2026-07-22 18:09:06 +02:00
|
|
|
//SPDX-License-Identifier: MIT
|
|
|
|
|
//SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®
|
|
|
|
|
|
2026-05-19 00:27:09 +02:00
|
|
|
// Sponza on Vulkan + WebGPU. Same example source, two backends — picked
|
|
|
|
|
// by CRAFTER_GRAPHICS_WINDOW_DOM. Both paths:
|
|
|
|
|
// 1. Load a Sponza .cmesh (positions + indices, optional per-vertex
|
|
|
|
|
// data region) and a single albedo .ctex from disk. The source
|
|
|
|
|
// assets are fetched once by project.cpp (Crafter.Build::GitFetch)
|
|
|
|
|
// from https://github.com/jimmiebergmann/Sponza and compressed
|
|
|
|
|
// into the bin dir at build time — they don't live in this repo.
|
|
|
|
|
// 2. Build BLAS + TLAS via the existing Mesh / RenderingElement3D
|
|
|
|
|
// flow. The on-disk format is identical between backends; only
|
|
|
|
|
// the decompression path differs (VK_EXT_memory_decompression
|
|
|
|
|
// on Vulkan, CPU GDeflate on WebGPU).
|
|
|
|
|
// 3. Upload the albedo as Image2D<RGBA8>, register it in the
|
|
|
|
|
// backend descriptor heap, and run the RT pipeline. Closest-hit
|
|
|
|
|
// shaders sample the texture at the hit's barycentric coords —
|
|
|
|
|
// proof-of-binding rather than UV-correct shading. Per-vertex
|
|
|
|
|
// UV interpolation is follow-up work (the attribs heap is in
|
|
|
|
|
// place on WebGPU; the Vulkan side needs a sibling data buffer
|
|
|
|
|
// exposed off Mesh).
|
|
|
|
|
//
|
|
|
|
|
// Sponza model: CC BY 3.0 — Frank Meinl (Crytek), packaged by Jimmie
|
|
|
|
|
// Bergmann and Morgan McGuire. https://casual-effects.com/data
|
|
|
|
|
|
|
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
#include "vulkan/vulkan.h"
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
import Crafter.Graphics;
|
|
|
|
|
import Crafter.Asset;
|
|
|
|
|
import Crafter.Math;
|
|
|
|
|
import Crafter.Event;
|
|
|
|
|
import std;
|
|
|
|
|
|
|
|
|
|
using namespace Crafter;
|
|
|
|
|
namespace fs = std::filesystem;
|
|
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
|
struct RGBA8 { std::uint8_t r, g, b, a; };
|
|
|
|
|
|
|
|
|
|
void RequireAssets(const fs::path& mesh, const fs::path& tex) {
|
|
|
|
|
const bool haveMesh = fs::exists(mesh);
|
|
|
|
|
const bool haveTex = fs::exists(tex);
|
|
|
|
|
if (haveMesh && haveTex) return;
|
|
|
|
|
std::println(std::cerr,
|
|
|
|
|
"[Sponza] missing asset(s):\n"
|
|
|
|
|
" mesh: {} {}\n"
|
|
|
|
|
" albedo: {} {}\n"
|
|
|
|
|
"The build should have populated these via cfg.assets +\n"
|
|
|
|
|
"GitFetch (see examples/Sponza/project.cpp). If you ran\n"
|
|
|
|
|
"the binary from outside its bin dir, cd into the bin dir\n"
|
|
|
|
|
"first — asset paths are relative to cwd.",
|
|
|
|
|
mesh.string(), haveMesh ? "OK" : "MISSING",
|
|
|
|
|
tex.string(), haveTex ? "OK" : "MISSING");
|
|
|
|
|
std::abort();
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
int main() {
|
|
|
|
|
// Native Vulkan path is single-material for now (see file header) —
|
|
|
|
|
// pick up just the first per-material output the build emits. The
|
|
|
|
|
// WebGPU branch below uses every mesh + a texture array.
|
|
|
|
|
const fs::path meshPath = "mesh_0.cmesh";
|
|
|
|
|
const fs::path texPath = "tex_0.ctex";
|
|
|
|
|
RequireAssets(meshPath, texPath);
|
|
|
|
|
|
|
|
|
|
CompressedMeshAsset loadedMesh = LoadCompressedMesh(meshPath);
|
|
|
|
|
CompressedTextureAsset loadedTex = LoadCompressedTexture(texPath);
|
|
|
|
|
std::println("[Sponza] loaded {} verts, {} idx, {}x{} albedo",
|
|
|
|
|
loadedMesh.vertexCount, loadedMesh.indexCount,
|
|
|
|
|
loadedTex.sizeX, loadedTex.sizeY);
|
|
|
|
|
|
feat(device): applications ask for the device features their shaders use
Device
- Device::Initialize(required, optional) takes DeviceFeatures, the five
core feature structs vulkan10 to vulkan14. The library enables only what
its own shaders and code use. Device::enabledFeatures says what was
enabled, supportedFeatures what the GPU has, apiVersion the version in
use.
- shaderInt16, shaderFloat16, storageBuffer16BitAccess, scalarBlockLayout
and the uniform-buffer, storage-buffer and storage-image non-uniform
indexing bits are no longer enabled for everyone. An application whose
shaders take uint16_t spec constants passes
{.vulkan10 = {.shaderInt16 = VK_TRUE}}. scalarBlockLayout stays on with
the NVIDIA workaround, whose TLAS address may sit in a struct's tail
padding.
