Vulkan compute shader. Smooth uv coordinates - vulkan

I have this shader:
#version 450
layout(binding = 0) buffer b0 {
vec2 src[ ];
};
layout(binding = 1) buffer b1 {
vec2 dst[ ];
};
layout(binding = 2) buffer b2 {
int index[ ];
};
layout (local_size_x = 1, local_size_y = 1, local_size_z = 1) in;
void main()
{
int ind =int(gl_GlobalInvocationID.x);
vec2 norm;
norm=src[index[ind*3+2]]-src[index[ind*3]]+src[index[ind*3+1]]-src[index[ind*3]];
norm/=2.0;
dst[index[ind*3]] +=norm;
norm=src[index[ind*3+0]]-src[index[ind*3+1]]+src[index[ind*3+2]]-src[index[ind*3+1]];
dst[index[ind*3+1]] +=norm;
norm=src[index[ind*3+1]]-src[index[ind*3+2]]+src[index[ind*3+0]]-src[index[ind*3+2]];
norm/=2.0;
dst[index[ind*3+2]] +=norm;
}
Because dst buffer is not "atomic", the summation is incorrect.
Is there any way to solve this problem? My answer is no, but if i missed something.
For each vertex in polygon I am calculating a vector from vertex to the center of polygon. Different polygons has the same vertices.
dst - is a vertex buffer, the result of the summation of those shifts from vertex to polygon center.
Each time I have different computation results.

