Project 6: Mohamed Soudy

src/Renderer.cpp

@@ -198,6 +198,22 @@ void Renderer::CreateComputeDescriptorSetLayout() {
     // TODO: Create the descriptor set layout for the compute pipeline
     // Remember this is like a class definition stating why types of information
     // will be stored at each binding
+
+  VkDescriptorSetLayoutBinding bindings[] = {
+    { 0, VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 1, VK_SHADER_STAGE_COMPUTE_BIT, NULL },
+    { 1, VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 1, VK_SHADER_STAGE_COMPUTE_BIT, NULL },
+    { 2, VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 1, VK_SHADER_STAGE_COMPUTE_BIT, NULL },
+  };
+
+  // Create the descriptor set layout
+  VkDescriptorSetLayoutCreateInfo layoutInfo = {};
+  layoutInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO;
+  layoutInfo.bindingCount = static_cast<uint32_t>(3);
+  layoutInfo.pBindings = bindings;
+
+  if (vkCreateDescriptorSetLayout(logicalDevice, &layoutInfo, nullptr, &computeDescriptorSetLayout) != VK_SUCCESS) {
+    throw std::runtime_error("Failed to create descriptor set layout");
+  }
 }
 
 void Renderer::CreateDescriptorPool() {
@@ -215,6 +231,7 @@ void Renderer::CreateDescriptorPool() {
         // Time (compute)
         { VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER , 1 },
 
+        { VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 3 * static_cast<uint32_t>(scene->GetBlades().size()) },
         // TODO: Add any additional types and counts of descriptors you will need to allocate
     };
 
@@ -320,6 +337,43 @@ void Renderer::CreateModelDescriptorSets() {
 void Renderer::CreateGrassDescriptorSets() {
     // TODO: Create Descriptor sets for the grass.
     // This should involve creating descriptor sets which point to the model matrix of each group of grass blades
+  grassDescriptorSets.resize(scene->GetBlades().size());
+
+  // Describe the desciptor set
+  VkDescriptorSetLayout layouts[] = { modelDescriptorSetLayout };
+  VkDescriptorSetAllocateInfo allocInfo = {};
+  allocInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO;
+  allocInfo.descriptorPool = descriptorPool;
+  allocInfo.descriptorSetCount = static_cast<uint32_t>(grassDescriptorSets.size());
+  allocInfo.pSetLayouts = layouts;
+
+  // Allocate descriptor sets
+  if (vkAllocateDescriptorSets(logicalDevice, &allocInfo, grassDescriptorSets.data()) != VK_SUCCESS) {
+    throw std::runtime_error("Failed to allocate descriptor set");
+  }
+
+  std::vector<VkWriteDescriptorSet> descriptorWrites(grassDescriptorSets.size());
+
+  for (uint32_t i = 0; i < scene->GetBlades().size(); ++i) {
+    VkDescriptorBufferInfo modelBufferInfo = {};
+    modelBufferInfo.buffer = scene->GetBlades()[i]->GetModelBuffer();
+    modelBufferInfo.offset = 0;
+    modelBufferInfo.range = sizeof(ModelBufferObject);
+
+    descriptorWrites[i + 0].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+    descriptorWrites[i + 0].dstSet = grassDescriptorSets[i];
+    descriptorWrites[i + 0].dstBinding = 0;
+    descriptorWrites[i + 0].dstArrayElement = 0;
+    descriptorWrites[i + 0].descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
+    descriptorWrites[i + 0].descriptorCount = 1;
+    descriptorWrites[i + 0].pBufferInfo = &modelBufferInfo;
+    descriptorWrites[i + 0].pImageInfo = nullptr;
+    descriptorWrites[i + 0].pTexelBufferView = nullptr;
+  }
+
+  // Update descriptor sets
+  vkUpdateDescriptorSets(logicalDevice, static_cast<uint32_t>(descriptorWrites.size()), descriptorWrites.data(), 0, nullptr);
+
 }
 
