Crafter.Graphics/examples/HDRBloom/main.cpp

247 lines
12 KiB
C++
Raw Permalink Normal View History

2026-07-22 18:09:06 +02:00
//SPDX-License-Identifier: MIT
//SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®
// HDRBloom — cross-backend-shaped HDR post-process on the WebGPU/DOM
// backend, exercising the primitives added for issue #27:
//
// 1. rgba16float runtime textures (StorageImage2D) with STORAGE + SAMPLED
// usage — the scene + bloom-mip targets.
// 2. A write-only StorageTexture binding kind (UICustomBindingKind::
// StorageTexture) so compute passes write those float targets, plus
// float-texture sampling via SampledTexture.
// 3. PipelineRTWebGPU's RESOLVE writing linear radiance into a user
// rgba16float texture (hdrOutputFormat) instead of the canvas.
//
// Pipeline shape (the same one a Vulkan bloom would use):
// RT → linear rgba16float scene
// threshold (compute, sample float → write float)
// blur (compute, sample float → write float)
// composite (UI custom shader: scene + bloom → tonemap+gamma → canvas)
//
// The threshold/blur passes run from onBeforeUpdate so each lands on its own
// queue submit — WebGPU's per-submit ordering gives the storage-write →
// sampled-read barrier the chain needs (there is no barrier between
// dispatches within one compute pass). The composite runs in-frame as a UI
// custom shader so it owns the canvas ping-pong. Bloom is therefore one
// frame behind the sharp scene, which is imperceptible for this static view.
//
// WebGPU/DOM only — the wavefront tracer is the WebGPU software RT path.
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
int main() { return 0; } // native bloom is wireable today (see issue gap 4)
#else
#include <cstddef> // offsetof
import Crafter.Graphics;
import Crafter.Math;
import Crafter.Event;
import std;
using namespace Crafter;
namespace fs = std::filesystem;
namespace {
constexpr int kGrid = 3;
constexpr float kSpacing = 2.5f;
constexpr float kHalf = 0.5f;
struct CameraGPU {
float origin[3]; float pad0;
float right[3]; float tanHalf;
float up[3]; float aspect;
float forward[3]; float pad1;
};
static_assert(sizeof(CameraGPU) == 64);
struct Dim { std::uint32_t w, h, _0, _1; };
// Composite push: standard header + the three heap slots the UI custom
// shader's group(2) bindings resolve through.
struct CompositePush {
UIDispatchHeader hdr;
std::uint32_t hdrSlot;
std::uint32_t bloomSlot;
std::uint32_t sampSlot;
std::uint32_t _pad;
};
}
int main() {
Device::Initialize();
static Window window(1280, 720, "HDRBloom");
auto cmd = window.StartInit();
DescriptorHeapWebGPU heap;
heap.Initialize(/*images*/ 4, /*buffers*/ 4, /*samplers*/ 2);
window.descriptorHeap = &heap;
const std::uint16_t W = static_cast<std::uint16_t>(window.width);
const std::uint16_t H = static_cast<std::uint16_t>(window.height);
// ── RT pipeline: HDR output (RESOLVE → rgba16float) ────────────────
std::array<WebGPUShader, 3> shaders {{
WebGPUShader(fs::path("raygen.wgsl"), "raygen_main", WebGPURTStage::Raygen),
WebGPUShader(fs::path("miss.wgsl"), "miss_main", WebGPURTStage::Miss),
WebGPUShader(fs::path("closesthit.wgsl"), "closesthit_main", WebGPURTStage::ClosestHit),
}};
ShaderBindingTableWebGPU sbt;
sbt.Init(shaders);
std::array<RTShaderGroup, 1> raygenGroups {{ { .type = RTShaderGroupType::General, .generalShader = 0 } }};
std::array<RTShaderGroup, 1> missGroups {{ { .type = RTShaderGroupType::General, .generalShader = 1 } }};
std::array<RTShaderGroup, 1> hitGroups {{ { .type = RTShaderGroupType::TrianglesHitGroup, .closestHitShader = 2 } }};
std::array<UICustomBinding, 1> rtBindings {{
{ .group = 3, .binding = 0, .kind = UICustomBindingKind::Buffer, .pushOffset = 0 },
}};
PipelineRTWebGPU pipeline;
