Initial clustered lights implementation (tiled clustering only)

packages/dev/core/src/Buffers/storageBuffer.ts

@@ -46,6 +46,10 @@ export class StorageBuffer {
         return this._buffer;
     }
 
+    public clear(byteOffset?: number, byteLength?: number): void {
+        this._engine.clearStorageBuffer(this._buffer, byteOffset, byteLength);
+    }
+
     /**
      * Updates the storage buffer
      * @param data the data used to update the storage buffer

packages/dev/core/src/Engines/WebGPU/webgpuShaderProcessorsWGSL.ts

@@ -335,7 +335,8 @@ export class WebGPUShaderProcessorWGSL extends WebGPUShaderProcessor {
     }
 
     public finalizeShaders(vertexCode: string, fragmentCode: string): { vertexCode: string; fragmentCode: string } {
-        const enabledExtensions: string[] = [];
+        // TODO: conditionally enable if needed AND supported
+        const enabledExtensions: string[] = ["subgroups"];
 
         const fragCoordCode =
             fragmentCode.indexOf("fragmentInputs.position") >= 0 && !this.pureMode

packages/dev/core/src/Engines/engineCapabilities.ts

@@ -27,6 +27,8 @@ export interface EngineCapabilities {
     maxVertexUniformVectors: number;
     /** Maximum number of uniforms per fragment shader */
     maxFragmentUniformVectors: number;
+    /** The number of bits that can be accurately represented in shader floats */
+    shaderFloatPrecision: number;
     /** Defines if standard derivatives (dx/dy) are supported */
     standardDerivatives: boolean;
     /** Defines if s3tc texture compression is supported */
@@ -80,6 +82,8 @@ export interface EngineCapabilities {
     depthTextureExtension: boolean;
     /** Defines if float color buffer are supported */
     colorBufferFloat: boolean;
+    /** Defines if float color blending is supported */
+    blendFloat: boolean;
     /** Defines if half float color buffer are supported */
     colorBufferHalfFloat?: boolean;
     /** Gets disjoint timer query extension (null if not supported) */

packages/dev/core/src/Engines/nativeEngine.ts

@@ -286,6 +286,7 @@ export class NativeEngine extends Engine {
             maxDrawBuffers: 8,
             maxFragmentUniformVectors: 16,
             maxVertexUniformVectors: 16,
+            shaderFloatPrecision: 23, // TODO: is this correct?
             standardDerivatives: true,
             astc: null,
             pvrtc: null,
@@ -297,6 +298,7 @@ export class NativeEngine extends Engine {
             fragmentDepthSupported: false,
             highPrecisionShaderSupported: true,
             colorBufferFloat: false,
+            blendFloat: false,
             supportFloatTexturesResolve: false,
             rg11b10ufColorRenderable: false,
             textureFloat: true,

packages/dev/core/src/Engines/nullEngine.ts

@@ -133,6 +133,7 @@ export class NullEngine extends Engine {
             maxVaryingVectors: 16,
             maxFragmentUniformVectors: 16,
             maxVertexUniformVectors: 16,
+            shaderFloatPrecision: 10, // Minimum precision for mediump floats WebGL 1
             standardDerivatives: false,
             astc: null,
             pvrtc: null,
@@ -144,6 +145,7 @@ export class NullEngine extends Engine {
             fragmentDepthSupported: false,
             highPrecisionShaderSupported: true,
             colorBufferFloat: false,
+            blendFloat: false,
             supportFloatTexturesResolve: false,
             rg11b10ufColorRenderable: false,
             textureFloat: false,