Related

Optimization for scene with custom shader

I have a three.js scene made with rogue engine, which im using to make a VR experience.
In that im using a fairly complex shader, it takes world space location of two locators for transitioning between their normal shader and just some color, the transition is using noise for some effect (see video below, its showing the effect of the first locator but the second one is also similar, it goes bottom to top),
the location of the object is passed as Vector 3 uniforms., the shader itself im injecting to a MeshStandardMaterial using onBeforeCompile.
the performance is already bad and really tanks when im using textures, im using three texture sets for the scene, im using diffuse,rough,metal,emission and AO so each is sampled thrice and then masked using vertex colors. (not present in the code below)
varying vec3 W_Pos; //world position vector
varying vec3 F_Nrml; //normal vector
varying vec3 camDir; // cam facing
varying vec3 vertexColor;
uniform vec3 astral_locator; // First locator
uniform vec3 astral_spread; // i pass the locator's scale here and scale it up for the transition
uniform vec3 starScatter_starScale_nScale; //three float parameters im passing as vector for easier control in rogue engine
uniform vec3 breakPoints;
uniform vec3 c1;
uniform vec3 c2;
uniform vec3 c3;
uniform vec3 noise_locator; //Second locator
uniform vec3 nStretch_nScale_emSharp;// same as above, three floats passed as a vector
uniform vec3 emCol;
vec4 mod289(vec4 x){return x - floor(x * (1.0 / 289.0)) * 289.0;}
vec4 perm(vec4 x){return mod289(((x * 34.0) + 1.0) * x);}
vec3 rand2( vec3 p ) {
return fract(
sin(
vec3(dot(p,vec3(127.1,310.7,143.54)),dot(p,vec3(269.5,183.3,217.42)),dot(p,vec3(2459.5,133.3,17.42))))*43758.5453);
}
float mapping(float number, float inMin, float inMax, float outMin, float outMax){return (number - inMin) * (outMax - outMin) / (inMax - inMin) + outMin;}
vec4 vertexMask(vec4 map1, vec4 map2, vec4 map3, vec3 vertMask){vec4 me1 = mix(vec4(0.0), map1,vertMask.r); vec4 me2 = mix(me1, map2,vertMask.g); vec4 me3 = mix(me2, map3,vertMask.b); return me3;}
//Noises
float noise(vec3 p){
vec3 a = floor(p);
vec3 d = p - a;
d = d * d * (3.0 - 2.0 * d);
vec4 b = a.xxyy + vec4(0.0, 1.0, 0.0, 1.0);
vec4 k1 = perm(b.xyxy);
vec4 k2 = perm(k1.xyxy + b.zzww);
vec4 c = k2 + a.zzzz;
vec4 k3 = perm(c);
vec4 k4 = perm(c + 1.0);
vec4 o1 = fract(k3 * (1.0 / 41.0));
vec4 o2 = fract(k4 * (1.0 / 41.0));
vec4 o3 = o2 * d.z + o1 * (1.0 - d.z);
vec2 o4 = o3.yw * d.x + o3.xz * (1.0 - d.x);
return o4.y * d.y + o4.x * (1.0 - d.y);
}
float facing(){
vec3 nrml = F_Nrml;
vec3 cam = camDir;
vec3 normal = normalize(nrml.xyz);
vec3 eye = normalize(-cam);
float rim = smoothstep(-0.75, 1.0, 1.0 - dot(normal, eye));
return clamp(rim, 0.0, 1.0);
}
//Function for the second locatior
vec2 noiseMove(vec3 loc,vec3 noiseDat){
float noise_stretch = noiseDat.x;
float noise_scale = noiseDat.y;
float emission_sharp = noiseDat.z;
float noise_move = -loc.y;
float gen_Pattern;
float gen_Pattern_invert;
float emi_sharp_fac;
float transparency;
float emission;
gen_Pattern = ((W_Pos.y+noise_move)*noise_stretch) + noise(W_Pos.xyz*noise_scale);
gen_Pattern_invert = 1.0 - gen_Pattern;
emi_sharp_fac = clamp(emission_sharp*1000.0,1.0,1000.0)*gen_Pattern;
emission = emission_sharp*gen_Pattern;
emission = 1.0 - emission;
emission = emission * emi_sharp_fac;
emission = clamp(emission,0.0,1.0);
transparency = clamp(gen_Pattern_invert,0.0,1.0);
return vec2(emission,transparency);
}
//Function for the first locator
vec4 astral(vec3 loc, vec3 spr,vec3 cee1,vec3 cee2,vec3 cee3, vec3 breakks, vec3 star){//star is WIP
float f = facing();
float re1 = mapping(f,breakks.x,1.0,0.0,1.0);
float re2 = mapping(f,breakks.y,1.0,0.0,1.0);
float re3 = mapping(f,breakks.z,1.0,0.0,1.0);
vec3 me1 = mix(vec3(0.,0.,0.),cee1,re1);
vec3 me2 = mix(me1,cee2,re2);
vec3 me3 = mix(me2,cee3,re3);
float dist = distance(W_Pos.xyz + (noise(W_Pos.xyz*star.z)-0.5),loc);
float val = step(dist,spr.x);
return vec4(me3,val);
}
void main(){
vec4 ast = astral(astral_locator,astral_spread,c1,c2,c3,breakPoints,starScatter_starScale_nScale);
vec2 noice = noiseMove(noise_locator,nStretch_nScale_emSharp);
vec3 outp = mix(mix(outgoingLight,ast.xyz,ast.w),emCol,noice.x); //Take output light from the three.js shader and mix it with the custom shader
float t = noice.y;
#ifdef NONSCIFI
t = 1.0 - noice.y;
#endif
t *= diffuseColor.a;
gl_FragColor = vec4(outp*t,t);
}
is there a way to optimize it better? a couple things i can think of is storing the noise and then using it instead of calculating every frame, and figuring out occlusion culling (renderpass doesnt work well in VR so cant store the depth pass, gotta figure a way), objects in the scene are already instances to reduce draw calls. im assuming making some objects static might help, including the locators but i dont know if it will stop the uniform from updating every frame.
is there anything else that can be done?
also i apologize for the structure of the question, i rarely post questions thanks to stackoverflow :p

shader value conversion error when passing value between vertex and fragment shader