- Every GPU is weighed before one is chosen: Vulkan 1.3, the swapchain and,
below 1.4, maintenance5 extensions, the library's needs, the required
features. One that can't run the application is skipped, saying why when
it ranks higher. A CPU device runs it only when nothing else is listed,
and CRAFTER_GRAPHICS_DEVICE never falls back. A GPU two drivers both list
is tried through each.
- When no GPU qualifies, Initialize throws naming each GPU's gaps. It
destroys the instance it made, before any Wayland connection, so it can
be called again asking for less.
- maintenance5 is vulkan14's on a 1.4 GPU and VK_KHR_maintenance5's below.
CRAFTER_GRAPHICS_NO_VULKAN_1_4 runs as a 1.3 application, to exercise
that path on a 1.4 GPU.
- VK_KHR_spirv_1_4 and VK_KHR_shader_float_controls, core since 1.2, are no
longer enabled, nor VK_EXT_shader_atomic_float, which was enabled without
its feature struct. memoryDecompression's feature bit is queried before
it is enabled.
Shaders
- VulkanShader checks a module's capabilities, declared directly or
implicitly, against the enabled core features, the GPU's subgroup
operations and the optional groups, and throws naming the field to pass,
or saying the GPU lacks it. The tables are generated from vk.xml and
SPIR-V's grammar.
- WorkaroundNvidiaAS::Patch sized a row-major matrix push member by its
columns, so the TLAS address could land inside it.
Window
- The swapchain format is one whose own feature flags allow storage reads
and writes without a format, which since Vulkan 1.3 each format says for
itself; shaderStorageImageRead/WriteWithoutFormat are no longer required.
Tests
- DeviceFeatures: ResolveFeatures, ChooseDevice and CheckShaderCapabilities,
without a GPU.
- FeatureRequests: required and optional features end to end, the 1.3
path, and a retry after a refusal.
- PushConstantRewrite: a row-major mat3x4 push member.
- HeapASRead, HeapDynamicIndexHit, RTPassPushData and the ray-tracing
examples ask for the features their shaders use.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 06:40:02 +01:00
|
|
|
// The raygen and closest-hit shaders take heap slots as uint16_t spec
|
|
|
|
|
// constants.
|
|
|
|
|
Device::Initialize({.vulkan10 = {.shaderInt16 = VK_TRUE}});
|
2026-05-19 00:27:09 +02:00
|
|
|
Window window(1280, 720, "Sponza");
|
|
|
|
|
VkCommandBuffer cmd = window.StartInit();
|
|
|
|
|
|
|
|
|
|
DescriptorHeapVulkan descriptorHeap;
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
descriptorHeap.Initialize(/*images*/ 2, /*buffers*/ 1, /*samplers*/ 1);
|
2026-05-19 00:27:09 +02:00
|
|
|
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
// Specialization constants: the TLAS slot offset for raygen (shared
|
|
|
|
|
// with the VulkanTriangle pattern), and the albedo's image and sampler
|
|
|
|
|
// slots for closesthit.
|
2026-05-19 00:27:09 +02:00
|
|
|
VkSpecializationMapEntry raygenEntry = { .constantID = 0, .offset = 0, .size = sizeof(std::uint16_t) };
|
|
|
|
|
VkSpecializationInfo raygenSpec = {
|
|
|
|
|
.mapEntryCount = 1, .pMapEntries = &raygenEntry,
|
|
|
|
|
.dataSize = sizeof(std::uint16_t), .pData = &descriptorHeap.bufferStartElement,
|
|
|
|
|
};
|
|
|
|
|
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
// Allocate the albedo's slots first so their indices are known when we
|
2026-05-19 00:27:09 +02:00
|
|
|
// compile closesthit.spv.
