compute shader

src/8.guest/2022/5.computeshader_helloworld/computeShader.comp

@@ -0,0 +1,28 @@
+#version 430 core
+
+layout (local_size_x = 10, local_size_y = 10, local_size_z = 1) in;
+
+// ----------------------------------------------------------------------------
+//
+// uniforms
+//
+// ----------------------------------------------------------------------------
+
+layout(rgba32f, binding = 0) uniform image2D imgOutput;
+
+layout (location = 0) uniform float t;                 /**< Time */
+
+// ----------------------------------------------------------------------------
+//
+// functions
+//
+// ----------------------------------------------------------------------------
+
+void main() {
+    vec4 pixel = vec4(0.0, 0.0, 0.0, 1.0);
+    ivec2 pixelCoord = ivec2(gl_GlobalInvocationID.xy);
+    float speed = 0.5;
+    pixel.x = float(int((float(pixelCoord.x)/(gl_NumWorkGroups.x*gl_WorkGroupSize.x)+t*speed)*100)%100)/100;
+	pixel.y = float(pixelCoord.y)/(gl_NumWorkGroups.y*gl_WorkGroupSize.y);
+    imageStore(imgOutput, pixelCoord, pixel);
+}

src/8.guest/2022/5.computeshader_helloworld/computeShader.h

@@ -0,0 +1,49 @@
+#include <learnopengl/shader_m.h>
+
+
+class ComputeShader : public Shader
+{
+	public:
+		ComputeShader(const char* computePath)
+		{
+            // 1. retrieve the vertex/fragment source code from filePath
+            std::string computeCode;
+            std::ifstream cShaderFile;
+            // ensure ifstream objects can throw exceptions:
+            cShaderFile.exceptions(std::ifstream::failbit | std::ifstream::badbit);
+            try
+            {
+                // open files
+                cShaderFile.open(computePath);
+
+                std::stringstream cShaderStream;
+                // read file's buffer contents into streams
+                cShaderStream << cShaderFile.rdbuf();
+                // close file handlers
+                cShaderFile.close();
+                // convert stream into string
+                computeCode = cShaderStream.str();
+            }
+            catch (std::ifstream::failure& e)
+            {
+                std::cout << "ERROR::SHADER::FILE_NOT_SUCCESFULLY_READ: " << e.what() << std::endl;
+            }
+            const char* cShaderCode = computeCode.c_str();
+            // 2. compile shaders
+            unsigned int compute;
+            // compute shader
+            compute = glCreateShader(GL_COMPUTE_SHADER);
+            glShaderSource(compute, 1, &cShaderCode, NULL);
+            glCompileShader(compute);
+            checkCompileErrors(compute, "COMPUTE");
+           
+            // shader Program
+            ID = glCreateProgram();
+            glAttachShader(ID, compute);
+            glLinkProgram(ID);
+            checkCompileErrors(ID, "PROGRAM");
+            // delete the shaders as they're linked into our program now and no longer necessery
+            glDeleteShader(compute);
+
+		}
+};