I have the following fragment and vertex shader.
Vertex:
#version 450
layout(location = 0) in vec2 Position;
layout(location = 1) in vec4 Color;
layout(location = 0) out vec2 fPosition;
void main()
{
gl_Position = vec4(Position, 0, 1);
fPosition = Position;
}
Fragment:
#version 450
layout(location = 0) in vec2 fPosition;
layout(location = 0) out vec4 fColor;
void main() {
vec4 colors[4] = vec4[](
vec4(1.0, 0.0, 0.0, 1.0),
vec4(0.0, 1.0, 0.0, 1.0),
vec4(0.0, 0.0, 1.0, 1.0),
vec4(0.0, 0.0, 0.0, 1.0)
);
fColor = vec4(1.0);
for(int row = 0; row < 2; row++) {
for(int col = 0; col < 2; col++) {
float dist = distance(fPosition, vec2(-0.50 + col, 0.50 - row));
float delta = fwidth(dist);
float alpha = smoothstep(0.45-delta, 0.45, dist);
fColor = mix(colors[row*2+col], fColor, alpha);
}
}
}
But when compiling this I am getting the following error:
cannot convert from ' gl_Position 4-component vector of float Position' to 'layout( location=0) smooth out highp 2-component vector of float'
And i have no clue how to fix it. (this is my first time doing shader programming).
If additional information is needed please let me know.
1.
You do not need to specify layouts when transferring variables between vertex shader and fragment shader. Remove the layout(location = 0) parameter for the fPosition variable in the vertex and fragment shader.
2.
You only need to specify layout if you passing the variables (your position buffers) to the vertex shader through buffers. To add on, variables like positions, normals and textureCoords must always pass through the vertex shader first and then to the fragment shader.
3.
When exporting your final colour (fColor in your case) from the fragment shader, you do not need to pass a location, just specify the vector4 variable as out vec4 fColor; openGL detects it automatically.
4.
The error you actually got was telling you that you were assigning vector4 variable (fColor) to your already stored vec2 variables (fPosition). Note: In your vertex shader at attribute (location) "0", you had accessed the vertices that you had loaded, but you tried to assign a vector4 to the same location later in the fragment shader. OpenGL does not automatically overwrite data like that.

How to do batching without UBOs?

