diff options
| -rw-r--r-- | README.md | 11 | ||||
| -rw-r--r-- | docs/pardes-rendering.md | 253 | ||||
| -rw-r--r-- | src/abi.zig | 8 | ||||
| -rw-r--r-- | src/gpu/Executor.zig | 41 | ||||
| -rw-r--r-- | src/gpu/scene.zig | 55 | ||||
| -rw-r--r-- | src/host/Host.zig | 10 | ||||
| -rw-r--r-- | src/sketch/clock.zig | 2 | ||||
| -rw-r--r-- | src/sketch/root.zig | 27 | ||||
| -rw-r--r-- | src/sketch/web.zig | 5 | ||||
| -rw-r--r-- | web/host.js | 53 |
10 files changed, 443 insertions, 22 deletions
@@ -1170,6 +1170,17 @@ released by the host on session reset; call `model.release(host)` to release the earlier. Vertex storage layout and shader uniform layout are checked at comptime; GLSL uniform declarations are generated from the Zig types. +A separate fullscreen pass can sample a completed render with +`f.postProcess(source, target, .{ .vertex = vertex_shader, .fragment = fragment_shader, +.sample_depth = true, .fragment_uniforms = uniforms })`. Allocate distinct source +and target images in setup, then draw the target image after this command. +Native fragment bindings are color at 0 and depth at 1 (set 2). Web GLSL uses +separate texture/sampler pairs at 0/1 and 2/3 (set 2). Fragment uniforms use set 3, +binding 0. Depth sampling requires the source's latest pass to have `.depth = true` +and `.samples = 1`; missing depth, multisampled depth and feedback loops are +rejected. Omit `sample_depth` for a color-only pass. Native profiling reports this +work separately as `postprocess`. + `profile` also includes `p95_ms` and `p99_ms`: nearest-rank percentiles of the latest 2048 measured commands per label. Mean and worst cover every command since reset. `profile-trace` exposes those retained samples as CSV (`label,sample,ns`), diff --git a/docs/pardes-rendering.md b/docs/pardes-rendering.md new file mode 100644 index 0000000..0c89724 --- /dev/null +++ b/docs/pardes-rendering.md @@ -0,0 +1,253 @@ +# Pardes and the shared GPU executor + +Pardes already draws its interface with SDL_GPU. Its addon ABI originally +accepted cells and CPU RGBA rasters only. The optional GPU path lets an addon +submit a scene, render it into a texture on the frontend's device, and composite +that texture into the pane without reading pixels back to the CPU. + +## What is shared now + +`src/gpu/Executor.zig` is the executor previously in `src/host/gpu.zig`. It +owns shaders, pipelines, buffers and offscreen targets, but no window, SDL +renderer, sketch state or image manager. Both sketchbook and pardes use it. + +- `init(allocator, device)` borrows an existing SDL GPU device. +- `record(command_buffer, pass)` records a pass into the caller's command + buffer. The caller submits it. Shader and pipeline creation happens before + drawing; errors propagate to the caller. +- `run(pass)` records and submits a pass itself; sketchbook uses this convenience. +- `output(image)` borrows the target texture and dimensions. It is valid until + resize, `forget(image)`, or `deinit()`. Release external wrappers before those + operations. The executor owns the texture. +- `postProcess(command_buffer, source, target, post)` records a fullscreen + second pass sampling `source` into a distinct `target`, on the same command + buffer. The executor owns and reuses its nearest-neighbour sampler. +- Upload, compute, asynchronous buffer download and pipeline caching remain + available. Their submission policy is unchanged. + +Sketchbook's host wraps the output in an SDL_Renderer image. Pardes samples it +directly in its existing image compositor, using premultiplied blending. + +Embedders request the `gpu-only` build option, take the `abi`, `gpu` and +`gpu_scene` modules, and supply the `gpu` module's `c` import from their existing +SDL translation. This avoids building a second host or creating another device. +Pardes currently uses a sibling checkout dependency (`../sketchbook`); pin a +published revision when these two changes are released together. + +## Keep GPU support optional + +Pardes ABI 3.1 appends one optional submission callback and its context to +`pa_paint`. The old fields and required callbacks are unchanged. A GPU addon +checks the host ABI before reading the extension; a null callback means it is +unavailable. The Zig helper `Paint.gpu(bytes)` performs both checks. + +The callback copies the scene during the call, so stack buffers are safe. An +addon still paints cells or a raster. Accepting the scene only means the host +can carry it: a terminal, the native macOS frontend, or a frontend that refuses +the shader displays the fallback. Neither ordinary addons nor the core need +SDL or a GPU. The callback transports opaque display data; graphics types do +not enter the main C ABI. + +`src/gpu/scene.zig` is the separate, versioned scene format and Zig codec. SGPU +version 1 carries one self-contained render pass: SPIR-V vertex and fragment +shaders, vertex layouts, draws, uniforms, blending, clipping, MSAA and stencil. +It contains no pointers or device handles. `Pass.image` is `.none` on the wire; +the frontend supplies its own target. A clear colour is