pipeline.Init(cmd, raygenGroups, missGroups, hitGroups, sbt, rtBindings,
WebGPUTexelFormat::RGBA16Float); // ← RESOLVE writes HDR
// ── Unit cube mesh. ────────────────────────────────────────────────
static std::array<Vector<float, 3, 3>, 8> verts {{
{-kHalf, -kHalf, -kHalf}, { kHalf, -kHalf, -kHalf},
{ kHalf, kHalf, -kHalf}, {-kHalf, kHalf, -kHalf},
{-kHalf, -kHalf, kHalf}, { kHalf, -kHalf, kHalf},
{ kHalf, kHalf, kHalf}, {-kHalf, kHalf, kHalf},
}};
static std::array<std::uint32_t, 36> indices {{
0,1,2, 0,2,3, 5,4,7, 5,7,6, 4,0,3, 4,3,7,
1,5,6, 1,6,2, 4,5,1, 4,1,0, 3,2,6, 3,6,7,
}};
static Mesh cube;
cube.Build(verts, indices, cmd);
WebGPUBuffer<CameraGPU, true> cameraBuf;
cameraBuf.Create(1);
static std::array<std::uint32_t, 1> rtHandles { cameraBuf.handle };
static std::vector<RenderingElement3D> renderers;
renderers.reserve(static_cast<std::size_t>(kGrid * kGrid * kGrid));
const float origin0 = -0.5f * static_cast<float>(kGrid - 1) * kSpacing;
for (int x = 0; x < kGrid; ++x)
for (int y = 0; y < kGrid; ++y)
for (int z = 0; z < kGrid; ++z) {
renderers.emplace_back();
RenderingElement3D& r = renderers.back();
auto& tx = r.instance.transform.matrix;
tx[0][0] = 1; tx[0][1] = 0; tx[0][2] = 0; tx[0][3] = origin0 + float(x) * kSpacing;
tx[1][0] = 0; tx[1][1] = 1; tx[1][2] = 0; tx[1][3] = origin0 + float(y) * kSpacing;
tx[2][0] = 0; tx[2][1] = 0; tx[2][2] = 1; tx[2][3] = origin0 + float(z) * kSpacing;
r.instance.instanceCustomIndex = static_cast<std::uint32_t>(renderers.size() - 1);
r.instance.mask = 0xFF;
r.instance.instanceShaderBindingTableRecordOffset = 0;
r.instance.flags = kRTGeometryInstanceForceOpaque;
r.instance.accelerationStructureReference = cube.blasAddr;
RenderingElement3D::Add(&r);
}
RenderingElement3D::BuildTLAS(cmd, 0);
// ── HDR scene + bloom mip targets (rgba16float). ───────────────────
StorageImage2D hdrScene; hdrScene.Create(W, H);
StorageImage2D bloomA; bloomA.Create(W, H);
StorageImage2D bloomB; bloomB.Create(W, H);
// Heap slots for the composite's sampled inputs + sampler.
ImageSlot hdrSlot = hdrScene.AllocateSlot(heap);
ImageSlot bloomSlot = bloomB.AllocateSlot(heap);
SamplerSlot sampSlot = AllocateLinearClampSampler(heap);
// ── Threshold + blur compute passes. ───────────────────────────────
std::array<UICustomBinding, 2> bloomBindings {{
{ .group = 1, .binding = 0, .kind = UICustomBindingKind::SampledTexture, .pushOffset = 0 },
{ .group = 1, .binding = 1, .kind = UICustomBindingKind::StorageTexture,
.format = static_cast<std::uint8_t>(WebGPUTexelFormat::RGBA16Float), .pushOffset = 0 },
}};
PlainComputeShader threshold;
threshold.Load(fs::path("threshold.comp.wgsl"), sizeof(Dim), bloomBindings);
PlainComputeShader blur;
blur.Load(fs::path("blur.comp.wgsl"), sizeof(Dim), bloomBindings);
std::array<std::uint32_t, 2> thresholdHandles { hdrScene.handle, bloomA.handle };
std::array<std::uint32_t, 2> blurHandles { bloomA.handle, bloomB.handle };
// ── Composite UI custom shader. ────────────────────────────────────
UIRenderer ui;
ui.Initialize(window, heap, cmd);
UICustomBinding compBindings[] = {
{ .group = 2, .binding = 0, .kind = UICustomBindingKind::SampledTexture,
.pushOffset = static_cast<std::uint32_t>(offsetof(CompositePush, hdrSlot)) },
{ .group = 2, .binding = 1, .kind = UICustomBindingKind::SampledTexture,
.pushOffset = static_cast<std::uint32_t>(offsetof(CompositePush, bloomSlot)) },
{ .group = 2, .binding = 2, .kind = UICustomBindingKind::Sampler,
.pushOffset = static_cast<std::uint32_t>(offsetof(CompositePush, sampSlot)) },
};
WebGPUComputeShader composite;
composite.Load(fs::path("composite.comp.wgsl"), compBindings);
window.FinishInit();
// ── Passes: RT first (writes HDR scene), then UI (composite→canvas).