 void Renderer::CreateTimeDescriptorSet() {
@@ -360,6 +414,72 @@ void Renderer::CreateTimeDescriptorSet() {
 void Renderer::CreateComputeDescriptorSets() {
     // TODO: Create Descriptor sets for the compute pipeline
     // The descriptors should point to Storage buffers which will hold the grass blades, the culled grass blades, and the output number of grass blades 
+  computeDescriptorSets.resize(scene->GetBlades().size());
+
+  // Describe the desciptor set
+  VkDescriptorSetLayout layouts[] = { computeDescriptorSetLayout };
+  VkDescriptorSetAllocateInfo allocInfo = {};
+  allocInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO;
+  allocInfo.descriptorPool = descriptorPool;
+  allocInfo.descriptorSetCount = static_cast<uint32_t>(computeDescriptorSets.size());
+  allocInfo.pSetLayouts = layouts;
+
+  // Allocate descriptor sets
+  if (vkAllocateDescriptorSets(logicalDevice, &allocInfo, computeDescriptorSets.data()) != VK_SUCCESS) {
+    throw std::runtime_error("Failed to allocate descriptor set");
+  }
+
+  std::vector<VkWriteDescriptorSet> descriptorWrites(3 * computeDescriptorSets.size());
+
+  for (uint32_t i = 0; i < scene->GetBlades().size(); ++i) {
+    VkDescriptorBufferInfo bladeBufferInfo = {};
+    bladeBufferInfo.buffer = scene->GetBlades()[i]->GetBladesBuffer();
+    bladeBufferInfo.offset = 0;
+    bladeBufferInfo.range = NUM_BLADES * sizeof(Blade);
+
+    VkDescriptorBufferInfo culledBladeBufferInfo = {};
+    culledBladeBufferInfo.buffer = scene->GetBlades()[i]->GetCulledBladesBuffer();
+    culledBladeBufferInfo.offset = 0;
+    culledBladeBufferInfo.range = NUM_BLADES * sizeof(Blade);
+
+    VkDescriptorBufferInfo numBladeBufferInfo = {};
+    numBladeBufferInfo.buffer = scene->GetBlades()[i]->GetNumBladesBuffer();
+    numBladeBufferInfo.offset = 0;
+    numBladeBufferInfo.range = sizeof(BladeDrawIndirect);
+
+    descriptorWrites[3 * i + 0].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+    descriptorWrites[3 * i + 0].dstSet = computeDescriptorSets[i];
+    descriptorWrites[3 * i + 0].dstBinding = 0;
+    descriptorWrites[3 * i + 0].dstArrayElement = 0;
+    descriptorWrites[3 * i + 0].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    descriptorWrites[3 * i + 0].descriptorCount = 1;
+    descriptorWrites[3 * i + 0].pBufferInfo = &bladeBufferInfo;
+    descriptorWrites[3 * i + 0].pImageInfo = nullptr;
+    descriptorWrites[3 * i + 0].pTexelBufferView = nullptr;
+
+    descriptorWrites[3 * i + 1].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+    descriptorWrites[3 * i + 1].dstSet = computeDescriptorSets[i];
+    descriptorWrites[3 * i + 1].dstBinding = 1;
+    descriptorWrites[3 * i + 1].dstArrayElement = 0;
+    descriptorWrites[3 * i + 1].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    descriptorWrites[3 * i + 1].descriptorCount = 1;
+    descriptorWrites[3 * i + 1].pBufferInfo = &culledBladeBufferInfo;
+    descriptorWrites[3 * i + 1].pImageInfo = nullptr;
+    descriptorWrites[3 * i + 1].pTexelBufferView = nullptr;
+
+    descriptorWrites[3 * i + 2].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+    descriptorWrites[3 * i + 2].dstSet = computeDescriptorSets[i];
+    descriptorWrites[3 * i + 2].dstBinding = 2;
+    descriptorWrites[3 * i + 2].dstArrayElement = 0;
+    descriptorWrites[3 * i + 2].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    descriptorWrites[3 * i + 2].descriptorCount = 1;
+    descriptorWrites[3 * i + 2].pBufferInfo = &numBladeBufferInfo;
+    descriptorWrites[3 * i + 2].pImageInfo = nullptr;
+    descriptorWrites[3 * i + 2].pTexelBufferView = nullptr;
+  }
+
+  // Update descriptor sets
+  vkUpdateDescriptorSets(logicalDevice, static_cast<uint32_t>(descriptorWrites.size()), descriptorWrites.data(), 0, nullptr);
 }
 