required, so a frame +can be skipped or a new replica attached without replaying old GPU work. + +The encoding is `SGPU`, a little-endian u32 version, then the current +`abi.gpu.Pass` fields in declaration order, recursively. Slice counts and enums +are u32; scalars use little endian; optionals and booleans use a 0/1 byte. No +native padding is serialized. Changing these fields requires a format version +change. The decoder bounds allocation, dimensions, draws, shader metadata, +vertex ranges and uniform sizes before the executor sees the pass. This is +structural validation, not a shader sandbox: use shaders from a trusted session. + +SGPU version 2 keeps the v1 pass encoding and appends one `PostProcess`: +vertex shader, fragment shader, and fragment uniform bytes. The vertex stage +has no uniforms or inputs; the fragment stage has exactly one implicit sampler +at set 2, binding 0, reading the completed first pass. `decodeFrame` accepts both +versions; `encode` still writes v1 and `encodePostProcess` writes v2. The same +frame allocation, shader and uniform limits apply. This deliberately supports +one postprocessing pass, without adding a render graph or C ABI fields. + +The current limits are 4 MiB per scene, 4096 pixels per side, 64 pipelines, +4096 draws, and 16 KiB per stage's uniform block. Version 1 deliberately has no +storage-buffer handles or compute commands. Local sketchbook applications keep +the existing richer API; persistent remote GPU resources need their own +lifetime and recovery protocol before exposing them to addons. + +Pardes carries scene bytes in its authoritative pane-frame stream, including +changes where the cells are identical. Replicas need no addon code. Unchanged +scenes are not resent or rerendered. Shader bytes are currently included in each +changed scene; this is suitable for the snake example, not a large streaming +mesh. Closing a pane releases its frontend target. Unsupported frontends ignore +the scene and display the fallback. + +## First consumer: SnakeShader + +In the pardes checkout: + +``` +zig build snake-shader -Dplatform=tui -Dpdf=false -Doptimize=ReleaseSafe +zig build -Dplatform=gui -Dpdf=false -Doptimize=ReleaseSafe +``` + +In the rebuilt GUI session, execute: + +``` +Addon load /absolute/path/to/pardes/zig-out/lib/libsnake_shader.so +SnakeShader +``` + +The build requires `glslc`. The example sends board occupancy and a small set +of parameters to a fragment shader. `h j k l` and arrows steer, `r` restarts; +losing focus pauses movement. A two-turn buffer supports quick corners and +corrections, with 60 ms of grace for late input and collision recovery. The +board fills its pane with whole square cells and resizes dynamically. Shrinking +translates the snake inward, shortening only a tail that cannot fit; the score +is preserved. The last active view owns the board dimensions, so an idle replica +does not resize another player's game. On an older host it remains a text snake. +Building a new binary does not upgrade a running session. + +`snake.post.frag` samples the board in a separate GPU pass and adds a three-column +RGB phosphor mask and four-row scanlines, a nine-tap bloom and filmic colour +mapping. Hovering adds a local glow and rim to the cell. A 3.5% food pulse and +0.6% phosphor shimmer keep a paused or finished game subtly alive. Visible panes +animate at 20 Hz; hidden panes stop requesting animation ticks. Its intermediate and final textures +are reused and resized together; closing the pane releases both. No CPU readback +or extra command-buffer submission is needed. A host without SGPU v2 displays +the text fallback. Use `test/gpu_snake.py BINARY ADDON OUTPUT --crt` to check the +actual RGB triads and scanline modulation, as well as the game colours. +The target covers the pane with an opaque background and centres the whole-cell +grid in any remaining margin, so fallback text cannot leak around a successful +render. These effects require no new scene commands or C ABI fields. + +`test/gpu_snake_interaction.py GUI V1_ADDON CURRENT_ADDON OUTPUT` checks live +record migration, a second reload, column resize, hover/leave, and pixel changes +while movement is paused, preserving unsaved text and shell identities. The addon +also tests buffered turns, grace deadlines, geometry, state loading and optional +GPU fallback. Its version 2 record accepts version 1 saved games. + +## Next steps: move pardes's low-level renderer + +1. **Texture bindings and instancing.** Extend the shared pipeline/draw model + with sampled textures, samplers and instance layouts/counts. Pardes's glyph + atlas and cell renderer need these before they can use the executor. Add + pixel tests for glyph masks, clipping and straight/premultiplied alpha. +2. **Extract common resource operations.** Move texture creation, staged full + and dirty-row uploads, transfer buffers and sampler caching out of + `pardes/src/gui/gui.zig`. Keep ownership explicit and use the caller's + command buffer. Test resize, partial-upload failure, window close and device + teardown against both hosts. +3. **Move the compositor a pass at a time.