.xzyw + s1.xzyw * sh.zzww;
-
-    vec3 p0 = vec3(a0.xy, h.x);
-    vec3 p1 = vec3(a0.zw, h.y);
-    vec3 p2 = vec3(a1.xy, h.z);
-    vec3 p3 = vec3(a1.zw, h.w);
-
-    //Normalise gradients
-    vec4 norm = taylorInvSqrt(
-            vec4(dot(p0, p0), dot(p1, p1), dot(p2, p2), dot(p3, p3)));
-    p0 *= norm.x;
-    p1 *= norm.y;
-    p2 *= norm.z;
-    p3 *= norm.w;
-
-    // Mix final noise value
-    vec4 m = max(0.6 - vec4(dot(x0, x0), dot(x1, x1), dot(x2, x2), dot(x3, x3)),
-            0.0);
-    m = m * m;
-    return 42.0
-            * dot(m * m, vec4(dot(p0, x0), dot(p1, x1), dot(p2, x2), dot(p3, x3)));
-}
-
-float snoise(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);
-
-    // Other corners
-    vec2 i1;
-    i1 = (x0.x > x0.y) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);
-    vec4 x12 = x0.xyxy + C.xxzz;
-    x12.xy -= i1;
-
-    // Permutations
-    i = mod289(i); // Avoid truncation effects in permutation
-    vec3 p = permute(
-            permute(i.y + vec3(0.0, i1.y, 1.0)) + i.x + vec3(0.0, i1.x, 1.0));
-
-    vec3 m = max(0.5 - vec3(dot(x0, x0), dot(x12.xy, x12.xy), dot(x12.zw, x12.zw)),
-            0.0);
-    m = m * m;
-    m = m * m;
-
-    // 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 * fract(p * C.www) - 1.0;
-    vec3 h = abs(x) - 0.5;
-    vec3 ox = floor(x + 0.5);
-    vec3 a0 = x - ox;
-
-    // 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
-    vec3 g;
-    g.x = a0.x * x0.x + h.x * x0.y;
-    g.yz = a0.yz * x12.xz + h.yz * x12.yw;
-    return 130.0 * dot(m, g);
-}
-
-// the interpolated normal
-in vec3 _normal;
-in vec3 _color;
-in vec2 _texCoord0;
-in vec4 _position;
-
-// TODO add more uniforms
-uniform float iGlobalTime;           // shader playback time (in seconds)
-uniform vec3 iWorldScale;            // the dimensions of the object being rendered
-
-// TODO add support for textures
-// TODO document available inputs other than the uniforms
-// TODO provide world scale in addition to the untransformed position
-
-const vec3 DEFAULT_SPECULAR = vec3(0.1);
-const float DEFAULT_SHININESS = 10;
-
-)SHADER";
-
-// V1 shaders, only support emissive
-// vec4 getProceduralColor()
-const QString SHADER_TEMPLATE_V1 = SHADER_COMMON + R"SCRIBE(
-
-#line 1001
-%1
-#line 317
-
-void main(void) {
-    vec4 emissive = getProceduralColor();
-
-    float alpha = emissive.a;
-    if (alpha != 1.0) {
-        discard;
-    }
-
-    vec4 diffuse = vec4(_color.rgb, alpha);
-    vec4 normal = vec4(packNormal(normalize(_normal)), 0.5);
-
-    _fragColor0 = diffuse;
-    _fragColor1 = normal;
-    _fragColor2 = vec4(emissive.rgb, DEFAULT_SHININESS / 128.0);
-}
-
-)SCRIBE";
-
-// void getProceduralDiffuseAndEmissive(out vec4 diffuse, out vec4 emissive)
-const QString SHADER_TEMPLATE_V2 = SHADER_COMMON + R"SCRIBE(
-// FIXME should we be doing the swizzle here?
-vec3 iResolution = iWorldScale.xzy;
-
-// FIXME Mouse X,Y coordinates, and Z,W are for the click position if clicked (not supported in High Fidelity at the moment)
-vec4 iMouse = vec4(0);
-
-// FIXME We set the seconds (iDate.w) of iDate to iGlobalTime, which contains the current date in seconds
-vec4 iDate = vec4(0, 0, 0, iGlobalTime);
-
-
-#line 1001
-%1
-#line 351
-
-void main(void) {
-    vec3 diffuse = _color.rgb;
-    vec3 specular = DEFAULT_SPECULAR;
-    float shininess = DEFAULT_SHININESS;
-    
-    float emissiveAmount = getProceduralColors(diffuse, specular, shininess);
-
-    _fragColor0 = vec4(diffuse.rgb, 1.0);
-    _fragColor1 = vec4(packNormal(normalize(_normal.xyz)), 1.0 - (emissiveAmount / 2.0));
-    _fragColor2 = vec4(specular, shininess / 128.0);
-}
-)SCRIBE";
diff --git a/libraries/entities-renderer/src/RenderableShapeEntityItem.cpp b/libraries/entities-renderer/src/RenderableShapeEntityItem.cpp
index c93ae252e3..ec07e10ccf 100644
--- a/libraries/entities-renderer/src/RenderableShapeEntityItem.cpp
+++ b/libraries/entities-renderer/src/RenderableShapeEntityItem.cpp
@@ -98,7 +98,7 @@ void RenderableShapeEntityItem::render(RenderArgs* args) {
     }
     batch.setModelTransform(modelTransform); // use a transform with scale, rotation, registration point and translation
     if (_procedural->ready()) {
-        _procedural->prepare(batch, getPosition(), getDimensions());
+        _procedural->prepare(batch, getPosition(), getDimensions(), getOrientation());
         auto outColor = _procedural->getColor(color);
         batch._glColor4f(outColor.r, outColor.g, outColor.b, outColor.a);
         DependencyManager::get<GeometryCache>()->renderShape(batch, MAPPING[_shape]);
diff --git a/libraries/gpu-gl/CMakeLists.txt b/libraries/gpu-gl/CMakeLists.txt
index dfac6dd516..398fdd04d6 100644
--- a/libraries/gpu-gl/CMakeLists.txt
+++ b/libraries/gpu-gl/CMakeLists.txt
@@ -1,5 +1,4 @@
 set(TARGET_NAME gpu-gl)
-AUTOSCRIBE_SHADER_LIB(gpu)
 setup_hifi_library()
 link_hifi_libraries(shared gl gpu)
 GroupSources("src")
diff --git a/libraries/gpu-gl/src/gpu/gl/GLBackend.cpp b/libraries/gpu-gl/src/gpu/gl/GLBackend.cpp
index ece1ee730c..e18b784018 100644
--- a/libraries/gpu-gl/src/gpu/gl/GLBackend.cpp
+++ b/libraries/gpu-gl/src/gpu/gl/GLBackend.cpp
@@ -114,6 +114,7 @@ GLBackend::CommandCall GLBackend::_commandCalls[Batch::NUM_COMMANDS] =
     (&::gpu::gl::GLBackend::do_glUniform3fv),
     (&::gpu::gl::GLBackend::do_glUniform4fv),
     (&::gpu::gl::GLBackend::do_glUniform4iv),
+    (&::gpu::gl::GLBackend::do_glUniformMatrix3fv),
     (&::gpu::gl::GLBackend::do_glUniformMatrix4fv),
 
