OpenGL进阶之Instancing

Instancing

Instancing绘制我想很多童鞋都不陌生，这个技术主要用来快速渲染大量相同的几何体，可以大大提高绘制效率。每个instance在shader中都有一个独一无二的索引，可以用来访问每个instance对应的渲染参数。使用Instancing技术之所以能够大大提高效率，主要是因为它大大减少了dip（draw indexed primitive）的数量。

在实际应用中，我们可以将所有的渲染参数打包到一个buffer中，将它们一起送到GPU，然后，只需要调用一次绘制命令，就可以绘制大批不同的实体。同样，如果instance data没有改变的话（比如我们明确知道它们是用来绘制静态物体的），则不需要每一帧都将这些数据往GPU送一次，只需要在程序第一次初始化组织数据时传输一次就够了。

可能大家比较熟悉的，还是通过VBO进行Instancing绘制，但在实际的程序编写和优化过程中，还有很多buffer可以用来Instancing，OpenGL也有很多存储数据的方式，像VBO,UBO,TBO,SSBO等等。下面就详细讲解一下利用不同的数据传输方式进行Instancing绘制。

Texture instancing

这种方式是将所有渲染用到的数据都保存在一张纹理当中，然后通过PBO（Pixel Buffer Object）的方式进行数据更新，PBO通过异步的方式实现CPU到GPU之间的数据传输，从而不需要阻塞CPU等待数据传输完成。

纹理创建：

glGenBuffers(2, textureInstancingPBO);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER, textureInstancingPBO[0]); 
 
//GL_STREAM_DRAW_ARB means that we will change data every frame
glBufferData(GL_PIXEL_UNPACK_BUFFER, INSTANCES_DATA_SIZE, 0, GL_STREAM_DRAW_ARB);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER, textureInstancingPBO[1]);
glBufferData(GL_PIXEL_UNPACK_BUFFER, INSTANCES_DATA_SIZE, 0, GL_STREAM_DRAW_ARB);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER, 0);
//create texture where we will store instances data on gpu
glGenTextures(1, textureInstancingDataTex);
glBindTexture(GL_TEXTURE_2D, textureInstancingDataTex);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_R, GL_REPEAT); //in each line we store NUM_INSTANCES_PER_LINE object's data. 128 in our case
//for each object we store PER_INSTANCE_DATA_VECTORS data-vectors. 2 in our case
//GL_RGBA32F, we have float32 data
//complex_mesh_instances_data source data of instances, if we are not going to update data in the texture
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA32F, NUM_INSTANCES_PER_LINE * PER_INSTANCE_DATA_VECTORS, MAX_INSTANCES / NUM_INSTANCES_PER_LINE, 0, GL_RGBA, GL_FLOAT, &complex_mesh_instances_data[0]);
glBindTexture(GL_TEXTURE_2D, 0);

纹理更新：

glBindTexture(GL_TEXTURE_2D, textureInstancingDataTex);
glBindBufferARB(GL_PIXEL_UNPACK_BUFFER, textureInstancingPBO[current_frame_index]); // copy pixels from PBO to texture object
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, NUM_INSTANCES_PER_LINE * PER_INSTANCE_DATA_VECTORS, MAX_INSTANCES / NUM_INSTANCES_PER_LINE, GL_RGBA, GL_FLOAT, 0); // bind PBO to update pixel values
glBindBufferARB(GL_PIXEL_UNPACK_BUFFER, textureInstancingPBO[next_frame_index]);
//http://www.songho.ca/opengl/gl_pbo.html
// Note that glMapBufferARB() causes sync issue.
// If GPU is working with this buffer, glMapBufferARB() will wait(stall)
// until GPU to finish its job. To avoid waiting (idle), you can call
// first glBufferDataARB() with NULL pointer before glMapBufferARB().
// If you do that, the previous data in PBO will be discarded and
// glMapBufferARB() returns a new allocated pointer immediately
// even if GPU is still working with the previous data.
glBufferData(GL_PIXEL_UNPACK_BUFFER, INSTANCES_DATA_SIZE, 0, GL_STREAM_DRAW_ARB);
gpu_data = (float*)glMapBuffer(GL_PIXEL_UNPACK_BUFFER, GL_WRITE_ONLY_ARB);
if (gpu_data)
{
　　memcpy(gpu_data, complex_mesh_instances_data[0], INSTANCES_DATA_SIZE); // update data
　　glUnmapBuffer(GL_PIXEL_UNPACK_BUFFER); //release pointer to mapping buffer
}

使用texture instancing渲染：

//bind texture with instances data
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, textureInstancingDataTex);
glBindSampler(0, Sampler_nearest);
glBindVertexArray(geometry_vao_id); //what geometry to render
tex_instancing_shader.bind(); //with what shader
//tell shader texture with data located, what name it has
static GLint location = glGetUniformLocation(tex_instancing_shader.programm_id, s_texture_0);
if (location >= 0)
　　glUniform1i(location, 0); //render group of objects
glDrawElementsInstanced(GL_TRIANGLES, BOX_NUM_INDICES, GL_UNSIGNED_INT, NULL, CURRENT_NUM_INSTANCES);