** Start with native image quads, + then decorations and cell instances. Preserve ordering of pane content, + tags, notices and selection, clipping and window opacity. Pardes continues + to produce layout, shaped text and draw data; those are editor semantics. +4. **Persistent addon resources, when a consumer needs them.** Add + content-addressed shader/mesh resources and explicit updates to the separate + scene protocol. Define per-session/per-view ownership, quotas, invalidation, + reconnect and missed-frame recovery before adding compute/storage buffers. + Keep all of this behind the optional callback, not new mandatory addon ops. +5. **Other frontends.** Implement the scene executor on the native macOS path + (shader translation/backend choice needs deciding), preserving fallbacks. + Sketchbook's WebGPU implementation is another possible consumer; SGPU v1 + currently carries SPIR-V, not WGSL. +6. **Measure before widening the API.** Compare CPU record time, GPU time, + uploads, submissions and memory for many panes, large geometry and repeated + reload/resize. Batch compute/uploads into caller command buffers when + measurements justify it. Add allocation limits across targets, rather than + relying only on per-scene bounds, before treating this as a large-scene API. + +Do not migrate text shaping, editor layout, input routing or session state into +the renderer. Do not add raw device pointers to pardes's addon ABI. The shared +layer should execute graphics work; the applications decide what to draw. + +## Validation (2026-11-12) + +The two builds used Zig 0.17.0, ReleaseSafe, the SDL frontend, PDF disabled, +and the same pre-existing pardes edits. The baseline was the checkout before +the GPU changes. Three interleaved runs per build scrolled the same 10,000-line +file at a 100×30 grid. Three further runs restarted the shader snake every +16 ms to change its uniforms. Startup's first 500 ms was excluded. + +| Workload | Frames | Median frame work | p95 frame work | Frames over 16.7 ms | +| --- | ---: | ---: | ---: | ---: | +| Text scrolling, before | 458 | 7.627 ms | 16.068 ms | 16 | +| Text scrolling, after | 462 | 7.519 ms | 14.838 ms | 8 | +| Shader snake | 350 | 7.414 ms | 14.208 ms | 5 | + +These are FrameStats update + core render + present times, **not GPU timer +queries or a frame-rate guarantee**. The offscreen driver cannot present to a +headless Vulkan surface here, so the test includes GPU readback and software +presentation/capture. Both builds use the same path. Run-to-run variation was +substantial; the result supports no measured scrolling regression, not a claim +of a speedup. Median core-render time was 77 µs before, 78.5 µs after, and +124 µs for the shader snake. Shader images were checked for the board's solid +green segments and orange food, and visually inspected. + +Reproduce in pardes with `test/gpu_snake.py BINARY ADDON OUTPUT --text` for +scrolling, omitting `--text` for the shader. Each output directory keeps the +raw FrameStats TSV, screenshot, stderr and JSON summary. Use matching build +options, an otherwise idle machine, and interleave the baseline and changed +build; do not measure while compiling. + +`test/gpu_upgrade.py OLD_GUI NEW_GUI OLD_SNAKE SHADER_SNAKE OUTPUT` checks +in-place upgrade, unsaved text, shell identity, saved game state, addon reload, +and a second GPU replica. Explicitly loaded addons must be loaded again after +an upgrade; their placeholder panes retain the saved state in the meantime. +The test exposed an existing missing addon generation field in pardes's dump +codec; saving it is necessary for a replica joining after an addon reload. + +Pardes's full core suite passed 967 of 969 tests. The same two failures also +occurred in the baseline (965 of 967): the full-screen tty handoff test and +the terminal dump test's cleanup crash. They remain unresolved; the GPU +changes introduced no additional failures in this comparison. Addon fixtures, +old ABI 3.0 addon compatibility, shader pixels, and the isolated upgrade/reload/ +replica checks passed. The live session then upgraded with its text contents +and shell process IDs preserved. + +The sketchbook ReleaseSafe suite covers vector GPU/CPU pixel comparisons, +render targets, replay/reload, exports and scene playback. Its existing clock +test compared struct padding; it now compares fields, avoiding an unrelated +ReleaseSafe test failure. Its vector benchmark recorded the two small sample +scenes in 15–16 µs, with CPU parse+draw at 278–315 µs (the gate is 1 ms). + +The CRT follow-up passed the scene codec tests, addon fixtures, Sketchbook's +ReleaseSafe suite, v1 rendering compatibility, and the isolated upgrade/reload/ +column-resize/pane-close/replica test. Native captures verified RGB triads and +scanline contrast, including a narrow pane without fallback text leaking through. +Three interleaved runs of the final version measured median frame work of +10.409 ms before and 10.585 ms with CRT, with p95 at 16.671 and 17.512 ms +(328 frames each). This is a small measured extra