     (&::gpu::gl::GLBackend::do_glColor4f),
@@ -515,6 +516,22 @@ void GLBackend::do_glUniform4iv(Batch& batch, size_t paramOffset) {
     (void)CHECK_GL_ERROR();
 }
 
+void GLBackend::do_glUniformMatrix3fv(Batch& batch, size_t paramOffset) {
+    if (_pipeline._program == 0) {
+        // We should call updatePipeline() to bind the program but we are not doing that
+        // because these uniform setters are deprecated and we don;t want to create side effect
+        return;
+    }
+    updatePipeline();
+
+    glUniformMatrix3fv(
+        GET_UNIFORM_LOCATION(batch._params[paramOffset + 3]._int),
+        batch._params[paramOffset + 2]._uint,
+        batch._params[paramOffset + 1]._uint,
+        (const GLfloat*)batch.editData(batch._params[paramOffset + 0]._uint));
+    (void)CHECK_GL_ERROR();
+}
+
 void GLBackend::do_glUniformMatrix4fv(Batch& batch, size_t paramOffset) {
     if (_pipeline._program == 0) {
         // We should call updatePipeline() to bind the program but we are not doing that
diff --git a/libraries/gpu-gl/src/gpu/gl/GLBackend.h b/libraries/gpu-gl/src/gpu/gl/GLBackend.h
index 610672f44f..5255a6cb25 100644
--- a/libraries/gpu-gl/src/gpu/gl/GLBackend.h
+++ b/libraries/gpu-gl/src/gpu/gl/GLBackend.h
@@ -136,6 +136,7 @@ public:
     virtual void do_glUniform3fv(Batch& batch, size_t paramOffset) final;
     virtual void do_glUniform4fv(Batch& batch, size_t paramOffset) final;
     virtual void do_glUniform4iv(Batch& batch, size_t paramOffset) final;
+    virtual void do_glUniformMatrix3fv(Batch& batch, size_t paramOffset) final;
     virtual void do_glUniformMatrix4fv(Batch& batch, size_t paramOffset) final;
 