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
auto imgSlots = descriptorHeap.AllocateImageSlots(2);
|
|
|
|
|
auto bufSlots = descriptorHeap.AllocateBufferSlots(1);
|
|
|
|
|
auto samplerSlots = descriptorHeap.AllocateSamplerSlots(1);
|
2026-05-19 00:27:09 +02:00
|
|
|
std::uint16_t albedoHeapSlot = static_cast<std::uint16_t>(imgSlots.firstElement + 1);
|
|
|
|
|
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
const std::array<std::uint16_t, 2> hitConstants { albedoHeapSlot, samplerSlots.firstElement };
|
|
|
|
|
const std::array<VkSpecializationMapEntry, 2> hitEntries {{
|
|
|
|
|
{ .constantID = 0, .offset = 0, .size = sizeof(std::uint16_t) },
|
|
|
|
|
{ .constantID = 1, .offset = sizeof(std::uint16_t), .size = sizeof(std::uint16_t) },
|
|
|
|
|
}};
|
2026-05-19 00:27:09 +02:00
|
|
|
VkSpecializationInfo hitSpec = {
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
.mapEntryCount = static_cast<std::uint32_t>(hitEntries.size()), .pMapEntries = hitEntries.data(),
|
|
|
|
|
.dataSize = sizeof(hitConstants), .pData = hitConstants.data(),
|
2026-05-19 00:27:09 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
std::array<VulkanShader, 3> shaders {{
|
|
|
|
|
{ "raygen.spv", "main", VK_SHADER_STAGE_RAYGEN_BIT_KHR, &raygenSpec },
|
|
|
|
|
{ "miss.spv", "main", VK_SHADER_STAGE_MISS_BIT_KHR, nullptr },
|
|
|
|
|
{ "closesthit.spv", "main", VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR, &hitSpec },
|
|
|
|
|
}};
|
|
|
|
|
ShaderBindingTableVulkan shaderTable;
|
|
|
|
|
shaderTable.Init(shaders);
|
|
|
|
|
|
|
|
|
|
std::array<VkRayTracingShaderGroupCreateInfoKHR, 1> raygenGroups {{ {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_RAY_TRACING_SHADER_GROUP_CREATE_INFO_KHR,
|
|
|
|
|
.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_GENERAL_KHR,
|
|
|
|
|
.generalShader = 0, .closestHitShader = VK_SHADER_UNUSED_KHR,
|
|
|
|
|
.anyHitShader = VK_SHADER_UNUSED_KHR, .intersectionShader = VK_SHADER_UNUSED_KHR,
|
|
|
|
|
} }};
|
|
|
|
|
std::array<VkRayTracingShaderGroupCreateInfoKHR, 1> missGroups {{ {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_RAY_TRACING_SHADER_GROUP_CREATE_INFO_KHR,
|
|
|
|
|
.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_GENERAL_KHR,
|
|
|
|
|
.generalShader = 1, .closestHitShader = VK_SHADER_UNUSED_KHR,
|
|
|
|
|
.anyHitShader = VK_SHADER_UNUSED_KHR, .intersectionShader = VK_SHADER_UNUSED_KHR,
|
|
|
|
|
} }};
|
|
|
|
|
std::array<VkRayTracingShaderGroupCreateInfoKHR, 1> hitGroups {{ {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_RAY_TRACING_SHADER_GROUP_CREATE_INFO_KHR,
|
|
|
|
|
.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_TRIANGLES_HIT_GROUP_KHR,
|
|
|
|
|
.generalShader = VK_SHADER_UNUSED_KHR, .closestHitShader = 2,
|
|
|
|
|
.anyHitShader = VK_SHADER_UNUSED_KHR, .intersectionShader = VK_SHADER_UNUSED_KHR,
|
|
|
|
|
} }};
|
|
|
|
|
|
|
|
|
|
PipelineRTVulkan pipeline;
|
|
|
|
|
pipeline.Init(cmd, raygenGroups, missGroups, hitGroups, shaderTable);
|
|
|
|
|
|
|
|
|
|
Mesh sponzaMesh;
|
|
|
|
|
sponzaMesh.Build(loadedMesh, cmd);
|
|
|
|
|
|
|
|
|
|
Image2D<RGBA8> albedo;
|
|
|
|
|
albedo.Create(loadedTex.sizeX, loadedTex.sizeY, /*mipLevels*/ 1, cmd,
|
|
|
|
|
VK_FORMAT_R8G8B8A8_UNORM,
|
|
|
|
|
VK_IMAGE_USAGE_TRANSFER_DST_BIT | VK_IMAGE_USAGE_SAMPLED_BIT,
|
|
|
|
|
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
|
|
|
|
|
albedo.Update(loadedTex, cmd, VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
|
|
|
|
|
|
|
|
|
|
static RenderingElement3D renderer;
|
|
|
|
|
renderer.instance = {
|
|
|
|
|
.transform = {},
|
|
|
|
|
.instanceCustomIndex = 0,
|
|
|
|
|
.mask = 0xFF,
|
|
|
|
|
.instanceShaderBindingTableRecordOffset = 0,
|
|
|
|
|
.flags = VK_GEOMETRY_INSTANCE_FORCE_OPAQUE_BIT_KHR,
|
|
|
|
|
.accelerationStructureReference = sponzaMesh.blasAddr,
|
|
|
|
|
};
|
|
|
|
|
MatrixRowMajor<float, 4, 3, 1>::Identity()
|
|
|
|
|
.Store(reinterpret_cast<float*>(renderer.instance.transform.matrix));
|
|
|
|
|
RenderingElement3D::elements.emplace_back(&renderer);
|
|
|
|
|
RenderingElement3D::BuildTLAS(cmd, 0);
|
|
|
|
|
RenderingElement3D::BuildTLAS(cmd, 1);
|
|
|
|
|
RenderingElement3D::BuildTLAS(cmd, 2);
|
|
|
|
|
|
|
|
|
|
window.FinishInit();
|
|
|
|
|
|
fix(window): size the swapchain for its present mode, and key frames in flight by frame instead of image
Window
- CreateSwapchain asked for exactly numFrames (3) images whatever the
surface said, read them into a three-element array, and keyed the
command buffers, the fences and the descriptor-heap copy holding "its"
swapchain image by the acquired image index. A swapchain of another
size fell back to FIFO (asked for MAILBOX or IMMEDIATE) or threw, and a
surface whose minimum is above three got a create info below it
(#160). Mesa's MAILBOX needs four images: Turnip on phoc, llvmpipe on
any Wayland compositor.
- The present mode is picked first, then the swapchain is sized by
SwapchainCapabilities: the surface's counts for that mode where the
instance has surface_maintenance1. With swapchain_maintenance1 the
swapchain names its mode (VkSwapchainPresentModesCreateInfoKHR), which
is what makes the mode's own count the one that applies, at creation and
to the forward progress of a UINT64_MAX acquire; without it the stricter
of the mode's and the surface's counts for all modes. It asks for
numFrames or that minimum where more, never past the maximum
(SwapchainMinImageCount). Turnip's FIFO keeps its three images and
MAILBOX gets four. The FIFO fallback and presentModeUnfit are gone.