cost, not a zero-overhead +claim; the same offscreen capture limitations above apply. The live session +was upgraded and pane 42 reloaded with its game state, text and shells preserved. + +The game-feel follow-up passed seven addon tests, its updated scripted fixture, +GPU colour/CRT checks, and the interaction test for migration, reload, resizing, +hover/leave and animation while paused. The upgrade/reload/replica test also +passed. Migration exposed two existing host bugs: reload passed the replacement +library's version for the old record, and restored records retained the old +version after successful migration. Pardes now preserves the input record version +until loading succeeds and saves subsequent records with the current version; +a focused core regression test covers both paths. No ABI fields were added. + +Three interleaved before/after runs compared the previous CRT addon with the +resizable board, bloom, colour mapping, hover glow and idle animation: + +| Workload | Frames | Median frame work | p95 frame work | +| --- | ---: | ---: | ---: | +| Previous CRT snake | 378 | 4.759 ms | 14.616 ms | +| New snake and effects | 369 | 5.271 ms | 15.313 ms | +| Text scrolling, before (one run) | 136 | 12.848 ms | 19.067 ms | +| Text scrolling, after (one run) | 133 | 13.275 ms | 19.027 ms | + +The effects added about 0.5 ms to the pooled median in this capture. Individual +snake-run medians ranged from 4.6 to 12.7 ms, so system variation was substantial; +the scrolling pair is a smoke check, not evidence of zero regression. These are +the same offscreen/readback measurements described above, not GPU timer queries. +Visible paused games now request animation frames instead of remaining idle. +The full core and Sketchbook suites were not repeated for this follow-up. +The live session was upgraded and pane 42 migrated to version 2, retaining its +score, length, step count, focus, file contents and shell identities; the open +source-directory listing refreshed from disk. diff --git a/src/abi.zig b/src/abi.zig index d91fa23..7177f14 100644 --- a/src/abi.zig +++ b/src/abi.zig @@ -370,6 +370,8 @@ pub const Command = union(enum) { /// Renders a GPU pass into an image made by `Host.newImage`, when /// `Host.gpu` says the host can. gpu: gpu.Pass, + /// Fullscreen pass sampling a completed GPU image, into a different image. + post_process: struct { source: Image, target: Image, effect: gpu.PostProcess }, /// Bytes into a buffer made by `Host.newBuffer`, at `offset`. upload: struct { buffer: Buffer, offset: u32 = 0, bytes: []const u8 }, /// Runs a compute shader over buffers (see `abi.gpu`). @@ -579,8 +581,10 @@ pub const gpu = struct { draws: []const Draw, }; - /// A fullscreen triangle sampling one completed pass at fragment binding 0. + /// Fullscreen triangle: color at fragment binding 0, optional depth at 1. pub const PostProcess = struct { + /// Requires a preceding single-sample pass with depth enabled. + sample_depth: bool = false, vertex: Shader, fragment: Shader, fragment_uniforms: []const u8 = &.{}, @@ -813,7 +817,7 @@ pub const Sketch = struct { pub const hash: u64 = blk: { @setEvalBranchQuota(1_000_000); var h: u64 = 0; - for (.{ Rect, Color, BlendMode, Corners, Event, Mode, Stream, Input, Image, Audio, Cursor, Voice, Command, gpu.Pass, gpu.Pipeline, gpu.Draw, gpu.Dispatch, Host, Host.VTable, Context, Field, Layout, Info, Memory, Sketch }) |T| { + for (.{ Rect, Color, BlendMode, Corners, Event, Mode, Stream, Input, Image, Audio, Cursor, Voice, Command, gpu.Pass, gpu.Pipeline, gpu.Draw, gpu.Dispatch, gpu.PostProcess, Host, Host.VTable, Context, Field, Layout, Info, Memory, Sketch }) |T| { h = std.hash.Wyhash.hash(h, @typeName(T) ++ layout.signature(T)); } break :blk h; diff --git a/src/gpu/Executor.zig b/src/gpu/Executor.zig index 412d0ed..460b2d5 100644 --- a/src/gpu/Executor.zig +++ b/src/gpu/Executor.zig @@ -155,6 +155,8 @@ const Target = struct { msaa_fresh: bool = true, stencil_samples: u8 = 0, stencil: ?*c.SDL_GPUTexture = null, + depth_valid: bool = false, + depth_sampleable: bool = false, }; pub fn init(gpa: std.mem.Allocator, device: *c.SDL_GPUDevice) Gpu { @@ -229,25 +231,41 @@ pub fn run(g: *Gpu, pass: abi.gpu.Pass) !void { /// Records into the caller's command buffer; the caller submits it. /// Uploads cycle their buffers, allowing several passes in one frame. pub fn record(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, pass: abi.gpu.Pass) !void { - return g.recordWithInput(cmd, pass, null); + return g.recordWithInput(cmd, pass, &.