Project5: Hanting Xu

README.md

@@ -3,10 +3,64 @@ Vulkan Grass Rendering
 
 **University of Pennsylvania, CIS 565: GPU Programming and Architecture, Project 5**
 
-* (TODO) YOUR NAME HERE
-* Tested on: (TODO) Windows 22, i7-2222 @ 2.22GHz 22GB, GTX 222 222MB (Moore 2222 Lab)
+* Hanting Xu
+* [GitHub](https://github.com/HantingXu), [LinkedIn](www.linkedin.com/in/hanting-xu-25615b28b).
+* Tested on: (Personal Computer) Windows 11, i7-12700H @ 2.70GHz 32GB, GeForce RTX 3070 Ti Laptop GPU
 
-### (TODO: Your README)
+### Project Description
+#### General Introduction
 
-*DO NOT* leave the README to the last minute! It is a crucial part of the
-project, and we will not be able to grade you without a good README.
+Based on this [essay](https://www.cg.tuwien.ac.at/research/publications/2017/JAHRMANN-2017-RRTG/JAHRMANN-2017-RRTG-draft.pdf), this project simulate a field of grass using  Vulkan.
+
+#### Core Features
+* basic grass rendering using Bezier Curve.
+
+  * ![](img/blade_model.jpg)
+
+
+* grass rendering with simulated force, including gravity, wind force and recovery force.
+
+  * ![](img/force.png)
+
+
+* grass culling according to the orietation of the grass, view frustrum and distance.
+
+
+### Show Case
+* Basic Grass Rendering without Force and Culling Applied
+
+ * ![Result1](img/original.png)
+
+
+* With Gravity Force and Recovery Force Applied
+
+ * ![Result1](img/gravity.png)
+
+
+* With All Forces Applied
+
+  * ![Result1](img/wind.gif)
+
+
+* All Forces Applied with Orientation Culling
+
+  * ![Result1](img/orientation.gif)
+
+
+* All Forces Applied with View-Frustrum Culling
+
+  * ![Result1](img/frustrum.gif)
+
+
+* All Forces Applied with Distance Culling
+
+  * ![Result1](img/distance.gif)
+
+
+* All Features Applied
+
+  * ![Result1](img/all.gif)
+
+### Performance Analysis
+The graph below shows the different FPS change with respect to different culling methods. The x-axis in the graph represents the number of blades to be rendered, while y-axis means the FPS. As we may observe from the graph, the FPS of the grass simulation delines as the number of blades to be drawn grows higher. And culling does greatly improve the overall performance, especially for orientation and distance culling. However, in this setting the view-frustrum culling seems to be useless and have little effect on the performance. That is probably because of the setting of the offset parameter is so small that only very few blades are culled.
+* ![Result1](img/result.png)

src/Renderer.cpp

@@ -198,6 +198,38 @@ 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 bladesLayoutBinding = {};
+    bladesLayoutBinding.binding = 0;
+    bladesLayoutBinding.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    bladesLayoutBinding.descriptorCount = 1;
+    bladesLayoutBinding.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;
+    bladesLayoutBinding.pImmutableSamplers = nullptr;
+
+    VkDescriptorSetLayoutBinding culledBladesLayoutBinding = {};
+    culledBladesLayoutBinding.binding = 1;
+    culledBladesLayoutBinding.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    culledBladesLayoutBinding.descriptorCount = 1;
+    culledBladesLayoutBinding.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;
+    culledBladesLayoutBinding.pImmutableSamplers = nullptr;
+
+    VkDescriptorSetLayoutBinding numBladesLayoutBinding = {};
+    numBladesLayoutBinding.binding = 2;
+    numBladesLayoutBinding.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+    numBladesLayoutBinding.descriptorCount = 1;
+    numBladesLayoutBinding.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;
+    numBladesLayoutBinding.pImmutableSamplers = nullptr;
+
+    std::vector<VkDescriptorSetLayoutBinding> bindings = { bladesLayoutBinding, culledBladesLayoutBinding, numBladesLayoutBinding };
+
+    // Create the descriptor set layout
+    VkDescriptorSetLayoutCreateInfo layoutInfo = {};
+    layoutInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO;
+    layoutInfo.bindingCount = static_cast<uint32_t>(bindings.size());
+    layoutInfo.pBindings = bindings.data();
+
+    if (vkCreateDescriptorSetLayout(logicalDevice, &layoutInfo, nullptr, &computeDescriptorSetLayout) != VK_SUCCESS) {
+        throw std::runtime_error("Failed to create descriptor set layout");
+    }
 }
 
 void Renderer::CreateDescriptorPool() {
@@ -216,6 +248,7 @@ void Renderer::CreateDescriptorPool() {
         { VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER , 1 },
 
         // TODO: Add any additional types and counts of descriptors you will need to allocate
+        { VK_DESCRIPTOR_TYPE_STORAGE_BUFFER , static_cast<uint32_t>(3 * scene->GetBlades().size()) },
     };
 