- images, imageViewInfos (was imageViews: they are create-infos), the made
imageViews that descriptor sets take, imageInitialised and the
render-finished semaphores are per image, as many as the driver made.
The views are made once per swapchain. The semaphores only grow, since
a present of the old swapchain may still wait on one.
- Frames in flight stay numFrames, keyed by currentFrame, frameCounter %
numFrames: the command buffer, the fence, the acquire semaphore, the
heap copy (or set), RenderingElement3D::tlases, the frameIdx a pass is
recorded with. currentImage is the acquired image. currentBuffer is
gone, so code that used it stops compiling instead of picking the wrong
one; RenderPass::Record's frameIdx keeps its name and is now the frame
slot, as RenderPass.cppm says.
- The frame's fence is waited before the acquire. The acquire semaphores
need no spare then, and a frame waits for exactly the one numFrames
before it, which the deletion queue and the staging rings count on and
fences keyed by image did not promise once images come back out of
order. The swapchain slots are written before the fence is reset.
- From the acquire to the present the window is recording: a Resize or
SetPresentMode from a listener (a VSync key ticked in onUpdate) takes
effect after the present, through RebuildSwapchain, together with a
present that found the swapchain out of date. Rebuilding mid-frame used
to destroy the image the frame was drawing into; with images sized per
swapchain it would also index past the new one's end.
DescriptorHeapVulkan
- Frames and images pair up differently from frame to frame, so no heap
copy can keep one swapchain image. AddSwapchainSlot(slot, window) lists
an image slot as that window's swapchain image, and Window::Render
writes the image a frame acquired into its window's listed slots in that
frame's copy, or its set, before onUpdate, skipping a slot that holds it
already. A slot is one window's, so two windows can share a heap without
writing each other's slots under each other's frames in flight. A slot
listed during a frame its window records is written at once. A slot past
the heap's image slots, an empty ImageSlot's 0xFFFF among them, is
refused. Freeing a slot unlists it, as does initialising the heap in
either binding model. WriteImageSet, the one use of which this
replaces, is gone, and with it the per-frame dimension of setImageViews.
Device
- VK_KHR_surface_maintenance1 (or EXT) and VK_KHR_get_surface_capabilities2
are enabled where the loader has them (surfaceMaintenance1Supported,
vkGetPhysicalDeviceSurfaceCapabilities2KHR), and the matching
swapchain_maintenance1 with its feature where the device has it
(swapchainMaintenance1Supported).
- DistinctGpus groups the physical devices by GPU as CRAFTER_GRAPHICS_DEVICE
numbers them, for ChooseGpu and tests.
UI
- UIRenderer lists its output slot instead of writing every copy itself,
and again on every resize; the resize listener is gone on both
backends. The headers' frameIdx is currentFrame.
Examples
- VulkanTriangle, Sponza, SponzaBench and RTVolume list their output slot
and write only the per-frame TLASes. They wrote imageViews[f] into copy
f once, which a resize left pointing at destroyed images.
Tests
- SwapchainImageCount: SwapchainMinImageCount on the numbers drivers
report; every offered mode keeps its mode and gets what the window asks
for; every frame presents the colour it drew, read back a texel per
frame; a switch and a resize asked for during a frame wait for its
present; a slot listed during a frame holds its image at once; two
windows on one heap draw their own colours. The frame checks run again
in child processes, through CRAFTER_GRAPHICS_DEVICE, on a GPU whose
swapchains have more images than frames (this one, else llvmpipe), in
each binding model the parent didn't cover; a child skips only for a GPU
that can't run the library, and checks it runs the model it was asked
for.
- FrameLoopSync checks the frame slot follows the frame counter and counts
the swapchain's own images. HeapASRead, HeapDynamicIndexHit and
RTPassPushData list their swapchain slot and drop their resize rewrites.
Docs
- README, AGENTS.md and AGENTS.consumer.md: frames and images, the
swapchain slots, rebuilds held to the present, the new optional groups.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:51:18 +01:00
|
|
|
// Write descriptors: TLAS at bufSlots[0] and albedo (a sampled image) at
|
|
|
|
|
// imgSlots[1], into every frame's copy of the heap, each frame with its
|
|
|
|
|
// own TLAS, and the albedo's sampler at samplerSlots[0] in the sampler
|
|
|
|
|
// heap. The output image at imgSlots[0] is the swapchain's, which the
|
|
|
|
|
// window writes every frame with the image that frame draws into.
|
|
|
|
|
descriptorHeap.AddSwapchainSlot(imgSlots.firstElement, window);
|
2026-05-19 00:27:09 +02:00
|
|
|
VkDeviceAddressRangeKHR tlasRanges[Window::numFrames];
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
// The heap takes an image view's create-info, not a VkImageView.