{}); +} + +pub fn runPostProcess(g: *Gpu, source: abi.Image, target: abi.Image, post: abi.gpu.PostProcess) !void { + const start = g.startTiming(); + const cmd = c.SDL_AcquireGPUCommandBuffer(g.device) orelse return error.GpuCommandBuffer; + errdefer _ = c.SDL_CancelGPUCommandBuffer(cmd); + try g.postProcess(cmd, source, target, post); + try g.submit(cmd, "postprocess", start); } /// A second pass on the same command buffer; input and output must differ. pub fn postProcess(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, source: abi.Image, target: abi.Image, post: abi.gpu.PostProcess) !void { if (source == target) return error.FeedbackLoop; - const input = g.output(source) orelse return error.MissingImage; + const input = g.targets.get(source) orelse return error.MissingImage; + var textures: [2]*c.SDL_GPUTexture = undefined; + textures[0] = input.texture; + if (post.sample_depth) { + if (!input.depth_valid or input.stencil == null) return error.MissingDepthAttachment; + if (input.stencil_samples != 1) return error.MultisampleDepthUnsupported; + if (!input.depth_sampleable) return error.DepthSamplingUnsupported; + textures[1] = input.stencil.?; + } try g.recordWithInput(cmd, .{ .image = target, .width = input.width, .height = input.height, .pipelines = &.{.{ .vertex = post.vertex, .fragment = post.fragment, .stride = 0, .attributes = &.{}, .blend = .none }}, .draws = &.{.{ .pipeline = 0, .vertex_count = 3, .fragment_uniforms = post.fragment_uniforms }}, - }, input.texture); + }, textures[0 .. 1 + @as(usize, @intFromBool(post.sample_depth))]); } -fn recordWithInput(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, pass: abi.gpu.Pass, input: ?*c.SDL_GPUTexture) !void { +fn recordWithInput(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, pass: abi.gpu.Pass, input: []const *c.SDL_GPUTexture) !void { if (pass.width == 0 or pass.height == 0 or pass.draws.len == 0 and pass.clear == null) return; - if (input != null and g.post_sampler == null) { + if (input.len != 0 and g.post_sampler == null) { g.post_sampler = c.SDL_CreateGPUSampler(g.device, &std.mem.zeroInit(c.SDL_GPUSamplerCreateInfo, .{ .min_filter = c.SDL_GPU_FILTER_NEAREST, .mag_filter = c.SDL_GPU_FILTER_NEAREST, @@ -269,7 +287,7 @@ fn recordWithInput(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, pass: abi.gpu.Pass, in if (d.pipeline >= pass.pipelines.len) return error.BadPipeline; const p = pass.pipelines[d.pipeline]; if ((p.depth_test != null or p.depth_write) and !pass.depth) return error.MissingDepthAttachment; - if (built[d.pipeline] == null) built[d.pipeline] = try g.pipeline(pass.pipelines[d.pipeline], samples, pass.stencil or pass.depth, @intFromBool(input != null)); + if (built[d.pipeline] == null) built[d.pipeline] = try g.pipeline(pass.pipelines[d.pipeline], samples, pass.stencil or pass.depth, @intCast(input.len)); } // Every draw's vertices go up in one copy. @@ -314,13 +332,14 @@ fn recordWithInput(g: *Gpu, cmd: *c.SDL_GPUCommandBuffer, pass: abi.gpu.Pass, in depth.texture = t.stencil; depth.load_op = if (pass.depth) c.SDL_GPU_LOADOP_CLEAR else c.SDL_GPU_LOADOP_DONT_CARE; depth.clear_depth = 1; - depth.store_op = c.SDL_GPU_STOREOP_DONT_CARE; + depth.store_op = if (pass.depth) c.SDL_GPU_STOREOP_STORE else c.SDL_GPU_STOREOP_DONT_CARE; depth.stencil_load_op = c.SDL_GPU_LOADOP_CLEAR; depth.stencil_store_op = c.SDL_GPU_STOREOP_DONT_CARE; depth.clear_stencil = 0; } const rp = c.SDL_BeginGPURenderPass(cmd, &color, 1, if (pass.stencil or pass.depth) &depth else null) orelse return error.GpuRenderPass; - if (input) |texture_| c.SDL_BindGPUFragmentSamplers(rp, 0, &.{ .texture = texture_, .sampler = g.post_sampler.? }, 1); + t.depth_valid = pass.depth; + for (input, 0..) |texture_, slot| c.SDL_BindGPUFragmentSamplers(rp, @intCast(slot), &.{ .texture = texture_, .sampler = g.post_sampler.? }, 1); var bound: ?*c.SDL_GPUGraphicsPipeline = null; // State already set in this pass, so draws that repeat it skip the call. var vertex_uniforms: ?[]const u8 = null; @@ -575,9 +594,13 @@ fn renderTarget(g: *Gpu, image: abi.Image, w: u32, h: u32, samples: u8, stencil: t.msaa_fresh = true; } if (stencil and (t.stencil == null or t.stencil_samples != samples)) { + const sampled_usage = c.SDL_GPU_TEXTUREUSAGE_DEPTH_STENCIL_TARGET | c.SDL_GPU_TEXTUREUSAGE_SAMPLER; + const sampleable = samples == 1 and c.SDL_GPUTextureSupportsFormat(g.device, g.stencil_format, c.SDL_GPU_TEXTURETYPE_2D, sampled_usage); + const replacement = try g.texture(w, h, g.stencil_format, if (sampleable) sampled_usage else c.SDL_GPU_TEXTUREUSAGE_DEPTH_STENCIL_TARGET, samples); if (t.stencil) |s| c.SDL_ReleaseGPUTexture(g.device, s); - t.stencil = try g.texture(w, h, g.stencil_format, c.SDL_GPU_TEXTUREUSAGE_DEPTH_STENCIL_TARGET, samples); + t.stencil = replacement; t.stencil_samples = samples; + t.depth_sampleable = sampleable; } return t; } diff --git a/src/gpu/scene.zig b/src/gpu/scene.zig index e5ff3d0..d5e1db5 100644 --- a/src/gpu/scene.zig +++ b/src/gpu/scene.zig @@ -2,6 +2,7 @@ //! Version 1: "SGPU", u32 version, then Pass fields in declaration order. //! Version 2 appends one fullscreen PostProcess sampling that pass's output. //! Version 3 adds depth fields and an optional PostProcess after the pass. +//! Version 4 adds optional depth sampling to PostProcess. //! Integers/enums/f32 are little endian; slices have a u32 count, optionals //! and bools a byte (0 or 1). No pointers, native padding, or device handles. //! Storage buffers are not part of this version: each frame stands alone. @@ -22,11 +23,12 @@ pub fn encode(w: *std.Io.Writer, pass: abi.gpu.Pass) !void { pub fn encodePostProcess(w: *std.Io.Writer, pass: abi.gpu.Pass, post: