gputex 0.3.4 → 0.5.0

package/dist/index.d.ts

@@ -6,6 +6,8 @@ declare const TextureFormat: {
     readonly BC7_SRGB: "BC7_SRGB";
     readonly ASTC_4x4: "ASTC_4x4";
     readonly ASTC_4x4_SRGB: "ASTC_4x4_SRGB";
+    readonly ETC2_RGB8: "ETC2_RGB8";
+    readonly ETC2_RGB8_SRGB: "ETC2_RGB8_SRGB";
 };
 type TextureFormat = (typeof TextureFormat)[keyof typeof TextureFormat];
 declare const WebGPUFeature: {
@@ -33,6 +35,31 @@ interface Capabilities {
 }
 declare function detectCapabilities(adapter: FeatureProvider): Capabilities;
 
+/** One level of a mip chain. 4 bytes per pixel (RGBA8). */
+interface MipLevel {
+    data: Uint8ClampedArray;
+    width: number;
+    height: number;
+}
+/**
+ * Produce the full mip chain from a level-0 image. The chain goes down
+ * to a 1×1 level — the standard OpenGL / WebGPU convention — so the
+ * caller gets `floor(log2(max(w, h))) + 1` levels total.
+ *
+ * Levels whose logical dimensions are below the encoder's 4×4 block
+ * grid are still produced here at their true logical size; padding up
+ * to a single block is the encoder's job, not ours.
+ */
+declare function generateMipChain(level0: MipLevel): MipLevel[];
+/**
+ * Pad a mip level up to a multiple of 4 in each dimension using clamp-
+ * to-edge sampling. Used before handing sub-4×4 levels to a block-
+ * compression encoder, which requires at least one full block per level.
+ *
+ * If the input is already block-aligned this returns the input unchanged.
+ */
+declare function padToBlockMultiple(level: MipLevel): MipLevel;
+
 /**
  * Anything `GPUQueue.copyExternalImageToTexture` accepts. Matches the
  * WebGPU spec's CopyExternalImageSource set.
@@ -49,32 +76,26 @@ interface EncoderOptions {
      */
     disableF16?: boolean;
 }
-/**
- * Encoder quality level. 'fast' (default) uses the projection-based paths in
- * the shaders — an order of magnitude faster for a ≤0.65 dB PSNR cost. 'high'
- * runs the exhaustive search, matching the CPU reference encoders
- * block-for-block (byte-identical up to FP tie-breaks with equal error).
- * BC1's 'high' adds a principal-axis endpoint seed and iterative refit.
- */
-type EncodeQuality = 'fast' | 'high';
 interface EncodeCallOptions {
     /** Tags the output color space. Forced 'linear' for encoders with supportsSrgb=false. */
     colorSpace?: 'srgb' | 'linear';
-    /** Encode quality / speed trade-off. Default 'fast'. */
-    quality?: EncodeQuality;
 }
 /**
- * Result of a raw bytes-only encode. This is the encoder's native output: the
- * compressed block bytes plus dimensions, with no Three.js (or any engine)
- * involvement. Feed `data` into whatever renderer's compressed-texture upload
- * you like, or use `buildCompressedTexture()` from `gputex/three`.
+ * One level of encoded output: the compressed block bytes plus logical and
+ * block-aligned dimensions. This is the encoder's native output shape, with
+ * no Three.js (or any engine) involvement — feed `data` into whatever
+ * renderer's compressed-texture upload you like, or use
+ * `buildCompressedTexture()` from `gputex/three`.
  */
-interface EncodeBytesResult {
+interface EncodedLevelBytes {
     width: number;
     height: number;
     paddedWidth: number;
     paddedHeight: number;
     data: Uint8Array;
+}
+/** Result of a raw bytes-only single-image encode. */
+interface EncodeBytesResult extends EncodedLevelBytes {
     encodeMs: number;
     /**
      * GPU-side compute-pass time in ms, measured with timestamp queries.