src/8.guest/2022/5.computeshader_helloworld/computer_shader_hello_world.cpp

@@ -0,0 +1,196 @@
+#include <glad/glad.h>
+#include <GLFW/glfw3.h>
+
+#include <glm/glm.hpp>
+#include <glm/gtc/matrix_transform.hpp>
+#include <glm/gtc/type_ptr.hpp>
+
+#include <learnopengl/shader_m.h>
+#include <learnopengl/camera.h>
+
+#include <iostream>
+
+#include "computeShader.h"
+
+void framebuffer_size_callback(GLFWwindow* window, int width, int height);
+void renderQuad();
+
+// settings
+const unsigned int SCR_WIDTH = 800;
+const unsigned int SCR_HEIGHT = 600;
+
+// texture size
+const unsigned int TEXTURE_WIDTH = 1000, TEXTURE_HEIGHT = 1000;
+
+// timing 
+float deltaTime = 0.0f; // time between current frame and last frame
+float lastFrame = 0.0f; // time of last frame
+
+int main(int argc, char* argv[])
+{
+	// glfw: initialize and configure
+	// ------------------------------
+	glfwInit();
+	glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 4);
+	glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3);
+	glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);
+
+	#ifdef __APPLE__
+		glfwWindowHint(GLFW_OPENGL_FORWARD_COMPAT, GL_TRUE);
+	#endif
+
+	// glfw window creation
+	// --------------------
+	GLFWwindow* window = glfwCreateWindow(SCR_WIDTH, SCR_HEIGHT, "LearnOpenGL", NULL, NULL);
+	if (window == NULL)
+	{
+		std::cout << "Failed to create GLFW window" << std::endl;
+		glfwTerminate();
+		return -1;
+	}
+	glfwMakeContextCurrent(window);
+	glfwSetFramebufferSizeCallback(window, framebuffer_size_callback);
+	glfwSwapInterval(0);
+
+	// glad: load all OpenGL function pointers
+	// ---------------------------------------
+	if (!gladLoadGLLoader((GLADloadproc)glfwGetProcAddress))
+	{
+		std::cout << "Failed to initialize GLAD" << std::endl;
+		return -1;
+	}
+
+	// query limitations
+	// -----------------
+	int max_compute_work_group_count[3];
+	int max_compute_work_group_size[3];
+	int max_compute_work_group_invocations;
+
+	for (int idx = 0; idx < 3; idx++) {
+		glGetIntegeri_v(GL_MAX_COMPUTE_WORK_GROUP_COUNT, idx, &max_compute_work_group_count[idx]);
+		glGetIntegeri_v(GL_MAX_COMPUTE_WORK_GROUP_SIZE, idx, &max_compute_work_group_size[idx]);
+	}	
+	glGetIntegerv(GL_MAX_COMPUTE_WORK_GROUP_INVOCATIONS, &max_compute_work_group_invocations);
+
+	std::cout << "OpenGL Limitations: " << std::endl;
+	std::cout << "maxmimum number of work groups in X dimension " << max_compute_work_group_count[0] << std::endl;
+	std::cout << "maxmimum number of work groups in Y dimension " << max_compute_work_group_count[1] << std::endl;
+	std::cout << "maxmimum number of work groups in Z dimension " << max_compute_work_group_count[2] << std::endl;
+
+	std::cout << "maxmimum size of a work group in X dimension " << max_compute_work_group_size[0] << std::endl;
+	std::cout << "maxmimum size of a work group in Y dimension " << max_compute_work_group_size[1] << std::endl;
+	std::cout << "maxmimum size of a work group in Z dimension " << max_compute_work_group_size[2] << std::endl;
+
+	std::cout << "Number of invocations in a single local work group that may be dispatched to a compute shader " << max_compute_work_group_invocations << std::endl;
+
+	// build and compile shaders
+	// -------------------------
+	Shader screenQuad("screenQuad.vs", "screenQuad.fs");
+	ComputeShader computeShader("computeShader.comp");
+
+	screenQuad.use();
+	screenQuad.setInt("tex", 0);
+
+	// Create texture for opengl operation
+	// -----------------------------------
+	GLuint texture;
+
+	glGenTextures(1, &texture);
+	glActiveTexture(GL_TEXTURE0);
+	glBindTexture(GL_TEXTURE_2D, texture);
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
