diff options
Diffstat (limited to 'src/gpu')
| -rw-r--r-- | src/gpu/Executor.zig | 41 | ||||
| -rw-r--r-- | src/gpu/scene.zig | 55 |
2 files changed, 79 insertions, 17 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; } 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); +} |