     VkDescriptorPoolCreateInfo poolInfo = {};
@@ -320,6 +353,42 @@ 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 grassBufferInfo = {};
+        grassBufferInfo.buffer = scene->GetBlades()[i]->GetModelBuffer();
+        grassBufferInfo.offset = 0;
+        grassBufferInfo.range = sizeof(ModelBufferObject);
+
+        descriptorWrites[i].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+        descriptorWrites[i].dstSet = grassDescriptorSets[i];
+        descriptorWrites[i].dstBinding = 0;
+        descriptorWrites[i].dstArrayElement = 0;
+        descriptorWrites[i].descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
+        descriptorWrites[i].descriptorCount = 1;
+        descriptorWrites[i].pBufferInfo = &grassBufferInfo;
+        descriptorWrites[i].pImageInfo = nullptr;
+        descriptorWrites[i].pTexelBufferView = nullptr;
+    }
+
+    // Update descriptor sets
+    vkUpdateDescriptorSets(logicalDevice, static_cast<uint32_t>(descriptorWrites.size()), descriptorWrites.data(), 0, nullptr);
 }
 
 void Renderer::CreateTimeDescriptorSet() {
@@ -360,6 +429,72 @@ 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 bladesBufferInfo = {};
+        bladesBufferInfo.buffer = scene->GetBlades()[i]->GetBladesBuffer();
+        bladesBufferInfo.offset = 0;
+        bladesBufferInfo.range = NUM_BLADES * sizeof(Blade);
+
+        VkDescriptorBufferInfo culledBladesBufferInfo = {};
+        culledBladesBufferInfo.buffer = scene->GetBlades()[i]->GetCulledBladesBuffer();
+        culledBladesBufferInfo.offset = 0;
+        culledBladesBufferInfo.range = NUM_BLADES * sizeof(Blade);
+
+        VkDescriptorBufferInfo numBladesBufferInfo = {};
+        numBladesBufferInfo.buffer = scene->GetBlades()[i]->GetNumBladesBuffer();
+        numBladesBufferInfo.offset = 0;
+        numBladesBufferInfo.range = sizeof(BladeDrawIndirect);
+
+        descriptorWrites[3 * i].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
+        descriptorWrites[3 * i].dstSet = computeDescriptorSets[i];
+        descriptorWrites[3 * i].dstBinding = 0;
+        descriptorWrites[3 * i].dstArrayElement = 0;
+        descriptorWrites[3 * i].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
+        descriptorWrites[3 * i].descriptorCount = 1;
+        descriptorWrites[3 * i].pBufferInfo = &bladesBufferInfo;
+        descriptorWrites[3 * i].pImageInfo = nullptr;
+        descriptorWrites[3 * i].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 = &culledBladesBufferInfo;
+        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 = &numBladesBufferInfo;
+        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 +852,7 @@ 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 +1019,11 @@ 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 (uint32_t i = 0; i < scene->GetBlades().size(); ++i)
+    {
+        vkCmdBindDescriptorSets(computeCommandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, computePipelineLayout, 2, 1, &computeDescriptorSets[i], 0, nullptr);
+        vkCmdDispatch(computeCommandBuffer, NUM_BLADES / WORKGROUP_SIZE, 1, 1);
+    }
 
     // ~ End recording ~
     if (vkEndCommandBuffer(computeCommandBuffer) != VK_SUCCESS) {
@@ -976,13 +1116,14 @@ 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, grassPipelineLayout, 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
@@ -1056,6 +1197,7 @@ Renderer::~Renderer() {
 
     vkDestroyDescriptorSetLayout(logicalDevice, cameraDescriptorSetLayout, nullptr);
     vkDestroyDescriptorSetLayout(logicalDevice, modelDescriptorSetLayout, nullptr);
+    vkDestroyDescriptorSetLayout(logicalDevice, computeDescriptorSetLayout, nullptr);
     vkDestroyDescriptorSetLayout(logicalDevice, timeDescriptorSetLayout, nullptr);
 
     vkDestroyDescriptorPool(logicalDevice, descriptorPool, nullptr);

src/Renderer.h

@@ -56,11 +56,14 @@ class Renderer {
     VkDescriptorSetLayout cameraDescriptorSetLayout;
     VkDescriptorSetLayout modelDescriptorSetLayout;
     VkDescriptorSetLayout timeDescriptorSetLayout;
+    VkDescriptorSetLayout computeDescriptorSetLayout;
 
     VkDescriptorPool descriptorPool;
 
     VkDescriptorSet cameraDescriptorSet;
     std::vector<VkDescriptorSet> modelDescriptorSets;
+    std::vector<VkDescriptorSet> grassDescriptorSets;
+    std::vector<VkDescriptorSet> computeDescriptorSets;
     VkDescriptorSet timeDescriptorSet;
 
     VkPipelineLayout graphicsPipelineLayout;