@@ -85,6 +106,16 @@ interface EncodeBytesResult {
      */
     gpuMs?: number;
 }
+/** Result of a whole-chain encode — see `Encoder.encodeMipChainToBytes()`. */
+interface EncodeMipChainResult {
+    /** Encoded levels in the order given; `levels[0]` is the base level. */
+    levels: EncodedLevelBytes[];
+    /** Wall-clock time for the whole chain: uploads → dispatches → readback. */
+    encodeMs: number;
+    /** GPU compute time for the whole chain's single compute pass (see
+     *  `EncodeBytesResult.gpuMs` for caveats). */
+    gpuMs?: number;
+}
 interface FormatVariant {
     colorSpace: 'srgb' | 'linear';
 }
@@ -126,55 +157,87 @@ declare abstract class Encoder {
     readonly adapter?: GPUAdapter;
     readonly ownsDevice: boolean;
     readonly disableF16: boolean;
-    protected _module: GPUShaderModule | null;
-    protected _moduleF16: GPUShaderModule | null;
-    protected _pipelineF16: GPUComputePipeline | null;
-    protected _pipeline: GPUComputePipeline;
-    protected _pipelineCache: Map<EncodeQuality, GPUComputePipeline>;
+    protected _pipelineReady: Promise<GPUComputePipeline>;
+    protected _prepPipelineReady: Promise<GPUComputePipeline> | null;
     private _cachedSrcTex;
     private _cachedSrcW;
     private _cachedSrcH;
+    private _cachedSrcSource;
+    private _cachedSrcFlipY;
     private _cachedDst;
     private _cachedStaging;
     private _cachedParams;
     private _lastParams;
-    private _bindGroupCache;
+    private _cachedBindGroup;
+    private _cachedPrepPlanes;
+    private _cachedPrepBindGroup;
     private _resourcesBusy;
+    /** Set when the active shader declares a @binding(3) sampler (the BC5
+     * kernels read texels through textureGather + clamp-to-edge). */
+    private _usesSampler;
+    private _sampler;
+    private _chainSig;
+    private _chainTextures;
+    private _chainPrepPlanes;
+    private _chainPrepBindGroups;
+    private _chainParams;
+    private _chainBindGroups;
+    private _chainDst;
+    private _chainStaging;
+    private _chainBusy;
     constructor({ device, adapter, ownsDevice, disableF16 }: EncoderOptions);
     protected _buildPipeline(): void;
-    /** The f32 module, parsed on first use (see `_module`). */
-    protected _ensureModule(): GPUShaderModule;
-    /**
-     * Pipeline for a given quality level. Encoders that don't declare a
-     * `QUALITY_HIGH` override (`supportsQuality === false`, e.g. BC1) ignore the
-     * argument and reuse the single pipeline. Specialised pipelines are cached.
-     */
-    protected _getPipeline(quality: EncodeQuality): GPUComputePipeline;
     destroy(): void;
     /** Short lowercase identifier used in GPU object labels and errors. */
     abstract get label(): string;
     /** 8 for BC1/BC4, 16 for BC5/BC7/ASTC 4×4. */
     abstract get bytesPerBlock(): number;
+    /**
+     * Pipeline-creation override constants for the active shader, or
+     * undefined for none. Subclasses expose quality/behaviour toggles this
+     * way so the OFF state is dead-coded by the shader compiler instead of
+     * branched at runtime.
+     */
+    protected pipelineConstants(): Record<string, number> | undefined;
     /** WGSL `@workgroup_size` dimensions. Default 8×8×1. */
     get workgroupSize(): readonly [number, number, number];
     /** Whether this format has an sRGB variant. Default true. */
     get supportsSrgb(): boolean;
     /**
-     * Whether the shader declares a `QUALITY_HIGH` pipeline-overridable constant
-     * (i.e. has distinct fast/high search paths). Default false (e.g. a stub or a
-     * format with a single path); BC1/BC5/BC7/ASTC override it to true.
+     * Format of the single-shot source texture the encode pass samples.
+     * Encoders that read only a channel subset can narrow it to cut DRAM
+     * traffic on the bandwidth-bound compute pass (BC5 reads rg8unorm — half
+     * the bytes of rgba8). Must be valid as a copyExternalImageToTexture
+     * destination and renderable. Chain encodes keep rgba8unorm regardless
+     * (their inputs are RGBA mip levels / texture views); the WGSL is
+     * format-agnostic (`texture_2d<f32>`), so mixing is byte-identical.
      */
-    get supportsQuality(): boolean;
+    protected get srcTextureFormat(): GPUTextureFormat;
     /**
-     * Optional f16 WGSL for the 'fast' path. Used only when the device reports the
-     * `shader-f16` feature; the format's f32 `wgslSource()` is the fallback and
-     * `'high'` always uses it. Returns null when there's no f16 variant.
+     * Optional f16 WGSL variant. Used only when the device reports the
+     * `shader-f16` feature; the format's f32 `wgslSource()` is the automatic
+     * fallback. Returns null when there's no f16 variant.