 void Renderer::CreateGraphicsPipeline() {
@@ -717,7 +837,7 @@ void Renderer::CreateComputePipeline() {
     computeShaderStageInfo.pName = "main";
 
     // TODO: Add the compute dsecriptor set layout you create to this list
-    std::vector<VkDescriptorSetLayout> descriptorSetLayouts = { cameraDescriptorSetLayout, timeDescriptorSetLayout };
+    std::vector<VkDescriptorSetLayout> descriptorSetLayouts = { cameraDescriptorSetLayout, timeDescriptorSetLayout, computeDescriptorSetLayout };
 
     // Create pipeline layout
     VkPipelineLayoutCreateInfo pipelineLayoutInfo = {};
@@ -884,6 +1004,12 @@ void Renderer::RecordComputeCommandBuffer() {
     vkCmdBindDescriptorSets(computeCommandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, computePipelineLayout, 1, 1, &timeDescriptorSet, 0, nullptr);
 
     // TODO: For each group of blades bind its descriptor set and dispatch
+    for (int i = 0; i < computeDescriptorSets.size(); i++) {
+      vkCmdBindDescriptorSets(computeCommandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, computePipelineLayout, 2, 1, &computeDescriptorSets[i], 0, nullptr);
+      vkCmdDispatch(computeCommandBuffer, (NUM_BLADES + WORKGROUP_SIZE - 1) / WORKGROUP_SIZE, 1, 1);
+    }
+
+
 
     // ~ End recording ~
     if (vkEndCommandBuffer(computeCommandBuffer) != VK_SUCCESS) {
@@ -976,13 +1102,14 @@ void Renderer::RecordCommandBuffers() {
             VkBuffer vertexBuffers[] = { scene->GetBlades()[j]->GetCulledBladesBuffer() };
             VkDeviceSize offsets[] = { 0 };
             // TODO: Uncomment this when the buffers are populated
-            // vkCmdBindVertexBuffers(commandBuffers[i], 0, 1, vertexBuffers, offsets);
+            vkCmdBindVertexBuffers(commandBuffers[i], 0, 1, vertexBuffers, offsets);
 
             // TODO: Bind the descriptor set for each grass blades model
+            vkCmdBindDescriptorSets(commandBuffers[i], VK_PIPELINE_BIND_POINT_GRAPHICS, graphicsPipelineLayout, 1, 1, &grassDescriptorSets[j], 0, nullptr);
 
             // Draw
             // TODO: Uncomment this when the buffers are populated
-            // vkCmdDrawIndirect(commandBuffers[i], scene->GetBlades()[j]->GetNumBladesBuffer(), 0, 1, sizeof(BladeDrawIndirect));
+            vkCmdDrawIndirect(commandBuffers[i], scene->GetBlades()[j]->GetNumBladesBuffer(), 0, 1, sizeof(BladeDrawIndirect));
         }
 