+	glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA32F, TEXTURE_WIDTH, TEXTURE_HEIGHT, 0, GL_RGBA, GL_FLOAT, NULL);
+
+	glBindImageTexture(0, texture, 0, GL_FALSE, 0, GL_READ_WRITE, GL_RGBA32F);
+
+	glActiveTexture(GL_TEXTURE0);
+	glBindTexture(GL_TEXTURE_2D, texture);
+
+	// render loop
+	// -----------
+	int fCounter = 0;
+	while (!glfwWindowShouldClose(window))
+	{
+		// Set frame time
+		GLfloat currentFrame = glfwGetTime();
+		deltaTime = currentFrame - lastFrame;
+		lastFrame = currentFrame;
+		if(fCounter > 500) {
+			std::cout << "FPS: " << 1 / deltaTime << std::endl;
+			fCounter = 0;
+		} else {
+			fCounter++;
+		}		
+
+		computeShader.use();
+		computeShader.setFloat("t", currentFrame);
+		glDispatchCompute((GLuint)TEXTURE_WIDTH/10, (GLuint)TEXTURE_HEIGHT/10, 1);
+
+		// make sure writing to image has finished before read
+		glMemoryBarrier(GL_SHADER_IMAGE_ACCESS_BARRIER_BIT);
+
+		// render image to quad
+		glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
+		screenQuad.use();
+		
+		renderQuad();
+
+		// glfw: swap buffers and poll IO events (keys pressed/released, mouse moved etc.)
+		// -------------------------------------------------------------------------------
+		glfwSwapBuffers(window);
+		glfwPollEvents();
+	}
+
+	// optional: de-allocate all resources once they've outlived their purpose:
+	// ------------------------------------------------------------------------
+	glDeleteTextures(1, &texture);
+	glDeleteProgram(screenQuad.ID);
+	glDeleteProgram(computeShader.ID);
+
+	glfwTerminate();
+
+	return EXIT_SUCCESS;
+}
+
+// renderQuad() renders a 1x1 XY quad in NDC
+// -----------------------------------------
+unsigned int quadVAO = 0;
+unsigned int quadVBO;
+void renderQuad()
+{
+	if (quadVAO == 0)
+	{
+		float quadVertices[] = {
+			// positions        // texture Coords
+			-1.0f,  1.0f, 0.0f, 0.0f, 1.0f,
+			-1.0f, -1.0f, 0.0f, 0.0f, 0.0f,
+			 1.0f,  1.0f, 0.0f, 1.0f, 1.0f,
+			 1.0f, -1.0f, 0.0f, 1.0f, 0.0f,
+		};
+		// setup plane VAO
+		glGenVertexArrays(1, &quadVAO);
+		glGenBuffers(1, &quadVBO);
+		glBindVertexArray(quadVAO);
+		glBindBuffer(GL_ARRAY_BUFFER, quadVBO);
+		glBufferData(GL_ARRAY_BUFFER, sizeof(quadVertices), &quadVertices, GL_STATIC_DRAW);
+		glEnableVertexAttribArray(0);
+		glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 5 * sizeof(float), (void*)0);
+		glEnableVertexAttribArray(1);
+		glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, 5 * sizeof(float), (void*)(3 * sizeof(float)));
+	}
+	glBindVertexArray(quadVAO);
+	glDrawArrays(GL_TRIANGLE_STRIP, 0, 4);
+	glBindVertexArray(0);
+}
+
+// glfw: whenever the window size changed (by OS or user resize) this callback function executes
+// ---------------------------------------------------------------------------------------------
+void framebuffer_size_callback(GLFWwindow* window, int width, int height)
+{
+	// make sure the viewport matches the new window dimensions; note that width and 
+	// height will be significantly larger than specified on retina displays.
+	glViewport(0, 0, width, height);
+}

src/8.guest/2022/5.computeshader_helloworld/screenQuad.fs

@@ -0,0 +1,12 @@
+#version 330 core
+out vec4 FragColor;
+
+in vec2 TexCoords;
+
+uniform sampler2D tex;
+
+void main()
+{             
+    vec3 texCol = texture(tex, TexCoords).rgb;      
+    FragColor = vec4(texCol, 1.0);
+}

src/8.guest/2022/5.computeshader_helloworld/screenQuad.vs

@@ -0,0 +1,11 @@
+#version 330 core
+layout (location = 0) in vec3 aPos;
+layout (location = 1) in vec2 aTexCoords;
+
+out vec2 TexCoords;
+
+void main()
+{
+    TexCoords = aTexCoords;
+    gl_Position = vec4(aPos, 1.0);
+}