|
|
|
|
|
const VkImageViewCreateInfo albedoView {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
|
|
|
|
|
.image = albedo.image,
|
|
|
|
|
.viewType = VK_IMAGE_VIEW_TYPE_2D,
|
|
|
|
|
.format = VK_FORMAT_R8G8B8A8_UNORM,
|
|
|
|
|
.subresourceRange = {
|
|
|
|
|
.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT,
|
|
|
|
|
.levelCount = albedo.mipLevels,
|
|
|
|
|
.layerCount = 1,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
const VkImageDescriptorInfoEXT albedoInfo {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_IMAGE_DESCRIPTOR_INFO_EXT,
|
|
|
|
|
.pView = &albedoView,
|
|
|
|
|
.layout = VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL,
|
2026-05-19 00:27:09 +02:00
|
|
|
};
|
|
|
|
|
for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
|
|
|
|
|
tlasRanges[f] = { .address = RenderingElement3D::tlases[f].address };
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
std::vector<VkResourceDescriptorInfoEXT> resources;
|
|
|
|
|
std::vector<VkHostAddressRangeEXT> destinations;
|
fix(window): size the swapchain for its present mode, and key frames in flight by frame instead of image
Window
- CreateSwapchain asked for exactly numFrames (3) images whatever the
surface said, read them into a three-element array, and keyed the
command buffers, the fences and the descriptor-heap copy holding "its"
swapchain image by the acquired image index. A swapchain of another
size fell back to FIFO (asked for MAILBOX or IMMEDIATE) or threw, and a
surface whose minimum is above three got a create info below it
(#160). Mesa's MAILBOX needs four images: Turnip on phoc, llvmpipe on
any Wayland compositor.
- The present mode is picked first, then the swapchain is sized by
SwapchainCapabilities: the surface's counts for that mode where the
instance has surface_maintenance1. With swapchain_maintenance1 the
swapchain names its mode (VkSwapchainPresentModesCreateInfoKHR), which
is what makes the mode's own count the one that applies, at creation and
to the forward progress of a UINT64_MAX acquire; without it the stricter
of the mode's and the surface's counts for all modes. It asks for
numFrames or that minimum where more, never past the maximum
(SwapchainMinImageCount). Turnip's FIFO keeps its three images and
MAILBOX gets four. The FIFO fallback and presentModeUnfit are gone.
- images, imageViewInfos (was imageViews: they are create-infos), the made
imageViews that descriptor sets take, imageInitialised and the
render-finished semaphores are per image, as many as the driver made.
The views are made once per swapchain. The semaphores only grow, since
a present of the old swapchain may still wait on one.
- Frames in flight stay numFrames, keyed by currentFrame, frameCounter %
numFrames: the command buffer, the fence, the acquire semaphore, the
heap copy (or set), RenderingElement3D::tlases, the frameIdx a pass is
recorded with. currentImage is the acquired image. currentBuffer is
gone, so code that used it stops compiling instead of picking the wrong
one; RenderPass::Record's frameIdx keeps its name and is now the frame
slot, as RenderPass.cppm says.
- The frame's fence is waited before the acquire. The acquire semaphores
need no spare then, and a frame waits for exactly the one numFrames
before it, which the deletion queue and the staging rings count on and
fences keyed by image did not promise once images come back out of
order. The swapchain slots are written before the fence is reset.
- From the acquire to the present the window is recording: a Resize or
SetPresentMode from a listener (a VSync key ticked in onUpdate) takes
effect after the present, through RebuildSwapchain, together with a
present that found the swapchain out of date. Rebuilding mid-frame used
to destroy the image the frame was drawing into; with images sized per
swapchain it would also index past the new one's end.
DescriptorHeapVulkan
- Frames and images pair up differently from frame to frame, so no heap
copy can keep one swapchain image. AddSwapchainSlot(slot, window) lists
an image slot as that window's swapchain image, and Window::Render
writes the image a frame acquired into its window's listed slots in that
frame's copy, or its set, before onUpdate, skipping a slot that holds it
already. A slot is one window's, so two windows can share a heap without
writing each other's slots under each other's frames in flight. A slot
listed during a frame its window records is written at once. A slot past
the heap's image slots, an empty ImageSlot's 0xFFFF among them, is
refused. Freeing a slot unlists it, as does initialising the heap in
either binding model. WriteImageSet, the one use of which this
replaces, is gone, and with it the per-frame dimension of setImageViews.
Device
- VK_KHR_surface_maintenance1 (or EXT) and VK_KHR_get_surface_capabilities2
are enabled where the loader has them (surfaceMaintenance1Supported,
vkGetPhysicalDeviceSurfaceCapabilities2KHR), and the matching
swapchain_maintenance1 with its feature where the device has it
(swapchainMaintenance1Supported).
- DistinctGpus groups the physical devices by GPU as CRAFTER_GRAPHICS_DEVICE
numbers them, for ChooseGpu and tests.
UI
- UIRenderer lists its output slot instead of writing every copy itself,
and again on every resize; the resize listener is gone on both
backends. The headers' frameIdx is currentFrame.
Examples
- VulkanTriangle, Sponza, SponzaBench and RTVolume list their output slot
and write only the per-frame TLASes. They wrote imageViews[f] into copy
f once, which a resize left pointing at destroyed images.
Tests
- SwapchainImageCount: SwapchainMinImageCount on the numbers drivers
report; every offered mode keeps its mode and gets what the window asks
for; every frame presents the colour it drew, read back a texel per
frame; a switch and a resize asked for during a frame wait for its
present; a slot listed during a frame holds its image at once; two
windows on one heap draw their own colours. The frame checks run again
in child processes, through CRAFTER_GRAPHICS_DEVICE, on a GPU whose
swapchains have more images than frames (this one, else llvmpipe), in
each binding model the parent didn't cover; a child skips only for a GPU
that can't run the library, and checks it runs the model it was asked
for.