abi.gpu.PostProcess) !void { try validate(pass); try validatePostProcess(post); + if (post.sample_depth and (!pass.depth or pass.samples != 1)) return error.BadScene; try w.writeAll("SGPU"); - const version: u32 = if (pass.depth) 3 else 2; + const version: u32 = if (post.sample_depth) 4 else if (pass.depth) 3 else 2; try w.writeInt(u32, version, .little); try put(w, pass, version); - if (version == 3) try put(w, @as(?abi.gpu.PostProcess, post), version) else try put(w, post, version); + if (version >= 3) try put(w, @as(?abi.gpu.PostProcess, post), version) else try put(w, post, version); } /// Allocations belong to the caller's frame arena. Never run unvalidated @@ -42,13 +44,16 @@ pub fn decodeFrame(arena: std.mem.Allocator, bytes: []const u8) !Frame { var r: std.Io.Reader = .fixed(bytes); if (!std.mem.eql(u8, try r.take(4), "SGPU")) return error.BadScene; const version = try r.takeInt(u32, .little); - if (version < 1 or version > 3) return error.BadScene; + if (version < 1 or version > 4) return error.BadScene; var budget: usize = max_bytes * 4; const pass = try get(abi.gpu.Pass, arena, &r, &budget, version); - const post: ?abi.gpu.PostProcess = if (version == 3) try get(?abi.gpu.PostProcess, arena, &r, &budget, version) else if (version == 2) try get(abi.gpu.PostProcess, arena, &r, &budget, version) else null; + const post: ?abi.gpu.PostProcess = if (version >= 3) try get(?abi.gpu.PostProcess, arena, &r, &budget, version) else if (version == 2) try get(abi.gpu.PostProcess, arena, &r, &budget, version) else null; if (r.end != r.seek) return error.BadScene; try validate(pass); - if (post) |p| try validatePostProcess(p); + if (post) |p| { + try validatePostProcess(p); + if (p.sample_depth and (!pass.depth or pass.samples != 1)) return error.BadScene; + } return .{ .pass = pass, .post = post }; } @@ -57,6 +62,11 @@ fn depthField(comptime T: type, comptime name: []const u8) bool { (T == abi.gpu.Pipeline and (std.mem.eql(u8, name, "depth_test") or std.mem.eql(u8, name, "depth_write"))); } +fn absentField(comptime T: type, comptime name: []const u8, version: u32) bool { + return (version < 3 and depthField(T, name)) or + (version < 4 and T == abi.gpu.PostProcess and std.mem.eql(u8, name, "sample_depth")); +} + fn put(w: *std.Io.Writer, value: anytype, version: u32) anyerror!void { const T = @TypeOf(value); switch (@typeInfo(T)) { @@ -74,7 +84,7 @@ fn put(w: *std.Io.Writer, value: anytype, version: u32) anyerror!void { for (value) |v| try put(w, v, version); }, .@"struct" => |s| inline for (s.field_names) |name| { - if (version >= 3 or !depthField(T, name)) try put(w, @field(value, name), version); + if (!absentField(T, name, version)) try put(w, @field(value, name), version); }, else => @compileError("unsupported scene field"), } @@ -117,7 +127,7 @@ fn get(comptime T: type, a: std.mem.Allocator, r: *std.Io.Reader, budget: *usize .@"struct" => |s| { var out: T = undefined; inline for (s.field_names, s.field_types) |name, F| { - @field(out, name) = if (version < 3 and comptime depthField(T, name)) std.mem.zeroes(F) else try get(F, a, r, budget, version); + @field(out, name) = if (absentField(T, name, version)) std.mem.zeroes(F) else try get(F, a, r, budget, version); } return out; }, @@ -227,7 +237,7 @@ test "GPU postprocess keeps v1 readable and validates the complete second pass" bad = post; bad.fragment.storage_buffers = 1; try std.testing.expectError(error.BadShader, validatePostProcess(bad)); - out.written()[4] = 4; + out.written()[4] = 5; try std.testing.expectError(error.BadScene, decodeFrame(arena.allocator(), out.written())); } @@ -261,3 +271,32 @@ test "depth uses v3 and requires an attachment; legacy frames keep depth disable const legacy = try decode(arena.allocator(), out.written()); try std.testing.expect(!legacy.depth and legacy.pipelines[0].depth_test == null and !legacy.pipelines[0].depth_write); } + +test "depth postprocess uses v4 and rejects missing or multisampled source depth" { + const code = std.mem.asBytes(&[_]u32{ 0x07230203, 0, 0, 0, 0 }); + const pipelines = [_]abi.gpu.Pipeline{.{ .vertex = .{ .code = code }, .fragment = .{ .code = code }, .stride = 0, .attributes = &.{} }}; + var pass: abi.gpu.Pass = .{ .image = .none, .width = 32, .height = 24, .depth = true, .pipelines = &pipelines, .draws = &.{.{ .pipeline = 0, .vertex_count = 3 }} }; + var post: abi.gpu.PostProcess = .{ .sample_depth = true, .vertex = .{ .code = code }, .fragment = .{ .code = code } }; + var out: std.Io.Writer.Allocating = .init(std.testing.allocator); + defer out.deinit(); + var arena: std.heap.ArenaAllocator = .init(std.testing.allocator); + defer arena.deinit(); + try encodePostProcess(&out.writer, pass, post); + try std.testing.expectEqual(4, out.written()[4]); + try std.testing.expect((try decodeFrame(arena.allocator(), out.written())).post.?.sample_depth); + for (0..out.written().len) |i| { + _ = decodeFrame(arena.allocator(), out.written()[0..i]) catch continue; + return error.AcceptedTruncatedScene; + } + pass.depth = false; + try std.testing.expectError(error.BadScene, encodePostProcess(&out.writer, pass, post)); + pass.depth = true; + pass.samples = 4; + try std.testing.expectError(error.BadScene, encodePostProcess(&out.writer, pass, post)); + pass.samples = 1; + post.sample_depth = false; + out.clearRetainingCapacity(); + try encodePostProcess(&out.writer, pass, post); + try std.testing.expectEqual(3, out.written()[4]); + try std.testing.expect(!