      */
     wgslSourceFastF16(): string | null;
-    /** Whether the f16 fast path is both available and supported on this device. */
+    /** Whether the f16 shader is both available and supported on this device. */
     protected get _useF16(): boolean;
-    /** WGSL compute-shader source. */
+    /** WGSL compute-shader source (f32; the fallback when f16 is unavailable). */
     abstract wgslSource(): string;
+    /** WGSL for the preparation pass, or null when the encoder reads the
+     *  RGBA8 source directly. */
+    protected wgslPrepSource(): string | null;
+    /** Formats and sizes of the prepared planes for a padded source size. */
+    protected prepPlanes(paddedWidth: number, paddedHeight: number): {
+        format: GPUTextureFormat;
+        width: number;
+        height: number;
+    }[];
+    /** Workgroup counts for the prep dispatch. */
+    protected prepDispatch(blocksX: number, blocksY: number): [number, number];
+    /** Create the prepared-plane textures for one padded source size. */
+    private _createPrepPlanes;
+    /** Bind group for one prep dispatch. */
+    private _createPrepBindGroup;
     /** e.g. 'bc1-rgba-unorm-srgb'. */
     abstract gpuTextureFormat(opts: FormatVariant): GPUTextureFormat;
     /**
@@ -190,11 +253,59 @@ declare abstract class Encoder {
      * bytes into a `CompressedTexture`; callers targeting another engine feed
      * `data` into that engine's compressed-texture upload directly.
      */
-    encodeToBytes(source: EncoderImageSource, { flipY, quality, withGpuTime, }?: {
+    encodeToBytes(source: EncoderImageSource, { flipY, withGpuTime }?: {
         flipY?: boolean;
-        quality?: EncodeQuality;
         withGpuTime?: boolean;
     }): Promise<EncodeBytesResult>;
+    /**
+     * Encode a whole mip chain in ONE GPU submission. A per-level
+     * `encodeToBytes()` loop costs a full CPU↔GPU round trip per level (a
+     * 1024² chain is 11 levels → 11 `mapAsync` waits with the GPU idle in
+     * between); this path uploads every level, records one dispatch per level
+     * into a single compute pass, copies all outputs into one staging buffer
+     * and maps it once.
+     *
+     * `levels` are raw RGBA8 pixels in base-to-tail order; sizes don't have to
+     * halve level-to-level (each level is padded and clamped independently,
+     * exactly like `encodeToBytes`). Uploads use `writeTexture` — the direct
+     * raw-bytes path, which also sidesteps the broken
+     * `copyExternalImageToTexture` devices (see workarounds.ts). There is no
+     * flip option: bake any vertical flip into level 0 before generating the
+     * chain, as `compressTexture()` does.
+     */
+    encodeMipChainToBytes(levels: readonly MipLevel[], { withGpuTime }?: {
+        withGpuTime?: boolean;
+    }): Promise<EncodeMipChainResult>;
+    /**
+     * Encode every mip level of a GPU-resident texture in one submission —
+     * the zero-CPU-pixels counterpart of `encodeMipChainToBytes()`. Pair it
+     * with `generateGpuMipChain()` (gpuMipgen.ts): upload the image once,
+     * box-filter the chain on the GPU, then encode straight from the
+     * texture's mip views. Pixels never transit the CPU between the source
+     * image and the compressed-bytes readback.
+     *
+     * `srcTex` must be `rgba8unorm` with TEXTURE_BINDING usage; level 0's
+     * dimensions are taken from the texture and lower levels follow the
+     * standard floor-halving chain. Encoded output is identical to feeding
+     * the equivalent CPU chain to `encodeMipChainToBytes()`.
+     */
+    encodeMipChainFromTexture(srcTex: GPUTexture, { withGpuTime }?: {
+        withGpuTime?: boolean;
+    }): Promise<EncodeMipChainResult>;
+    /** Block-grid geometry + packed output offsets for a chain of levels.