- FrameLoopSync checks the frame slot follows the frame counter and counts
the swapchain's own images. HeapASRead, HeapDynamicIndexHit and
RTPassPushData list their swapchain slot and drop their resize rewrites.
Docs
- README, AGENTS.md and AGENTS.consumer.md: frames and images, the
swapchain slots, rebuilds held to the present, the new optional groups.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:51:18 +01:00
|
|
|
resources.reserve(Window::numFrames * 2);
|
|
|
|
|
destinations.reserve(Window::numFrames * 2);
|
2026-05-19 00:27:09 +02:00
|
|
|
for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
|
|
|
|
|
resources.push_back({
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_RESOURCE_DESCRIPTOR_INFO_EXT,
|
|
|
|
|
.type = VK_DESCRIPTOR_TYPE_ACCELERATION_STRUCTURE_KHR,
|
|
|
|
|
.data = { .pAddressRange = &tlasRanges[f] },
|
|
|
|
|
});
|
|
|
|
|
destinations.push_back({
|
|
|
|
|
.address = descriptorHeap.resourceHeap[f].value
|
|
|
|
|
+ descriptorHeap.BufferByteOffset(bufSlots.firstElement),
|
|
|
|
|
.size = Device::descriptorHeapProperties.bufferDescriptorSize,
|
|
|
|
|
});
|
|
|
|
|
resources.push_back({
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_RESOURCE_DESCRIPTOR_INFO_EXT,
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
.type = VK_DESCRIPTOR_TYPE_SAMPLED_IMAGE,
|
|
|
|
|
.data = { .pImage = &albedoInfo },
|
2026-05-19 00:27:09 +02:00
|
|
|
});
|
|
|
|
|
destinations.push_back({
|
|
|
|
|
.address = descriptorHeap.resourceHeap[f].value
|
|
|
|
|
+ descriptorHeap.ImageByteOffset(albedoHeapSlot),
|
|
|
|
|
.size = Device::descriptorHeapProperties.imageDescriptorSize,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
Device::vkWriteResourceDescriptorsEXT(Device::device,
|
|
|
|
|
static_cast<std::uint32_t>(resources.size()),
|
|
|
|
|
resources.data(), destinations.data());
|
|
|
|
|
for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
|
|
|
|
|
descriptorHeap.resourceHeap[f].FlushDevice();
|
|
|
|
|
}
|
|
|
|
|
|
fix(rt): split Sponza's combined image sampler into a heap texture and sampler
examples/Sponza no longer built natively (#164). Its closest-hit declared a
descriptor_heap sampler2D, which glslang has rejected since c8253623
("Reject descriptor_heap combined image samplers"), and main.cpp wrote it
through VkResourceDescriptorDataEXT::pCombinedImageSampler, which that union
no longer has: the descriptor heap has no combined image samplers. Both went
unnoticed because nothing builds the examples.
Sponza
- closesthit.glsl declares texture2D and sampler heap arrays and joins them
where it samples, as ui-shared.glsl and HeapDynamicIndexHit do. The
sampler slot is a second spec constant beside the image slot, so the
shader assumes nothing about where the host put it, and a constant index
keeps the example running on NVIDIA 610.43.02 (see its README). The
comment no longer says the image slot is offset by bufferStartElement;
only buffer slots are.
- main.cpp gives the heap a sampler slot, writes the albedo as a
SAMPLED_IMAGE from a view create-info, and writes the sampler into the
sampler heap from a VkSamplerCreateInfo with vkWriteSamplerDescriptorsEXT,
as UIRenderer::RegisterSampler does. SamplerVulkan's VkSampler had no use
left. The sampler keeps its linear filtering and repeat addressing and
drops anisotropy, which a hit shader cannot use: it samples at LOD 0,
without derivatives.
Docs
- README.md and examples/Sponza/README.md quote the new declarations, and
the Sponza README says why the texture and the sampler are two
descriptors. Its texture2DArray materials pattern declared a
descriptor_heap sampler2DArray, which glslang rejects as well; it now
joins a texture2DArray and a sampler.
- examples/SponzaBench/README.md drops its caveat that Sponza does not
compile.
Tests
- ExampleShaders compiles every GLSL shader under examples/ with glslang as
crafter-build does for the example (Vulkan rules, SPIR-V 1.4, shaders/ on
the include path, and the descriptor-set build where the example
registers one), so a glslang that starts rejecting one fails a test
rather than an example build nobody runs. It fails on Sponza's old
closest-hit and needs glslang only.