(try decodeFrame(arena.allocator(), out.written())).post.?.sample_depth); +} diff --git a/src/host/Host.zig b/src/host/Host.zig index 745d9a1..035a004 100644 --- a/src/host/Host.zig +++ b/src/host/Host.zig @@ -447,6 +447,7 @@ fn draw(self: *Host, now: u64, started: u64) !u64 { .audio => |a| self.audio.push(a.key, a.samples, a.clear), .quit => self.quit = true, .gpu => |pass| if (self.passes) |*g| self.runGpu(g, pass) catch |err| self.print("gpu pass: {t} ({s})", .{ err, c.SDL_GetError() }), + .post_process => |p| if (self.passes) |*g| self.runPostProcess(g, p.source, p.target, p.effect) catch |err| self.print("gpu postprocess: {t} ({s})", .{ err, c.SDL_GetError() }), .upload => |u| if (self.passes) |*g| g.write(u.buffer, u.offset, u.bytes) catch |err| self.print("gpu upload: {t} ({s})", .{ err, c.SDL_GetError() }), .compute => |d| if (self.passes) |*g| g.compute(d) catch |err| self.print("gpu compute: {t} ({s})", .{ err, c.SDL_GetError() }), .microphone => self.audio.listen(), @@ -981,6 +982,15 @@ fn apiEnv(ctx: *anyopaque, name: []const u8) ?[]const u8 { return hostOf(ctx).environ.get(name); } +fn runPostProcess(self: *Host, g: *Gpu, source: abi.Image, target: abi.Image, post: abi.gpu.PostProcess) !void { + const input = g.output(source) orelse return error.MissingImage; + const before = g.output(target); + const changed = if (before) |t| t.width != input.width or t.height != input.height else true; + if (changed) self.images.unwrap(target); + try g.runPostProcess(source, target, post); + if (g.output(target)) |t| try self.images.wrap(target, t.texture, t.width, t.height); +} + fn runGpu(self: *Host, g: *Gpu, pass: abi.gpu.Pass) !void { const before = g.output(pass.image); const changed = if (before) |t| t.width != pass.width or t.height != pass.height else true; diff --git a/src/sketch/clock.zig b/src/sketch/clock.zig index e64e2a8..2d63e12 100644 --- a/src/sketch/clock.zig +++ b/src/sketch/clock.zig @@ -85,7 +85,7 @@ test "N updates of one tick each step exactly as one update of N ticks" { var sum: u32 = 0; for (per) |n| sum += n; try std.testing.expectEqual(sum, total); - try std.testing.expectEqual(std.mem.toBytes(one), std.mem.toBytes(all)); + try std.testing.expectEqualDeep(one, all); try std.testing.expectEqual(@as(u32, Clock.max_steps), per[300]); try std.testing.expectEqual(@as(u64, total), all.count); } diff --git a/src/sketch/root.zig b/src/sketch/root.zig index 434478c..cb20ab9 100644 --- a/src/sketch/root.zig +++ b/src/sketch/root.zig @@ -232,6 +232,12 @@ pub const Frame = struct { kept.draws = draws; f.emit(.{ .gpu = kept }); } + /// Samples the source color and optionally depth into a distinct image. + pub fn postProcess(f: *Frame, source: Image, destination: Image, post: abi.gpu.PostProcess) void { + var kept = post; + kept.fragment_uniforms = f.keep(u8, post.fragment_uniforms); + f.emit(.{ .post_process = .{ .source = source, .target = destination, .effect = kept } }); + } /// `bytes` into a buffer made by `Host.newBuffer`. pub fn upload(f: *Frame, buffer: abi.Buffer, offset: u32, bytes: []const u8) void { f.emit(.{ .upload = .{ .buffer = buffer, .offset = offset, .bytes = bytes } }); @@ -469,3 +475,24 @@ test "setup receives session resources without a Frame and reports errors" { try std.testing.expectEqual(@as(u32, 1), session.calls); try std.testing.expect(seen); } + +test "postprocess preserves image handles and copies transient uniforms" { + var arena: std.heap.ArenaAllocator = .init(std.testing.allocator); + defer arena.deinit(); + var commands: std.ArrayList(abi.Command) = .empty; + var ctx: abi.Context = undefined; + ctx.commands = &commands; + var frame: Frame = undefined; + frame.ctx = &ctx; + frame.scratch = arena.allocator(); + var uniforms = [_]u8{ 1, 2, 3, 4 }; + const source: Image = @fromBackingInt(@intCast(1)); + const target: Image = @fromBackingInt(@intCast(2)); + frame.postProcess(source, target, .{ .vertex = .{ .code = "vertex" }, .fragment = .{ .code = "fragment" }, .sample_depth = true, .fragment_uniforms = &uniforms }); + uniforms[0] = 9; + const post = commands.items[0].post_process; + try std.testing.expectEqual(source, post.source); + try std.testing.expectEqual(target, post.target); + try std.testing.expect(post.effect.sample_depth); + try std.testing.expectEqualSlices(u8, &.