     virtual void do_glColor4f(Batch& batch, size_t paramOffset) final;
diff --git a/libraries/gpu/src/gpu/Batch.cpp b/libraries/gpu/src/gpu/Batch.cpp
index 9126f11acf..6dc1d63ca8 100644
--- a/libraries/gpu/src/gpu/Batch.cpp
+++ b/libraries/gpu/src/gpu/Batch.cpp
@@ -567,6 +567,16 @@ void Batch::_glUniform4iv(int32 location, int count, const int32* value) {
     _params.push_back(location);
 }
 
+void Batch::_glUniformMatrix3fv(int32 location, int count, uint8 transpose, const float* value) {
+    ADD_COMMAND(glUniformMatrix3fv);
+
+    const int MATRIX3_SIZE = 9 * sizeof(float);
+    _params.push_back(cacheData(count * MATRIX3_SIZE, value));
+    _params.push_back(transpose);
+    _params.push_back(count);
+    _params.push_back(location);
+}
+
 void Batch::_glUniformMatrix4fv(int32 location, int count, uint8 transpose, const float* value) {
     ADD_COMMAND(glUniformMatrix4fv);
 
diff --git a/libraries/gpu/src/gpu/Batch.h b/libraries/gpu/src/gpu/Batch.h
index a2ee57759f..4e51038368 100644
--- a/libraries/gpu/src/gpu/Batch.h
+++ b/libraries/gpu/src/gpu/Batch.h
@@ -14,6 +14,7 @@
 #include <vector>
 #include <mutex>
 #include <functional>
+#include <glm/gtc/type_ptr.hpp>
 
 #include <shared/NsightHelpers.h>
 
@@ -269,6 +270,7 @@ public:
     void _glUniform3fv(int location, int count, const float* value);
     void _glUniform4fv(int location, int count, const float* value);
     void _glUniform4iv(int location, int count, const int* value);
+    void _glUniformMatrix3fv(int location, int count, unsigned char transpose, const float* value);
     void _glUniformMatrix4fv(int location, int count, unsigned char transpose, const float* value);
 
     void _glUniform(int location, int v0) {
@@ -291,6 +293,10 @@ public:
         _glUniform4f(location, v.x, v.y, v.z, v.w);
     }
 
+    void _glUniform(int location, const glm::mat3& v) {
+        _glUniformMatrix3fv(location, 1, false, glm::value_ptr(v));
+    }
+
     void _glColor4f(float red, float green, float blue, float alpha);
 
     enum Command {
@@ -348,6 +354,7 @@ public:
         COMMAND_glUniform3fv,
         COMMAND_glUniform4fv,
         COMMAND_glUniform4iv,
+        COMMAND_glUniformMatrix3fv,
         COMMAND_glUniformMatrix4fv,
 
         COMMAND_glColor4f,
@@ -446,7 +453,7 @@ public:
     Params _params;
     Bytes _data;
 
-    // SSBO class... layout MUST match the layout in TransformCamera.slh
+    // SSBO class... layout MUST match the layout in Transform.slh
     class TransformObject {
     public:
         Mat4 _model;
diff --git a/libraries/gpu/src/gpu/Context.h b/libraries/gpu/src/gpu/Context.h
index cead2c623d..652338f911 100644
--- a/libraries/gpu/src/gpu/Context.h
+++ b/libraries/gpu/src/gpu/Context.h
@@ -95,7 +95,7 @@ public:
     virtual void syncCache() = 0;
     virtual void downloadFramebuffer(const FramebufferPointer& srcFramebuffer, const Vec4i& region, QImage& destImage) = 0;
 
-    // UBO class... layout MUST match the layout in TransformCamera.slh
+    // UBO class... layout MUST match the layout in Transform.slh
     class TransformCamera {
     public:
         mutable Mat4 _view;
diff --git a/libraries/gpu/src/gpu/Transform.slh b/libraries/gpu/src/gpu/Transform.slh
index 246167e186..20629c5f32 100644
--- a/libraries/gpu/src/gpu/Transform.slh
+++ b/libraries/gpu/src/gpu/Transform.slh
@@ -27,6 +27,10 @@ layout(std140) uniform transformCameraBuffer {
 TransformCamera getTransformCamera() {
     return _camera;
 }
+
+vec3 getEyeWorldPos() {
+    return _camera._viewInverse[3].xyz;
+}
 <@endfunc@>
 
 
diff --git a/libraries/procedural/src/procedural/Procedural.cpp b/libraries/procedural/src/procedural/Procedural.cpp
index 781b508bc7..a9a297a2e1 100644
--- a/libraries/procedural/src/procedural/Procedural.cpp
+++ b/libraries/procedural/src/procedural/Procedural.cpp
@@ -19,7 +19,7 @@
 #include <NumericalConstants.h>
 #include <GLMHelpers.h>
 