Closes #164.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 08:25:52 +01:00
|
|
|
// The sampler heap takes a sampler's create-info, as
|
|
|
|
|
// UIRenderer::RegisterSampler writes it.
|
|
|
|
|
const VkSamplerCreateInfo albedoSamplerInfo {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO,
|
|
|
|
|
.magFilter = VK_FILTER_LINEAR,
|
|
|
|
|
.minFilter = VK_FILTER_LINEAR,
|
|
|
|
|
.mipmapMode = VK_SAMPLER_MIPMAP_MODE_LINEAR,
|
|
|
|
|
.addressModeU = VK_SAMPLER_ADDRESS_MODE_REPEAT,
|
|
|
|
|
.addressModeV = VK_SAMPLER_ADDRESS_MODE_REPEAT,
|
|
|
|
|
.addressModeW = VK_SAMPLER_ADDRESS_MODE_REPEAT,
|
|
|
|
|
.maxLod = VK_LOD_CLAMP_NONE,
|
|
|
|
|
};
|
|
|
|
|
VkSamplerCreateInfo samplerInfos[Window::numFrames];
|
|
|
|
|
VkHostAddressRangeEXT samplerDestinations[Window::numFrames];
|
|
|
|
|
for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
|
|
|
|
|
samplerInfos[f] = albedoSamplerInfo;
|
|
|
|
|
samplerDestinations[f] = {
|
|
|
|
|
.address = descriptorHeap.samplerHeap[f].value
|
|
|
|
|
+ descriptorHeap.SamplerByteOffset(samplerSlots.firstElement),
|
|
|
|
|
.size = Device::descriptorHeapProperties.samplerDescriptorSize,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
Device::vkWriteSamplerDescriptorsEXT(Device::device, Window::numFrames,
|
|
|
|
|
samplerInfos, samplerDestinations);
|
|
|
|
|
for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
|
|
|
|
|
descriptorHeap.samplerHeap[f].FlushDevice();
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-19 00:27:09 +02:00
|
|
|
window.descriptorHeap = &descriptorHeap;
|
|
|
|
|
RTPass rtPass(&pipeline);
|
|
|
|
|
window.passes.push_back(&rtPass);
|
|
|
|
|
|
|
|
|
|
window.Render();
|
|
|
|
|
window.StartSync();
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
#else
|
|
|
|
|
int main() {
|
|
|
|
|
// ── Read scene manifest (produced by project.cpp's ImportSponzaBundle).
|
|
|
|
|
//
|
|
|
|
|
// line 1: albedoCount
|
|
|
|
|
// line 2: meshCount
|
|
|
|
|
// line 3..: per-mesh albedoIdx (-1 means "no albedo")
|
|
|
|
|
const fs::path manifestPath = "scene.txt";
|
|
|
|
|
if (!fs::exists(manifestPath)) {
|
|
|
|
|
std::println(std::cerr,
|
|
|
|
|
"[Sponza] missing scene.txt — the build should have produced "
|
|
|
|
|
"it (see examples/Sponza/project.cpp). If you ran the binary "
|
|
|
|
|
"from outside its bin dir, cd in first.");
|
|
|
|
|
std::abort();
|
|
|
|
|
}
|
|
|
|
|
std::ifstream manifest(manifestPath);
|
|
|
|
|
std::uint32_t albedoCount = 0, meshCount = 0;
|
|
|
|
|
manifest >> albedoCount >> meshCount;
|
|
|
|
|
std::vector<std::int32_t> meshAlbedo(meshCount);
|
|
|
|
|
for (std::uint32_t i = 0; i < meshCount; ++i) manifest >> meshAlbedo[i];
|
|
|
|
|
std::println("[Sponza] scene: {} albedos, {} meshes", albedoCount, meshCount);
|
|
|
|
|
|
|
|
|
|
Device::Initialize();
|
|
|
|
|
static Window window(1280, 720, "Sponza");
|
|
|
|
|
auto cmd = window.StartInit();
|
|
|
|
|
|
|
|
|
|
DescriptorHeapWebGPU heap;
|
|
|
|
|
heap.Initialize(/*images*/ 2, /*buffers*/ 2, /*samplers*/ 2);
|
|
|
|
|
|
2026-05-31 20:16:04 +00:00
|
|
|
std::array<WebGPUShader, 4> shaders {{
|
2026-05-19 00:27:09 +02:00
|
|
|
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),
|
2026-05-31 20:16:04 +00:00
|
|
|
WebGPUShader(fs::path("resolve.wgsl"), "resolve_main", WebGPURTStage::Resolve),
|
2026-05-19 00:27:09 +02:00
|
|
|
}};
|
|
|
|
|
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 },
|
|
|
|
|
}};
|
|
|
|
|
|
2026-05-31 20:16:04 +00:00
|
|
|
// Three user bindings at @group(3) (the wavefront pipeline reserves
|
|
|
|
|
// groups 0..2 for WfParams / data heaps / indirect args):
|
2026-05-19 00:27:09 +02:00
|
|
|
// binding 0 — albedo texture_2d_array (one layer per material)
|
|
|
|
|
// binding 1 — sampler (linear clamp)
|
|
|
|
|
// binding 2 — Camera storage buffer (host-driven, updated per frame)
|
|
|
|
|
std::array<UICustomBinding, 3> bindings {{
|
2026-06-09 12:55:14 +00:00
|
|
|
{ .group = 3, .binding = 0, .kind = UICustomBindingKind::SampledTextureArray, .pushOffset = 0 },
|
|
|
|
|
{ .group = 3, .binding = 1, .kind = UICustomBindingKind::Sampler, .pushOffset = 0 },
|
|
|
|
|
{ .group = 3, .binding = 2, .kind = UICustomBindingKind::Buffer, .pushOffset = 0 },
|
2026-05-19 00:27:09 +02:00
|
|
|
}};
|
|
|
|
|
|
|
|
|
|
PipelineRTWebGPU pipeline;
|
|
|
|
|
pipeline.Init(cmd, raygenGroups, missGroups, hitGroups, sbt, bindings);
|
|
|
|
|
|
|
|
|
|
// ── Albedo texture array — one rgba8unorm layer per material. ──────
|
|
|
|
|
//
|
|
|
|
|
// Probe layer 0 for the canonical layer dimensions; project.cpp
|
|
|
|
|
// already resized every albedo to the same square so any tex_N.ctex
|
|
|
|
|
// would do, layer 0 is just the first one we have.