I'm trying to implement batching for a WebGL renderer which is struggling with lots of small objects due to too many draw calls. What I thought is I'd batch them all by the kind of shader they use, then draw a few at a time, uploading material parameters and the model matrix for each object once in uniforms.
My problem is that the uniform size limits for non-UBO uniforms are extremely low, as in 256 floats low at a minimum. If my material uses, say, 8 floats, and if you factor in the model matrix, I barely have enough uniforms to draw 10 models in a single batch, which isn't really going to be enough.
Is there any hope to make this work without UBOs? Are textures an option? How are people doing batching without WebGL2 UBOs?
More details: I have no skinning or complex animations, I just have some shaders (diffuse, cook-torrance, whatever) and each model has different material settings for each shader, e.g. color, roughness, index of refraction which can be changed dynamically by the user (so it's not realistic to bake them into the vertex array because we have some high poly data, also users can switch shaders and not all shaders have the same number of parameters) as well as material maps obviously. The geometry itself is static and just has a linear transform on each model. For the most part all meshes are different so geometry instancing won't help a whole lot, but I can look at that later.
Thanks
I don't know that this is actually faster than lots of draw calls but here is drawing 4 models with a single draw call
It works by adding an id per model. So, for every vertex in model #0 put a 0, for every vertex in model #1 put a 1, etc.
Then it uses model id to index stuff in a texture. The easiest would be model id chooses the row of a texture and then all the data for that model can be pulled out of that row.
For WebGL1
attribute float modelId;
...
#define TEXTURE_WIDTH ??
#define COLOR_OFFSET ((0.0 + 0.5) / TEXTURE_WIDTH)
#define MATERIAL_OFFSET ((1.0 + 0.5) / TEXTURE_WIDTH)
float modelOffset = (modelId + .5) / textureHeight;
vec4 color = texture2D(perModelData, vec2(COLOR_OFFSET, modelOffset));
vec4 roughnessIndexOfRefaction = texture2D(perModelData,
vec2(MATERIAL_OFFSET, modelOffset));
etc..
As long as you are not drawing more than gl.getParameter(gl.MAX_TEXTURE_SIZE) models it will work. If you have more than that either use more draw calls or change the texture coordinate calculations so there's more than one model per row
In WebGL2 you'd change the code to use texelFetch and unsigned integers
in uint modelId;
...
#define COLOR_OFFSET 0
#define MATERIAL_OFFSET 1
vec4 color = texelFetch(perModelData, uvec2(COLOR_OFFSET, modelId));
vec4 roughnessIndexOfRefaction = texelFetch(perModelData,
uvec2(MATERIAL_OFFSET, modelId));
example of 4 models drawn with 1 draw call. For each model the model matrix and color are stored in the texture.
const m4 = twgl.m4;
const v3 = twgl.v3;
const gl = document.querySelector('canvas').getContext('webgl');
const ext = gl.getExtension('OES_texture_float');
if (!ext) {
alert('need OES_texture_float');
}
const COMMON_STUFF = `
#define TEXTURE_WIDTH 5.0
#define MATRIX_ROW_0_OFFSET ((0. + 0.5) / TEXTURE_WIDTH)
#define MATRIX_ROW_1_OFFSET ((1. + 0.5) / TEXTURE_WIDTH)
#define MATRIX_ROW_2_OFFSET ((2. + 0.5) / TEXTURE_WIDTH)
#define MATRIX_ROW_3_OFFSET ((3. + 0.5) / TEXTURE_WIDTH)
#define COLOR_OFFSET ((4. + 0.5) / TEXTURE_WIDTH)
`;
const vs = `
attribute vec4 position;
attribute vec3 normal;
attribute float modelId;
uniform float textureHeight;
uniform sampler2D perModelDataTexture;
uniform mat4 projection;
uniform mat4 view;
varying vec3 v_normal;
varying float v_modelId;
${COMMON_STUFF}
void main() {
v_modelId = modelId; // pass to fragment shader
float modelOffset = (modelId + 0.5) / textureHeight;
// note: in WebGL2 better to use texelFetch
mat4 model = mat4(
texture2D(perModelDataTexture, vec2(MATRIX_ROW_0_OFFSET, modelOffset)),
texture2D(perModelDataTexture, vec2(MATRIX_ROW_1_OFFSET, modelOffset)),
texture2D(perModelDataTexture, vec2(MATRIX_ROW_2_OFFSET, modelOffset)),
texture2D(perModelDataTexture, vec2(MATRIX_ROW_3_OFFSET, modelOffset)));
gl_Position = projection * view * model * position;