         // End render pass
@@ -1057,6 +1184,7 @@ Renderer::~Renderer() {
     vkDestroyDescriptorSetLayout(logicalDevice, cameraDescriptorSetLayout, nullptr);
     vkDestroyDescriptorSetLayout(logicalDevice, modelDescriptorSetLayout, nullptr);
     vkDestroyDescriptorSetLayout(logicalDevice, timeDescriptorSetLayout, nullptr);
+    vkDestroyDescriptorSetLayout(logicalDevice, computeDescriptorSetLayout, nullptr);
 
     vkDestroyDescriptorPool(logicalDevice, descriptorPool, nullptr);
 

src/Renderer.h

@@ -56,12 +56,17 @@ class Renderer {
     VkDescriptorSetLayout cameraDescriptorSetLayout;
     VkDescriptorSetLayout modelDescriptorSetLayout;
     VkDescriptorSetLayout timeDescriptorSetLayout;
-
+    VkDescriptorSetLayout computeDescriptorSetLayout;
+    VkDescriptorSetLayout grassDescriptorSetLayout;
+
     VkDescriptorPool descriptorPool;
 
     VkDescriptorSet cameraDescriptorSet;
     std::vector<VkDescriptorSet> modelDescriptorSets;
     VkDescriptorSet timeDescriptorSet;
+    std::vector<VkDescriptorSet> computeDescriptorSets;
+    std::vector<VkDescriptorSet> grassDescriptorSets;
+
 
     VkPipelineLayout graphicsPipelineLayout;
     VkPipelineLayout grassPipelineLayout;

src/shaders/compute.comp

@@ -36,21 +36,98 @@ struct Blade {
 // 	  uint firstInstance; // = 0
 // } numBlades;
 
+layout(set = 2, binding = 0) buffer InputBlades {
+  Blade blades[];
+} inputBlades;
+
+layout(set = 2, binding = 1) buffer CulledBlades {
+  Blade blades[];
+} culledBlades;
+
+layout(set = 2, binding = 2) buffer NumBlades {
+  uint vertexCount; 
+  uint instanceCount;
+  uint firstVertex;
+  uint firstInstance;
+} numBlades;
+
 bool inBounds(float value, float bounds) {
     return (value >= -bounds) && (value <= bounds);
 }
 
 void main() {
 	// Reset the number of blades to 0
 	if (gl_GlobalInvocationID.x == 0) {
-		// numBlades.vertexCount = 0;
+		numBlades.vertexCount = 0;
 	}
 	barrier(); // Wait till all threads reach this point
 
-    // TODO: Apply forces on every blade and update the vertices in the buffer
+  // TODO: Apply forces on every blade and update the vertices in the buffer
+  uint index = gl_GlobalInvocationID.x;
+  Blade blade = inputBlades.blades[index];
+
+	float h = blade.v1.w;
+	float w = blade.v2.w;
+	float stiff = blade.up.w;
+
+  vec3 v0 = blade.v0.xyz;
+	vec3 v1 = blade.v1.xyz;
+	vec3 v2 = blade.v2.xyz;
+	vec3 up = blade.up.xyz;
+
+  // gravity
+	vec3 gE = vec3(0.0, -9.8, 0.0);
+  vec3 f = normalize(cross(up, vec3(sin(blade.v0.w), 0.0, cos(blade.v0.w))));
+	vec3 gF = 0.25 * 9.8 * f;
+	vec3 gravity = gE + gF;
+
+  // recovery
+	vec3 recovery = (v0 + h * up - v2) * stiff;
+
+  // wind
+  vec3 dir = vec3(1.0, 0.0, 0.0) * cos(totalTime);			
+	float fd = 1 - abs(dot(normalize(dir), normalize(v2 - v0)));
+	float fr = dot((v2 - v0), up) / h;
+	vec3 wind = dir * fd * fr;
+
+	v2 += (recovery + gravity + wind) * deltaTime;
+
+  // validation
+  v2 = v2 - up * min(dot(up, v2 - v0), 0.0);
+
+  float lproj = length(v2 - v0 - up * dot(v2 - v0, up));
+	v1 = v0 + h * up * max(1.0 - (lproj / h), 0.05 * max(lproj / h, 1.0));
+
+  float n = 2.0;
+  float L0 = distance(v0, v2);
+	float L1 = distance(v0, v1) + distance(v1, v2);
+	float L = ((2.0 * L0) + (n - 1.0) * L1) / (n + 1.0);
+
+	float r = h / L;
+  vec3 v1corr = v0 + r * (v1 - v0);
+	vec3 v2corr = v1corr + r * (v2 - v1);
+
+	inputBlades.blades[index].v1.xyz = v1corr;
+	inputBlades.blades[index].v2.xyz = v2corr;
 