-#include "ProceduralShaders.h"
+#include "ProceduralCommon_frag.h"
 
 // Userdata parsing constants
 static const QString PROCEDURAL_USER_DATA_KEY = "ProceduralEntity";
@@ -39,6 +39,7 @@ static const std::string STANDARD_UNIFORM_NAMES[Procedural::NUM_STANDARD_UNIFORM
     "iFrameCount",
     "iWorldScale",
     "iWorldPosition",
+    "iWorldOrientation",
     "iChannelResolution"
 };
 
@@ -202,9 +203,10 @@ bool Procedural::ready() {
     return true;
 }
 
-void Procedural::prepare(gpu::Batch& batch, const glm::vec3& position, const glm::vec3& size) {
+void Procedural::prepare(gpu::Batch& batch, const glm::vec3& position, const glm::vec3& size, const glm::quat& orientation) {
     _entityDimensions = size;
     _entityPosition = position;
+    _entityOrientation = glm::mat3_cast(orientation);
     if (_shaderUrl.isLocalFile()) {
         auto lastModified = (quint64)QFileInfo(_shaderPath).lastModified().toMSecsSinceEpoch();
         if (lastModified > _shaderModified) {
@@ -227,7 +229,7 @@ void Procedural::prepare(gpu::Batch& batch, const glm::vec3& position, const glm
         std::string fragmentShaderSource = _fragmentSource;
         size_t replaceIndex = fragmentShaderSource.find(PROCEDURAL_COMMON_BLOCK);
         if (replaceIndex != std::string::npos) {
-            fragmentShaderSource.replace(replaceIndex, PROCEDURAL_COMMON_BLOCK.size(), SHADER_COMMON);
+            fragmentShaderSource.replace(replaceIndex, PROCEDURAL_COMMON_BLOCK.size(), ProceduralCommon_frag);
         }
 
         replaceIndex = fragmentShaderSource.find(PROCEDURAL_VERSION);
@@ -404,10 +406,10 @@ void Procedural::setupUniforms() {
         });
     }
 
-    if (gpu::Shader::INVALID_LOCATION != _standardUniformSlots[SCALE]) {
+    if (gpu::Shader::INVALID_LOCATION != _standardUniformSlots[ORIENTATION]) {
         // FIXME move into the 'set once' section, since this doesn't change over time
         _uniforms.push_back([=](gpu::Batch& batch) {
-            batch._glUniform(_standardUniformSlots[SCALE], _entityDimensions);
+            batch._glUniform(_standardUniformSlots[ORIENTATION], _entityOrientation);
         });
     }
 
diff --git a/libraries/procedural/src/procedural/Procedural.h b/libraries/procedural/src/procedural/Procedural.h
index f928d0e594..6991b47946 100644
--- a/libraries/procedural/src/procedural/Procedural.h
+++ b/libraries/procedural/src/procedural/Procedural.h
@@ -38,7 +38,7 @@ public:
     void parse(const QString& userDataJson);
 
     bool ready();
-    void prepare(gpu::Batch& batch, const glm::vec3& position, const glm::vec3& size);
+    void prepare(gpu::Batch& batch, const glm::vec3& position, const glm::vec3& size, const glm::quat& orientation);
     const gpu::ShaderPointer& getShader() const { return _shader; }
 
     glm::vec4 getColor(const glm::vec4& entityColor);
@@ -56,6 +56,7 @@ public:
         FRAME_COUNT,
         SCALE,
         POSITION,
+        ORIENTATION,
         CHANNEL_RESOLUTION,
         NUM_STANDARD_UNIFORMS
     };
@@ -93,6 +94,7 @@ protected:
     // Entity metadata
     glm::vec3 _entityDimensions;
     glm::vec3 _entityPosition;
+    glm::mat3 _entityOrientation;
 