+     *  `byteSpan` is both the dst buffer size and the readback copy size (a
+     *  multiple of 4: byteLen is a multiple of bytesPerBlock ≥ 8, offsets are
+     *  CHAIN_ALIGN-ed). */
+    private _chainGeometry;
+    /** Shared chain-encode tail: one compute pass with a dispatch per level,
+     *  one submit, one staging readback sliced into per-level byte arrays. */
+    private _submitChainAndRead;
+    /** Create the query set + resolve/staging buffers for one timed
+     *  submission, or null when the device lacks 'timestamp-query'. */
+    private _createTiming;
+    /** Read back a timed submission's pass duration (ms) and destroy the
+     *  timing objects. Timestamps are u64 nanoseconds. */
+    private _readTimingMs;
 }
 
 declare class BC1Encoder extends Encoder {
@@ -203,7 +314,6 @@ declare class BC1Encoder extends Encoder {
     get label(): string;
     get bytesPerBlock(): number;
     get supportsSrgb(): boolean;
-    get supportsQuality(): boolean;
     wgslSource(): string;
     wgslSourceFastF16(): string | null;
     gpuTextureFormat({ colorSpace }: FormatVariant): GPUTextureFormat;
@@ -215,19 +325,29 @@ declare class BC5Encoder extends Encoder {
     get label(): string;
     get bytesPerBlock(): number;
     get supportsSrgb(): boolean;
-    get supportsQuality(): boolean;
+    protected get srcTextureFormat(): GPUTextureFormat;
     wgslSource(): string;
     wgslSourceFastF16(): string;
     gpuTextureFormat(): GPUTextureFormat;
 }
 
+interface BC7EncoderOptions extends EncoderOptions {
+    /**
+     * Emit BC7 mode 4 on decorrelated blocks (normal maps, channel-packed
+     * atlases): a large quality win there, at up to ~1.5× encode time on
+     * exactly that content. See the header note for the measurements.
+     */
+    adaptiveMode4?: boolean;
+}
 declare class BC7Encoder extends Encoder {
     static readonly requiredFeature: GPUFeatureName;
     static readonly textureFormats: readonly TextureFormat[];
+    private readonly adaptiveMode4;
+    constructor(opts: BC7EncoderOptions);
+    protected pipelineConstants(): Record<string, number> | undefined;
     get label(): string;
     get bytesPerBlock(): number;
     get supportsSrgb(): boolean;
-    get supportsQuality(): boolean;
     wgslSource(): string;
     wgslSourceFastF16(): string;
     gpuTextureFormat({ colorSpace }: FormatVariant): GPUTextureFormat;
@@ -239,7 +359,17 @@ declare class ASTC4x4Encoder extends Encoder {
     get label(): string;
     get bytesPerBlock(): number;
     get supportsSrgb(): boolean;
-    get supportsQuality(): boolean;
+    wgslSource(): string;
+    wgslSourceFastF16(): string;
+    gpuTextureFormat({ colorSpace }: FormatVariant): GPUTextureFormat;
+}
+
+declare class ETC2Encoder extends Encoder {
+    static readonly requiredFeature: GPUFeatureName;
+    static readonly textureFormats: readonly TextureFormat[];
+    get label(): string;
+    get bytesPerBlock(): number;
+    get supportsSrgb(): boolean;
     wgslSource(): string;
     wgslSourceFastF16(): string;
     gpuTextureFormat({ colorSpace }: FormatVariant): GPUTextureFormat;
@@ -391,16 +521,26 @@ type TextureHint = 'color' | 'colorWithAlpha' | 'normal';
 /**
  * Optional format preference — a wish, not a demand. Applied when the
  * device supports the format and the hint is compatible; otherwise
- * selection proceeds normally (BC7 → ASTC → null). Currently only
+ * selection proceeds normally (BC7 → ASTC → ETC2 → null). Currently only
  * 'bc1': half the memory of BC7 (0.5 vs 1 byte/pixel) for opaque
  * colour, at visibly lower quality on smooth content.
  */
 type PreferredFormat = 'bc1';
+/**
+ * Memory/fidelity trade-off for opaque colour textures. 'high' (default)
+ * picks the 8-bpp formats (BC7 / ASTC 4×4); 'low' picks the 4-bpp ones
+ * (BC1 / ETC2 RGB8) when the adapter supports one. Hints that the 4-bpp
+ * formats can't carry ('colorWithAlpha', 'normal') ignore this and keep
+ * the 'high' selection.
+ */
+type FormatQuality = 'high' | 'low';
 interface SelectFormatOptions {
     /** Pick the sRGB variant when the format has one. Default 'srgb'. */
     colorSpace?: 'srgb' | 'linear';
     /** Prefer a specific format when supported. See `PreferredFormat`. */
     preferredFormat?: PreferredFormat;
+    /** Memory/fidelity trade-off. See `FormatQuality`. Default 'high'. */
+    quality?: FormatQuality;
 }
 interface FormatSelection {
     /** null = no compressed path on this adapter; caller should fall back. */
@@ -426,30 +566,21 @@ interface WebGLFormatSelection {
 }
 declare function selectWebGLFormat(caps: WebGLCapabilities, hint: TextureHint, options?: SelectFormatOptions): WebGLFormatSelection;
 
-/** One level of a mip chain. 4 bytes per pixel (RGBA8). */
-interface MipLevel {
-    data: Uint8ClampedArray;
-    width: number;
-    height: number;
-}
+/** Matches mipgen's chain length: floor(log2(max(w, h))) + 1 levels. */
+declare function gpuMipLevelCount(width: number, height: number): number;
 /**
- * Produce the full mip chain from a level-0 image. The chain goes down
- * to a 1×1 level — the standard OpenGL / WebGPU convention — so the
- * caller gets `floor(log2(max(w, h))) + 1` levels total.