 	// TODO: Cull blades that are too far away or not in the camera frustum and write them
 	// to the culled blades buffer
 	// Note: to do this, you will need to use an atomic operation to read and update numBlades.vertexCount
 	// You want to write the visible blades to the buffer without write conflicts between threads
+  vec4 eye = inverse(camera.view) * vec4(0.0, 0.0, 0.0, 1.0);
+
+  // orientation
+	vec3 dir_c = normalize(eye.xyz - v0); vec3 dir_b = f;						
+	if(dot(dir_c, dir_b) > 0.9) return;
+
+  // view-frustum
+  vec4 v0_prime = camera.proj * camera.view * vec4(v0, 1.0);
+	float hg	= v0_prime.w + 2.0;
+	if(!inBounds(v0_prime.x, hg) || !inBounds(v0_prime.y, hg) || !inBounds(v0_prime.z, hg)) return;
+
+  // distance
+  float d_proj = length(v0 - eye.xyz - up * dot(up, v0 - eye.xyz));
+ 	if(mod(index, 10.0) > floor(10.0 * (1 - (d_proj / 50.0)))) return;
+
+  culledBlades.blades[atomicAdd(numBlades.vertexCount, 1)] = inputBlades.blades[index];
 }

src/shaders/grass.frag

@@ -7,11 +7,13 @@ layout(set = 0, binding = 0) uniform CameraBufferObject {
 } camera;
 
 // TODO: Declare fragment shader inputs
+layout(location = 0) in vec4 pos;
+layout(location = 1) in vec4 nor;
+layout(location = 2) in vec2 uv;
 
 layout(location = 0) out vec4 outColor;
 
 void main() {
     // TODO: Compute fragment color
-
-    outColor = vec4(1.0);
+    outColor = mix(vec4(0.0, 0.2, 0.0, 1.0), vec4(0.0, 0.4, 0.0, 1.0), uv.y);
 }

src/shaders/grass.tesc

@@ -9,18 +9,31 @@ layout(set = 0, binding = 0) uniform CameraBufferObject {
 } camera;
 
 // TODO: Declare tessellation control shader inputs and outputs
+layout(location = 0) in vec4 v0[];
+layout(location = 1) in vec4 v1[];
+layout(location = 2) in vec4 v2[];
+layout(location = 3) in vec4 up[];
+
+layout(location = 0) out vec4 v0_out[];
+layout(location = 1) out vec4 v1_out[];
+layout(location = 2) out vec4 v2_out[];
+layout(location = 3) out vec4 up_out[];
 
 void main() {
 	// Don't move the origin location of the patch
     gl_out[gl_InvocationID].gl_Position = gl_in[gl_InvocationID].gl_Position;
 
 	// TODO: Write any shader outputs
+  v0_out[gl_InvocationID] = v0[gl_InvocationID];
+	v1_out[gl_InvocationID] = v1[gl_InvocationID];
+	v2_out[gl_InvocationID] = v2[gl_InvocationID];
+	up_out[gl_InvocationID] = up[gl_InvocationID];
 
 	// TODO: Set level of tesselation
-    // gl_TessLevelInner[0] = ???
-    // gl_TessLevelInner[1] = ???
-    // gl_TessLevelOuter[0] = ???
-    // gl_TessLevelOuter[1] = ???
-    // gl_TessLevelOuter[2] = ???
-    // gl_TessLevelOuter[3] = ???
+  gl_TessLevelInner[0] = 2.0;
+  gl_TessLevelInner[1] = 5.0;
+  gl_TessLevelOuter[0] = 5.0;
+  gl_TessLevelOuter[1] = 2.0;
+  gl_TessLevelOuter[2] = 5.0;
+  gl_TessLevelOuter[3] = 2.0;
 }