packages/dev/core/src/Engines/thinEngine.ts

@@ -506,6 +506,7 @@ export class ThinEngine extends AbstractEngine {
             maxVaryingVectors: this._gl.getParameter(this._gl.MAX_VARYING_VECTORS),
             maxFragmentUniformVectors: this._gl.getParameter(this._gl.MAX_FRAGMENT_UNIFORM_VECTORS),
             maxVertexUniformVectors: this._gl.getParameter(this._gl.MAX_VERTEX_UNIFORM_VECTORS),
+            shaderFloatPrecision: 0,
             parallelShaderCompile: this._gl.getExtension("KHR_parallel_shader_compile") || undefined,
             standardDerivatives: this._webGLVersion > 1 || this._gl.getExtension("OES_standard_derivatives") !== null,
             maxAnisotropy: 1,
@@ -533,6 +534,7 @@ export class ThinEngine extends AbstractEngine {
             drawBuffersExtension: false,
             maxMSAASamples: 1,
             colorBufferFloat: !!(this._webGLVersion > 1 && this._gl.getExtension("EXT_color_buffer_float")),
+            blendFloat: this._gl.getExtension("EXT_float_blend") !== null,
             supportFloatTexturesResolve: false,
             rg11b10ufColorRenderable: false,
             colorBufferHalfFloat: !!(this._webGLVersion > 1 && this._gl.getExtension("EXT_color_buffer_half_float")),
@@ -734,6 +736,19 @@ export class ThinEngine extends AbstractEngine {
 
             if (vertexhighp && fragmenthighp) {
                 this._caps.highPrecisionShaderSupported = vertexhighp.precision !== 0 && fragmenthighp.precision !== 0;
+                this._caps.shaderFloatPrecision = Math.min(vertexhighp.precision, fragmenthighp.precision);
+            }
+            // This will check both the capability and the `useHighPrecisionFloats` option
+            if (!this._shouldUseHighPrecisionShader) {
+                const vertexmedp = this._gl.getShaderPrecisionFormat(this._gl.VERTEX_SHADER, this._gl.MEDIUM_FLOAT);
+                const fragmentmedp = this._gl.getShaderPrecisionFormat(this._gl.FRAGMENT_SHADER, this._gl.MEDIUM_FLOAT);
+                if (vertexmedp && fragmentmedp) {
+                    this._caps.shaderFloatPrecision = Math.min(vertexmedp.precision, fragmentmedp.precision);
+                }
+            }
+            if (this._caps.shaderFloatPrecision < 10) {
+                // WebGL spec requires mediump precision to atleast be 10
+                this._caps.shaderFloatPrecision = 10;
             }
         }
 

packages/dev/core/src/Engines/webgpuEngine.ts

@@ -857,6 +857,7 @@ export class WebGPUEngine extends ThinWebGPUEngine {
             maxVaryingVectors: this._deviceLimits.maxInterStageShaderVariables,
             maxFragmentUniformVectors: Math.floor(this._deviceLimits.maxUniformBufferBindingSize / 4),
             maxVertexUniformVectors: Math.floor(this._deviceLimits.maxUniformBufferBindingSize / 4),
+            shaderFloatPrecision: 23, // WGSL always uses IEEE-754 binary32 floats (which have 23 bits of significand)
             standardDerivatives: true,
             astc: (this._deviceEnabledExtensions.indexOf(WebGPUConstants.FeatureName.TextureCompressionASTC) >= 0 ? true : undefined) as any,
             s3tc: (this._deviceEnabledExtensions.indexOf(WebGPUConstants.FeatureName.TextureCompressionBC) >= 0 ? true : undefined) as any,
@@ -869,6 +870,7 @@ export class WebGPUEngine extends ThinWebGPUEngine {
             fragmentDepthSupported: true,
             highPrecisionShaderSupported: true,
             colorBufferFloat: true,
+            blendFloat: this._deviceEnabledExtensions.indexOf(WebGPUConstants.FeatureName.Float32Blendable) >= 0,
             supportFloatTexturesResolve: false, // See https://github.com/gpuweb/gpuweb/issues/3844
             rg11b10ufColorRenderable: this._deviceEnabledExtensions.indexOf(WebGPUConstants.FeatureName.RG11B10UFloatRenderable) >= 0,
             textureFloat: true,
@@ -3901,6 +3903,10 @@ export class WebGPUEngine extends ThinWebGPUEngine {
         return this._createBuffer(data, creationFlags | Constants.BUFFER_CREATIONFLAG_STORAGE, label);
     }
 
+    public clearStorageBuffer(storageBuffer: DataBuffer, byteOffset?: number, byteLength?: number): void {
+        this._renderEncoder.clearBuffer(storageBuffer.underlyingResource, byteOffset, byteLength);
+    }
+
     /**
      * Updates a storage buffer
      * @param buffer the storage buffer to update