顶点着色器示例：

version 150 core
in vec3 s_pos;
in vec3 s_normal;
in vec2 s_uv;
uniform mat4 ModelViewProjectionMatrix;
 
uniform sampler2D s_texture_0;
out vec2 uv;
out vec3 instance_color;
void main()
{
　　const vec2 texel_size = vec2(1.0 / 256.0, 1.0 / 16.0);
　　const int objects_per_row = 128;
　　const vec2 half_texel = vec2(0.5, 0.5);
　　//calc texture coordinates - where our instance data located
　　//gl_InstanceID % objects_per_row - index of object in the line
　　//multiple by 2 as each object has 2 vectors of data
　　//gl_InstanceID / objects_per_row - in what line our data located
　　//multiple by texel_size gieves us 0..1 uv to sample from texture from interer texel id
　　vec2 texel_uv = (vec2((gl_InstanceID % objects_per_row) * 2, floor(gl_InstanceID / objects_per_row)) + half_texel) * texel_size;
　　vec4 instance_pos = textureLod(s_texture_0, texel_uv, 0);
　　instance_color = textureLod(s_texture_0, texel_uv + vec2(texel_size.x, 0.0), 0).xyz;
　　uv = s_uv;
　　gl_Position = ModelViewProjectionMatrix * vec4(s_pos + instance_pos.xyz, 1.0);
}

vertex buffer Instancing

通过将数据存储在vbo，然后通过制定不同的数据布局，来制定不同的渲染参数。

buffer创建：

//...code of base vertex declaration creation
//special atributes binding
glBindBuffer(GL_ARRAY_BUFFER, all_instances_data_vbo); //size of per instance data (PER_INSTANCE_DATA_VECTORS = 2 - so we have to create 2 additional attributes to transfer data)
const int per_instance_data_size = sizeof(vec4) * PER_INSTANCE_DATA_VECTORS;
glEnableVertexAttribArray(4);
glVertexAttribPointer((GLuint)4, 4, GL_FLOAT, GL_FALSE, per_instance_data_size, (GLvoid*)(0)); //tell that we will change this attribute per instance, not per vertex
glVertexAttribDivisor(4, 1);
glEnableVertexAttribArray(5); //5th vertex attribute, has 4 floats, sizeof(vec4) data offset
glVertexAttribPointer((GLuint)5, 4, GL_FLOAT, GL_FALSE, per_instance_data_size, (GLvoid*)(sizeof(vec4)));
//tell that we will change this attribute per instance, not per vertex
glVertexAttribDivisor(5, 1);

渲染：

vbo_instancing_shader.bind(); //our vertex buffer wit modified vertex declaration (vdecl)
glBindVertexArray(geometry_vao_vbo_instancing_id);
glDrawElementsInstanced(GL_TRIANGLES, BOX_NUM_INDICES, GL_UNSIGNED_INT, NULL, CURRENT_NUM_INSTANCES);

顶点着色器：

#version 150 core
in vec3 s_pos;
in vec3 s_normal;
in vec2 s_uv;
in vec4 s_attribute_3; //some_data;
in vec4 s_attribute_4; //instance pos
in vec4 s_attribute_5; //instance color
uniform mat4 ModelViewProjectionMatrix;
out vec3 instance_color;
void main()
{
　　instance_color = s_attribute_5.xyz;
　　gl_Position = ModelViewProjectionMatrix * vec4(s_pos + s_attribute_4.xyz, 1.0);
}

Uniform Buffer Instancing:

buffer创建：

glGenBuffers(1, dips_uniform_buffer);
glBindBuffer(GL_UNIFORM_BUFFER, dips_uniform_buffer);
glBufferData(GL_UNIFORM_BUFFER, INSTANCES_DATA_SIZE, &complex_mesh_instances_data[0], GL_STATIC_DRAW);
//uniform_buffer_data
glBindBuffer(GL_UNIFORM_BUFFER, 0);
//bind iniform buffer with instances data to shader
ubo_instancing_shader.bind(true);
GLint instanceData_location3 = glGetUniformLocation(ubo_instancing_shader.programm_id, "instance_data");
//link to shader
glUniformBufferEXT(ubo_instancing_shader.programm_id, instanceData_location3, dips_uniform_buffer); //actually binding

着色器数据访问：

#version 150 core
#extension GL_ARB_bindable_uniform : enable
#extension GL_EXT_gpu_shader4 : enable
in vec3 s_pos;
in vec3 s_normal;
in vec2 s_uv;
uniform mat4 ModelViewProjectionMatrix;
bindable uniform vec4 instance_data[4096]; //our uniform with instances data
out vec3 instance_color;
void main()
{
　　vec4 instance_pos = instance_data[gl_InstanceID*2];
　　instance_color = instance_data[gl_InstanceID*2+1].xyz;
　　gl_Position = ModelViewProjectionMatrix * vec4(s_pos + instance_pos.xyz, 1.0);
}