+ * Upload `source` and generate its full mip chain on the GPU. Returns an
+ * `rgba8unorm` texture with `gpuMipLevelCount` levels whose dimensions
+ * follow the standard floor-halving chain; feed it to
+ * `Encoder.encodeMipChainFromTexture()`. The caller owns the texture —
+ * destroy it after encoding.
  *
- * Levels whose logical dimensions are below the encoder's 4×4 block
- * grid are still produced here at their true logical size; padding up
- * to a single block is the encoder's job, not ours.
+ * The returned promise resolves once the work is submitted (not completed);
+ * queue ordering makes the levels visible to any later submission.
  */
-declare function generateMipChain(level0: MipLevel): MipLevel[];
-/**
- * Pad a mip level up to a multiple of 4 in each dimension using clamp-
- * to-edge sampling. Used before handing sub-4×4 levels to a block-
- * compression encoder, which requires at least one full block per level.
- *
- * If the input is already block-aligned this returns the input unchanged.
- */
-declare function padToBlockMultiple(level: MipLevel): MipLevel;
+declare function generateGpuMipChain(device: GPUDevice, source: ImageBitmap | ImageData | HTMLCanvasElement | OffscreenCanvas, { flipY }?: {
+    flipY?: boolean;
+}): Promise<GPUTexture>;
 
 /**
  * Target raster size for an SVG source. A number scales the SVG so its
@@ -474,4 +605,4 @@ interface RasterizeSvgOptions {
  */
 declare function rasterizeSvg(source: string | Blob, options?: RasterizeSvgOptions): Promise<ImageBitmap>;
 
-export { ASTC4x4Encoder, ASTC4x4WebGLEncoder, BC1Encoder, BC1WebGLEncoder, BC5Encoder, BC5WebGLEncoder, BC7Encoder, BC7WebGLEncoder, type Capabilities, type EncodeBytesResult, type EncodeCallOptions, type EncodeQuality, Encoder, type EncoderConstructor, type EncoderImageSource, type EncoderOptions, type ExtensionProvider, type FeatureProvider, type FormatSelection, type FormatVariant, type MipLevel, type PreferredFormat, type RasterizeSvgOptions, type RawPixelSource, type SelectFormatOptions, type SvgRasterSize, TextureFormat, type TextureHint, WebGLBlockEncoder, type WebGLCapabilities, type WebGLEncodeBytesResult, type WebGLEncoderConstructor, type WebGLEncoderImageSource, type WebGLEncoderOptions, type WebGLFormatSelection, WebGPUFeature, createWebGLContext, detectCapabilities, detectWebGLCapabilities, generateMipChain, getSharedWebGLContext, isWebGLAvailable, padToBlockMultiple, rasterizeSvg, selectFormat, selectWebGLFormat };
+export { ASTC4x4Encoder, ASTC4x4WebGLEncoder, BC1Encoder, BC1WebGLEncoder, BC5Encoder, BC5WebGLEncoder, BC7Encoder, type BC7EncoderOptions, BC7WebGLEncoder, type Capabilities, ETC2Encoder, type EncodeBytesResult, type EncodeCallOptions, type EncodeMipChainResult, type EncodedLevelBytes, Encoder, type EncoderConstructor, type EncoderImageSource, type EncoderOptions, type ExtensionProvider, type FeatureProvider, type FormatQuality, type FormatSelection, type FormatVariant, type MipLevel, type PreferredFormat, type RasterizeSvgOptions, type RawPixelSource, type SelectFormatOptions, type SvgRasterSize, TextureFormat, type TextureHint, WebGLBlockEncoder, type WebGLCapabilities, type WebGLEncodeBytesResult, type WebGLEncoderConstructor, type WebGLEncoderImageSource, type WebGLEncoderOptions, type WebGLFormatSelection, WebGPUFeature, createWebGLContext, detectCapabilities, detectWebGLCapabilities, generateGpuMipChain, generateMipChain, getSharedWebGLContext, gpuMipLevelCount, isWebGLAvailable, padToBlockMultiple, rasterizeSvg, selectFormat, selectWebGLFormat };