{ 1, 2, 3, 4 }, post.effect.fragment_uniforms); +} diff --git a/src/sketch/web.zig b/src/sketch/web.zig index 682bff6..937b491 100644 --- a/src/sketch/web.zig +++ b/src/sketch/web.zig @@ -43,6 +43,7 @@ const js = struct { /// A `Dispatch` or a `Pass`, described in JSON (see `describe`). extern "gpu" fn compute(ptr: [*]const u8, len: usize) void; extern "gpu" fn pass(ptr: [*]const u8, len: usize) void; + extern "gpu" fn postProcess(ptr: [*]const u8, len: usize) void; /// Answers through `sk_download`. extern "gpu" fn download(id: u32, offset: u32, size: u32, key: u32) void; extern "audio" fn rate() u32; @@ -234,6 +235,10 @@ fn Driver(comptime App: type) type { const json = describe(v); js.pass(json.ptr, json.len); }, + .post_process => |v| { + const json = describe(v); + js.postProcess(json.ptr, json.len); + }, .download => |v| js.download(@backingInt(v.buffer), v.offset, v.size, v.key), .open_file => |v| js.openFile(v.command.ptr, v.command.len, v.pattern.ptr, v.pattern.len), // Synthesised voices are not on the web yet; quitting a page diff --git a/web/host.js b/web/host.js index 7559dfc..efc335d 100644 --- a/web/host.js +++ b/web/host.js @@ -176,7 +176,7 @@ const gpu = { // Multisample and stencil attachments, kept per image. attachment(entry, kind, format, samples) { const key = `${kind} ${samples}`; - if (!entry.attachments[key]) entry.attachments[key] = gpu.device.createTexture({size: [entry.w, entry.h], format, sampleCount: samples, usage: GPUTextureUsage.RENDER_ATTACHMENT}); + if (!entry.attachments[key]) entry.attachments[key] = gpu.device.createTexture({size: [entry.w, entry.h], format, sampleCount: samples, usage: GPUTextureUsage.RENDER_ATTACHMENT | (kind === 'stencil' && samples === 1 ? GPUTextureUsage.TEXTURE_BINDING : 0)}); return entry.attachments[key]; }, // Copies the latest render into the image's canvas, once a frame, for @@ -234,9 +234,11 @@ const gpu = { }; const depthStencil = p.stencil || p.depth ? { view: gpu.attachment(entry, 'stencil', 'depth24plus-stencil8', samples).createView(), - depthLoadOp: 'clear', depthClearValue: 1, depthStoreOp: 'discard', + depthLoadOp: 'clear', depthClearValue: 1, depthStoreOp: p.depth ? 'store' : 'discard', stencilLoadOp: 'clear', stencilClearValue: 0, stencilStoreOp: 'discard', } : undefined; + entry.depthValid = p.depth; + entry.depthSamples = samples; // Every draw's bytes are written before the pass is submitted. const draws = p.draws.map(d => ({ d, @@ -263,6 +265,52 @@ const gpu = { gpu.device.queue.submit([commands.finish()]); }, + // Fragment group 2: color texture/sampler at 0/1, optional depth at 2/3. + postProcess({source, target, effect}) { + if (source === target) throw new Error('FeedbackLoop'); + const input = images[source]; + if (!input?.texture) throw new Error('MissingImage'); + if (effect.sample_depth && !input.depthValid) throw new Error('MissingDepthAttachment'); + if (effect.sample_depth && input.depthSamples !== 1) throw new Error('MultisampleDepthUnsupported'); + const output = gpu.target(target, input.w, input.h); + if (!output) return; + const key = `post ${effect.vertex.hash} ${effect.fragment.hash} ${effect.sample_depth}`; + let pipeline = gpu.pipelines.get(key); + if (!pipeline) { + const entries = [ + {binding: 0, visibility: GPUShaderStage.FRAGMENT, texture: {sampleType: 'float'}}, + {binding: 1, visibility: GPUShaderStage.FRAGMENT, sampler: {type: 'non-filtering'}}, + ]; + if (effect.sample_depth) entries.push( + {binding: 2, visibility: GPUShaderStage.FRAGMENT, texture: {sampleType: 'unfilterable-float'}}, + {binding: 3, visibility: GPUShaderStage.FRAGMENT, sampler: {type: 'non-filtering'}}, + ); + const layouts = [[], [], entries, effect.fragment.uniform_buffers ? [{binding: 0, visibility: GPUShaderStage.FRAGMENT, buffer: {type: 'uniform'}}] : []]; + pipeline = gpu.device.createRenderPipeline({ + layout: gpu.device.createPipelineLayout({bindGroupLayouts: layouts.map(entries => gpu.device.createBindGroupLayout({entries}))}), + vertex: {module: gpu.module(effect.vertex)}, + fragment: {module: gpu.module(effect.fragment), targets: [{format: 'rgba8unorm'}]}, + primitive: {topology: 'triangle-list'}, + }); + gpu.pipelines.set(key, pipeline); + } + gpu.postSampler ??= gpu.device.createSampler({minFilter: 'nearest', magFilter: 'nearest'}); + const entries = [{binding: 0, resource: input.texture.createView()}, {binding: 1, resource: gpu.postSampler}]; + if (effect.sample_depth) entries.push( + {binding: 2, resource: input.attachments['stencil 1'].createView({aspect: 'depth-only'})}, + {binding: 3, resource: gpu.postSampler}, + ); + const uniforms = gpu.uniforms(effect.fragment_uniforms); + const commands = gpu.device.createCommandEncoder(); + const pass = commands.beginRenderPass({colorAttachments: [{view: output.texture.createView(), loadOp: 'clear', storeOp: 'store'}]}); + pass.setPipeline(pipeline); + gpu.bind(pass, pipeline, [[], [], entries, gpu.uniform(uniforms)]); + pass.draw(3); + pass.end(); + gpu.device.queue.submit([commands.finish()]); + output.depthValid = false; + }, + // Reads a buffer back; it reaches the sketch before a later frame. arrived: [], download(id, offset, size, key) { @@ -604,6 +652,7 @@ const imports = { }, compute(ptr, len) { if (gpu.device) gpu.compute(JSON.parse(string(ptr, len))); }, pass(ptr, len) { if (gpu.device) gpu.pass(JSON.parse(string(ptr, len))); }, + postProcess(ptr, len) { if (gpu.device) gpu.postProcess(JSON.parse(string(ptr, len))); }, download(id, offset, size, key) { if (gpu.buffers[id]) gpu.download(id, offset, size, key); }, }, audio: { |