v_normal = mat3(view) * mat3(model) * normal;
}
`;
const fs = `
precision highp float;
varying vec3 v_normal;
varying float v_modelId;
uniform float textureHeight;
uniform sampler2D perModelDataTexture;
uniform vec3 lightDirection;
${COMMON_STUFF}
void main() {
float modelOffset = (v_modelId + 0.5) / textureHeight;
vec4 color = texture2D(perModelDataTexture, vec2(COLOR_OFFSET, modelOffset));
float l = dot(lightDirection, normalize(v_normal)) * .5 + .5;
gl_FragColor = vec4(color.rgb * l, color.a);
}
`;
// compile shader, link, look up locations
const programInfo = twgl.createProgramInfo(gl, [vs, fs]);
// make some vertex data
const modelVerts = [
twgl.primitives.createSphereVertices(1, 6, 4),
twgl.primitives.createCubeVertices(1, 1, 1),
twgl.primitives.createCylinderVertices(1, 1, 10, 1),
twgl.primitives.createTorusVertices(1, .2, 16, 8),
];
// merge all the vertices into one
const arrays = twgl.primitives.concatVertices(modelVerts);
// fill an array so each vertex of each model has a modelId
const modelIds = new Uint16Array(arrays.position.length / 3);
let offset = 0;
modelVerts.forEach((verts, modelId) => {
const end = offset + verts.position.length / 3;
while(offset < end) {
modelIds[offset++] = modelId;
}
});
arrays.modelId = { numComponents: 1, data: modelIds };
// calls gl.createBuffer, gl.bindBuffer, gl.bufferData
const bufferInfo = twgl.createBufferInfoFromArrays(gl, arrays);
const numModels = modelVerts.length;
const tex = gl.createTexture();
const textureWidth = 5; // 4x4 matrix, 4x1 color
gl.bindTexture(gl.TEXTURE_2D, tex);
gl.texImage2D(gl.TEXTURE_2D, 0, gl.RGBA, textureWidth, numModels, 0, gl.RGBA, gl.FLOAT, null);
gl.texParameteri(gl.TEXTURE_2D, gl.TEXTURE_MIN_FILTER, gl.NEAREST);
gl.texParameteri(gl.TEXTURE_2D, gl.TEXTURE_MAG_FILTER, gl.NEAREST);
gl.texParameteri(gl.TEXTURE_2D, gl.TEXTURE_WRAP_S, gl.CLAMP_TO_EDGE);
gl.texParameteri(gl.TEXTURE_2D, gl.TEXTURE_WRAP_T, gl.CLAMP_TO_EDGE);
// this data is for the texture, one row per model
// first 4 pixels are the model matrix, 5 pixel is the color
const perModelData = new Float32Array(textureWidth * numModels * 4);
const stride = textureWidth * 4;
const modelOffset = 0;
const colorOffset = 16;
// set the colors at init time
for (let modelId = 0; modelId < numModels; ++modelId) {
perModelData.set([r(), r(), r(), 1], modelId * stride + colorOffset);
}
function r() {
return Math.random();
}
function render(time) {
time *= 0.001; // seconds
twgl.resizeCanvasToDisplaySize(gl.canvas);
gl.viewport(0, 0, gl.canvas.width, gl.canvas.height);
gl.enable(gl.DEPTH_TEST);
gl.enable(gl.CULL_FACE);
const fov = Math.PI * 0.25;
const aspect = gl.canvas.clientWidth / gl.canvas.clientHeight;
const near = 0.1;
const far = 20;
const projection = m4.perspective(fov, aspect, near, far);
const eye = [0, 0, 10];
const target = [0, 0, 0];
const up = [0, 1, 0];
const camera = m4.lookAt(eye, target, up);
const view = m4.inverse(camera);
// set the matrix for each model in the texture data
const mat = m4.identity();
for (let modelId = 0; modelId < numModels; ++modelId) {
const t = time * (modelId + 1) * 0.3;
m4.identity(mat);
m4.rotateX(mat, t, mat);
m4.rotateY(mat, t, mat);
m4.translate(mat, [0, 0, Math.sin(t * 1.1) * 4], mat);
m4.rotateZ(mat, t, mat);
perModelData.set(mat, modelId * stride + modelOffset);
}
// upload the texture data
gl.bindTexture(gl.TEXTURE_2D, tex);
gl.texSubImage2D(gl.TEXTURE_2D, 0, 0, 0, textureWidth, numModels,
gl.RGBA, gl.FLOAT, perModelData);
gl.useProgram(programInfo.program);
// calls gl.bindBuffer, gl.enableVertexAttribArray, gl.vertexAttribPointer
twgl.setBuffersAndAttributes(gl, programInfo, bufferInfo);
// calls gl.activeTexture, gl.bindTexture, gl.uniformXXX
twgl.setUniforms(programInfo, {
lightDirection: v3.normalize([1, 2, 3]),
perModelDataTexture: tex,
textureHeight: numModels,
projection,
view,
});
// calls gl.drawArrays or gl.drawElements
twgl.drawBufferInfo(gl, bufferInfo);
requestAnimationFrame(render);
}
requestAnimationFrame(render);
body { margin: 0; }
canvas { width: 100vw; height: 100vh; display: block; }
<script src="https://twgljs.org/dist/4.x/twgl-full.min.js"></script>
<canvas></canvas>
Here's 2000 models in one draw call
https://jsfiddle.net/greggman/g2tcadho/

