diff options
| author | Gabriel Schneider <[email protected]> | 2026-11-16 22:02:43 -0300 |
|---|---|---|
| committer | Gabriel Schneider <[email protected]> | 2026-11-17 12:15:01 -0300 |
| commit | 1cb36ee39a8bbc2cf61c28003670d760841d6d3e (patch) | |
| tree | d7d01eb5b3a40920a8f71d091a106561ca56b282 /src/gpu/Executor.zig | |
| parent | 6933f99ddb2d7103515d26838496309a807bba26 (diff) | |
| download | sketchbook-1cb36ee39a8bbc2cf61c28003670d760841d6d3e.tar.gz sketchbook-1cb36ee39a8bbc2cf61c28003670d760841d6d3e.zip | |
gpu: add a post-process pass with optional depth sampling, and describe the executor pardes shares
`f.postProcess(source, target, .{...})` records a fullscreen pass that samples a completed render into a distinct target image: colour at fragment binding 0 and, with `sample_depth`, depth at 1, which needs the source's latest pass to have depth and one sample (missing depth, multisampled depth and feedback loops are rejected). The scene format's version 4 carries it, the executor records it on the caller's command buffer and owns the sampler, the web host does the same with its texture and sampler pairs, and native profiling reports the work as `postprocess`. The README says how to use it.
docs/pardes-rendering.md describes the executor as pardes uses it for addon scenes: a borrowed SDL GPU device, `record` into the caller's command buffer, `run`, `output` and `postProcess`.
The working copy as it stood on 2026-11-16; message written by Claude from the diff, at the author's request.
Diffstat (limited to 'src/gpu/Executor.zig')
| -rw-r--r-- | src/gpu/Executor.zig | 41 |
1 files changed, 32 insertions, 9 deletions
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; } |