Texture Buffer Instancing:

buffer创建：

tbo_instancing_shader.bind();
//bind to shader as special texture
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_BUFFER, dips_texture_buffer_tex);
glTexBuffer(GL_TEXTURE_BUFFER, GL_RGBA32F, dips_texture_buffer);
glBindVertexArray(geometry_vao_id);
glDrawElementsInstanced(GL_TRIANGLES, BOX_NUM_INDICES, GL_UNSIGNED_INT, NULL, CURRENT_NUM_INSTANCES);

顶点着色器数据访问：

#version 150 core
#extension GL_EXT_bindable_uniform : enable
#extension GL_EXT_gpu_shader4 : enable
in vec3 s_pos;
in vec3 s_normal;
in vec2 s_uv;
uniform mat4 ModelViewProjectionMatrix;
uniform samplerBuffer s_texture_0; //our TBO texture bufer
out vec3 instance_color;
void main()
{
　　//sample data from TBO
　　vec4 instance_pos = texelFetch(s_texture_0, gl_InstanceID*2);
　　instance_color = texelFetch(s_texture_0, gl_InstanceID*2+1).xyz;
　　gl_Position = ModelViewProjectionMatrix * vec4(s_pos + instance_pos.xyz, 1.0);
}

SSBO Instancing:

Buffer创建

glGenBuffers(1, ssbo);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, ssbo);
glBufferData(GL_SHADER_STORAGE_BUFFER, INSTANCES_DATA_SIZE, complex_mesh_instances_data[0], GL_STATIC_DRAW);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, ssbo);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, 0); // unbind

渲染代码：

//bind ssbo_instances_data, link to shader at 0 binding point
glBindBuffer(GL_SHADER_STORAGE_BUFFER, ssbo_instances_data);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, ssbo_instances_data);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, 0);
ssbo_instancing_shader.bind();
glBindVertexArray(geometry_vao_id);
glDrawElementsInstanced(GL_TRIANGLES, BOX_NUM_INDICES, GL_UNSIGNED_INT, NULL, CURRENT_NUM_INSTANCES);
glBindVertexArray(0);

顶点着色器：

#version 430
#extension GL_ARB_shader_storage_buffer_object : require
in vec3 s_pos;
in vec3 s_normal;
in vec2 s_uv;
uniform mat4 ModelViewProjectionMatrix;
//ssbo should be binded to 0
binding point layout(std430, binding = 0)
buffer ssboData { vec4 instance_data[4096]; };
out vec3 instance_color;
void main()
{
　　//gl_InstanceID is unique for each instance. So we able to set per instance data
　　vec4 instance_pos = instance_data[gl_InstanceID*2];
　　instance_color = instance_data[gl_InstanceID*2+1].xyz;
　　gl_Position = ModelViewProjectionMatrix * vec4(s_pos + instance_pos.xyz, 1.0);
}

Multi draw indirect：

这是一个非常有用的绘制命令，它可以达到跟instancing一样的效果，一次函数调用，多次dips。它对绘制一批Instance，不同geometry非常有用。

代码实例如下：

//fill indirect buffer with dips information. Just simple array
for (int i = 0; i < CURRENT_NUM_INSTANCES; i++)
{
　　multi_draw_indirect_buffer.vertexCount = BOX_NUM_INDICES;
　　multi_draw_indirect_buffer.instanceCount = 1;
　　multi_draw_indirect_buffer.firstVertex = i*BOX_NUM_INDICES;
　　multi_draw_indirect_buffer.baseVertex = 0;
　　multi_draw_indirect_buffer.baseInstance = 0;
}
glBindVertexArray(ws_complex_geometry_vao_id);
simple_geometry_shader.bind();
glMultiDrawElementsIndirect(GL_TRIANGLES, GL_UNSIGNED_INT, (GLvoid*)multi_draw_indirect_buffer[0], //our information about dips
CURRENT_NUM_INSTANCES, //number of dips 0);

glMultiDrawElementsIndirect在一次调用中，进行了多次glDrawElementsInstancedIndirect的绘制，但需要注意的是，这条指令有个很烦人的特点，就是每次glDrawElementsInstancedIndirect绘制对应对立的gl_InstanceID,每一次调用，gl_InstanceID都会从0重新开始。这在实际使用过程中一定要注意。

以上就是在实际instancing绘制中，主要会用到的数据组织方式，每一种方式都有自己的使用场景，需要根据实际的项目需要以及平台架构来决定哪种方式的效率最高。

引用link:

https://www.gamedev.net/articles/programming/graphics/opengl-api-overhead-r4614/

https://www.g-truc.net/post-0518.html

http://sol.gfxile.net/instancing.html