Generating Vertices in OpenGL ES 2.0 Vertex Shader

I am trying to draw a triangle with three vertices a,b,c. Typically, i would have these three vertex co-ordinates in an array and pass it as an attribute to my vertex shader.
But , is it possible to generate these vertex co-ordinates within the vertex shader itself rather than passing as an attribute (i.e. per vertex co-ordinate value for corresponding vertex position). If yes, any sample program to support it ?
Thanks.
You can create variables in vertex shader and pass it to fragment shader. An example:
Vertex shader
precision highp float;
uniform float u_time;
uniform float u_textureSize;
uniform mat4 u_mvpMatrix;
attribute vec4 a_position;
// This will be passed into the fragment shader.
varying vec2 v_textureCoordinate0;
void main()
{
// Create texture coordinate
v_textureCoordinate0 = a_position.xy / u_textureSize;
gl_Position = u_mvpMatrix * a_position;
}
And the fragment shader:
precision mediump float;
uniform float u_time;
uniform float u_pixel_amount;
uniform sampler2D u_texture0;
// Interpolated texture coordinate per fragment.
varying vec2 v_textureCoordinate0;
void main(void)
{
vec2 size = vec2( 1.0 / u_pixel_amount, 1.0 / u_pixel_amount);
vec2 uv = v_textureCoordinate0 - mod(v_textureCoordinate0,size);
gl_FragColor = texture2D( u_texture0, uv );
gl_FragColor.a=1.0;
}
How you can see, vector 2D named v_textureCoordinate0 is created in vertex shader and its interpolated value is used in fragment shader.
I hope it help you.

Calculate ray direction vector from screen coordanate

I'm looking for a better way (or a note that this is the best way) to transfer a pixel coordinate to its corresponding ray direction from a arbitrary camera position/direction.
My current method is as follows. I define a "camera" as a position vector, lookat vector, and up vector, named as such. (Note that the lookat vector is a unit vector in the direction the camera is facing, NOT where (position - lookat) is the direction, as is the standard in XNA's Matrix.CreateLookAt) These three vectors can uniquely define a camera position. Here's the actual code (well, not really the actual, a simplified abstracted version) (Language is HLSL)
float xPixelCoordShifted = (xPixelCoord / screenWidth * 2 - 1) * aspectRatio;
float yPixelCoordShifted = yPixelCoord / screenHeight * 2 - 1;
float3 right = cross(lookat, up);
float3 actualUp = cross(right, lookat);
float3 rightShift = mul(right, xPixelCoordShifted);
float3 upShift = mul(actualUp, yPixelCoordShifted);
return normalize(lookat + rightShift + upShift);
(the return value is the direction of the ray)
So what I'm asking is this- What's a better way to do this, maybe using matrices, etc. The problem with this method is that if you have too wide a viewing angle, the edges of the screen get sort of "radially stretched".
You can calculate it (ray) in pixel shader, HLSL code:
float4x4 WorldViewProjMatrix; // World*View*Proj
float4x4 WorldViewProjMatrixInv; // (World*View*Proj)^(-1)
void VS( float4 vPos : POSITION,
out float4 oPos : POSITION,
out float4 pos : TEXCOORD0 )
{
oPos = mul(vPos, WorldViewProjMatrix);
pos = oPos;
}
float4 PS( float4 pos : TEXCOORD0 )
{
float4 posWS = mul(pos, WorldViewProjMatrixInv);
float3 ray = posWS.xyz / posWS.w;
return float4(0, 0, 0, 1);
}
The information about your camera's position and direction is in View matrix (Matrix.CreateLookAt).