 private:
     // This should only be called from the render thread, as it shares data with Procedural::prepare
diff --git a/libraries/procedural/src/procedural/ProceduralShaders.h b/libraries/procedural/src/procedural/ProceduralCommon.slf
similarity index 93%
rename from libraries/procedural/src/procedural/ProceduralShaders.h
rename to libraries/procedural/src/procedural/ProceduralCommon.slf
index eddf53cb09..128723265f 100644
--- a/libraries/procedural/src/procedural/ProceduralShaders.h
+++ b/libraries/procedural/src/procedural/ProceduralCommon.slf
@@ -1,3 +1,5 @@
+<@include gpu/Config.slh@>
+//  Generated on <$_SCRIBE_DATE$>
 //
 //  Created by Bradley Austin Davis on 2015/09/05
 //  Copyright 2013-2015 High Fidelity, Inc.
@@ -17,11 +19,11 @@
 //               https://github.com/ashima/webgl-noise
 //
 
-
-const std::string SHADER_COMMON = R"SHADER(
+<@include gpu/Transform.slh@>
+<$declareStandardCameraTransform()$>
 
 float mod289(float x) {
-    return x - floor(x * (1.0 / 289.0)) * 289.0; 
+    return x - floor(x * (1.0 / 289.0)) * 289.0;
 }
 
 vec2 mod289(vec2 x) {
@@ -262,11 +264,6 @@ float snoise(vec2 v) {
     return 130.0 * dot(m, g);
 }
 
-// shader playback time (in seconds)
-uniform float iGlobalTime;
-// the dimensions of the object being rendered
-uniform vec3 iWorldScale;            
-
 #define PROCEDURAL 1
 
 //PROCEDURAL_VERSION
@@ -286,15 +283,16 @@ const float iSampleRate = 1.0;
 const vec4 iChannelTime = vec4(0.0);
 
 
+uniform float iGlobalTime;                  // shader playback time (in seconds)
 uniform vec4 iDate;
 uniform int iFrameCount;
-uniform vec3 iWorldPosition;
+uniform vec3 iWorldPosition;                // the position of the object being rendered
+uniform vec3 iWorldScale;                   // the dimensions of the object being rendered
+uniform mat3 iWorldOrientation;             // the orientation of the object being rendered
 uniform vec3 iChannelResolution[4];
 uniform sampler2D iChannel0;
 uniform sampler2D iChannel1;
 uniform sampler2D iChannel2;
 uniform sampler2D iChannel3;
 
-#endif
-
-)SHADER";
+#endif
\ No newline at end of file
diff --git a/libraries/procedural/src/procedural/ProceduralSkybox.cpp b/libraries/procedural/src/procedural/ProceduralSkybox.cpp
index 1aa59c90d7..9e9a26d902 100644
--- a/libraries/procedural/src/procedural/ProceduralSkybox.cpp
+++ b/libraries/procedural/src/procedural/ProceduralSkybox.cpp
@@ -52,7 +52,7 @@ void ProceduralSkybox::render(gpu::Batch& batch, const ViewFrustum& viewFrustum,
     batch.setModelTransform(Transform()); // only for Mac
 
     auto& procedural = skybox._procedural;
-    procedural.prepare(batch, glm::vec3(0), glm::vec3(1));
+    procedural.prepare(batch, glm::vec3(0), glm::vec3(1), glm::quat());
     auto textureSlot = procedural.getShader()->getTextures().findLocation("cubeMap");
     auto bufferSlot = procedural.getShader()->getBuffers().findLocation("skyboxBuffer");
     skybox.prepare(batch, textureSlot, bufferSlot);
diff --git a/libraries/render-utils/CMakeLists.txt b/libraries/render-utils/CMakeLists.txt
index c4f28aeffd..2a7d33e33a 100644
--- a/libraries/render-utils/CMakeLists.txt
+++ b/libraries/render-utils/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET_NAME render-utils)
-AUTOSCRIBE_SHADER_LIB(gpu model render)
+AUTOSCRIBE_SHADER_LIB(gpu model render procedural)
 # pull in the resources.qrc file
 qt5_add_resources(QT_RESOURCES_FILE "${CMAKE_CURRENT_SOURCE_DIR}/res/fonts/fonts.qrc")
 setup_hifi_library(Widgets OpenGL Network Qml Quick Script)
diff --git a/libraries/render/CMakeLists.txt b/libraries/render/CMakeLists.txt
index 76fc8303ce..c5cfdf3668 100644
--- a/libraries/render/CMakeLists.txt
+++ b/libraries/render/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET_NAME render)
-AUTOSCRIBE_SHADER_LIB(gpu model)
+AUTOSCRIBE_SHADER_LIB(gpu model procedural)
 setup_hifi_library()
 link_hifi_libraries(shared gpu model)