RTPass rtPass(&pipeline);
rtPass.handlesPtr = rtHandles.data();
rtPass.handlesCount = static_cast<std::uint32_t>(rtHandles.size());
rtPass.maxDepth = 1; // primary rays only
rtPass.outTexHandle = hdrScene.handle; // ← RESOLVE target
window.passes.push_back(&rtPass);
window.passes.push_back(&ui);
// ── Static camera framing the grid from a front corner. ────────────
const float ext = float(kGrid - 1) * kSpacing;
Vector<float, 3, 4> camPos { ext * 1.1f, ext * 0.8f, ext * 1.6f + 3.0f };
Vector<float, 3, 4> d { -camPos.x, -camPos.y, -camPos.z };
const float dl = std::sqrt(d.x*d.x + d.y*d.y + d.z*d.z);
Vector<float, 3, 4> forward { d.x/dl, d.y/dl, d.z/dl };
Vector<float, 3, 4> worldUp { 0.0f, 1.0f, 0.0f };
Vector<float, 3, 4> right { forward.y*worldUp.z - forward.z*worldUp.y,
forward.z*worldUp.x - forward.x*worldUp.z,
forward.x*worldUp.y - forward.y*worldUp.x };
const float rl = std::sqrt(right.x*right.x + right.y*right.y + right.z*right.z);
right.x /= rl; right.y /= rl; right.z /= rl;
Vector<float, 3, 4> up { right.y*forward.z - right.z*forward.y,
right.z*forward.x - right.x*forward.z,
right.x*forward.y - right.y*forward.x };
{
CameraGPU& g = cameraBuf.value[0];
g.origin[0]=camPos.x; g.origin[1]=camPos.y; g.origin[2]=camPos.z; g.pad0=0;
g.right[0]=right.x; g.right[1]=right.y; g.right[2]=right.z;
g.up[0]=up.x; g.up[1]=up.y; g.up[2]=up.z;
g.forward[0]=forward.x; g.forward[1]=forward.y; g.forward[2]=forward.z;
g.aspect = float(window.width) / float(window.height);
g.tanHalf = std::tan(60.0f * 3.14159265f / 360.0f);
g.pad1 = 0;
cameraBuf.FlushDevice();
}
// ── Bloom prepass: threshold + blur, each its own submit. ──────────
EventListener<void> bloomTick(&window.onBeforeUpdate, [&]() {
Dim dim { static_cast<std::uint32_t>(window.width),
static_cast<std::uint32_t>(window.height), 0, 0 };
const std::uint32_t gx = (window.width + 7u) / 8u;
const std::uint32_t gy = (window.height + 7u) / 8u;
threshold.Dispatch(&dim, sizeof(dim), thresholdHandles, gx, gy, 1);
blur.Dispatch(&dim, sizeof(dim), blurHandles, gx, gy, 1);
});
// ── Composite: scene + bloom → tonemap+gamma → canvas. ─────────────
EventListener<UIBuildArgs> composeSub(&ui.onBuild, [&](UIBuildArgs a) {
CompositePush pc { ui.FillHeader(0, 0), 0, 0, 0, 0 };
pc.hdrSlot = static_cast<std::uint32_t>(static_cast<std::uint16_t>(hdrSlot));
pc.bloomSlot = static_cast<std::uint32_t>(static_cast<std::uint16_t>(bloomSlot));
pc.sampSlot = static_cast<std::uint32_t>(static_cast<std::uint16_t>(sampSlot));
const std::uint32_t gx = (window.width + 7u) / 8u;
const std::uint32_t gy = (window.height + 7u) / 8u;
ui.Dispatch(a.cmd, composite, &pc, sizeof(pc), gx, gy, 1);
});
std::println("[HDRBloom] RT→rgba16float→threshold→blur→composite running");
window.Render();
window.StartUpdate();
window.StartSync();
return 0;
}
#endif