|
|
|
|
|
Image2DArray<RGBA8> albedoArray;
|
|
|
|
|
{
|
|
|
|
|
CompressedTextureAsset probe = LoadCompressedTexture("tex_0.ctex");
|
|
|
|
|
albedoArray.Create(probe.sizeX, probe.sizeY, static_cast<std::uint16_t>(albedoCount));
|
|
|
|
|
albedoArray.UpdateLayer(0, probe);
|
|
|
|
|
for (std::uint32_t i = 1; i < albedoCount; ++i) {
|
|
|
|
|
CompressedTextureAsset tex = LoadCompressedTexture(std::format("tex_{}.ctex", i));
|
|
|
|
|
albedoArray.UpdateLayer(static_cast<std::uint16_t>(i), tex);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
auto albedoArraySlot = albedoArray.AllocateSlot(heap);
|
|
|
|
|
SamplerSlot samplerSlot = AllocateLinearClampSampler(heap);
|
|
|
|
|
|
|
|
|
|
// Camera storage buffer — host writes (origin, right, up, forward,
|
|
|
|
|
// aspect, tanHalf) every frame from the input-driven free camera
|
|
|
|
|
// below. Layout matches the WGSL Camera struct in raygen.wgsl
|
|
|
|
|
// (vec3-aligned, std430). 64 bytes total.
|
|
|
|
|
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);
|
|
|
|
|
WebGPUBuffer<CameraGPU, true> cameraBuf;
|
|
|
|
|
cameraBuf.Create(1);
|
|
|
|
|
|
|
|
|
|
// Handle array fed to RTPass — order matches the bindings declaration.
|
|
|
|
|
static std::array<std::uint32_t, 3> userHandles {
|
|
|
|
|
heap.imageTable [albedoArraySlot.firstElement],
|
|
|
|
|
heap.samplerTable[samplerSlot.firstElement],
|
|
|
|
|
cameraBuf.handle,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
// ── Meshes + scene instances ───────────────────────────────────────
|
|
|
|
|
//
|
|
|
|
|
// One Mesh + one RenderingElement3D per material group from
|
|
|
|
|
// scene.txt. Meshes whose albedoIdx is -1 (the .obj's `usemtl` named
|
|
|
|
|
// something without a map_Kd in .mtl) get dropped — they're rare in
|
|
|
|
|
// Sponza and we'd have nothing to sample for them anyway.
|
|
|
|
|
//
|
|
|
|
|
// Vector capacity is reserved up-front: RenderingElement3D::Add
|
|
|
|
|
// takes a pointer that's stored in the static elements[] vector, so
|
|
|
|
|
// any later vector reallocation would dangle those pointers.
|
|
|
|
|
static std::vector<Mesh> meshes;
|
|
|
|
|
static std::vector<RenderingElement3D> renderers;
|
|
|
|
|
meshes.reserve(meshCount);
|
|
|
|
|
renderers.reserve(meshCount);
|
|
|
|
|
|
|
|
|
|
for (std::uint32_t i = 0; i < meshCount; ++i) {
|
|
|
|
|
if (meshAlbedo[i] < 0) continue;
|
|
|
|
|
CompressedMeshAsset loaded = LoadCompressedMesh(std::format("mesh_{}.cmesh", i));
|
|
|
|
|
meshes.emplace_back();
|
|
|
|
|
meshes.back().Build(loaded, cmd);
|
|
|
|
|
|
|
|
|
|
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] = 0;
|
|
|
|
|
tx[1][0] = 0; tx[1][1] = 1; tx[1][2] = 0; tx[1][3] = 0;
|
|
|
|
|
tx[2][0] = 0; tx[2][1] = 0; tx[2][2] = 1; tx[2][3] = 0;
|
|
|
|
|
// 24-bit instanceCustomIndex carries the albedo array layer that
|
|
|
|
|
// closesthit.wgsl reads as `hit.customIndex`.
|
|
|
|
|
r.instance.instanceCustomIndex = static_cast<std::uint32_t>(meshAlbedo[i]);
|
|
|
|
|
r.instance.mask = 0xFF;
|
|
|
|
|
r.instance.instanceShaderBindingTableRecordOffset = 0;
|
|
|
|
|
r.instance.flags = kRTGeometryInstanceForceOpaque;
|
|
|
|
|
r.instance.accelerationStructureReference = meshes.back().blasAddr;
|
|
|
|
|
RenderingElement3D::Add(&r);
|
|
|
|
|
}
|
|
|
|
|
RenderingElement3D::BuildTLAS(cmd, 0);
|
|
|
|
|
|
|
|
|
|
window.descriptorHeap = &heap;
|
|
|
|
|
window.FinishInit();
|
|
|
|
|
|
|
|
|
|
RTPass rtPass(&pipeline);
|
|
|
|
|
rtPass.handlesPtr = userHandles.data();
|
|
|
|
|
rtPass.handlesCount = static_cast<std::uint32_t>(userHandles.size());
|
2026-05-31 20:16:04 +00:00
|
|
|
rtPass.maxDepth = 2; // primary + shadow
|
2026-05-19 00:27:09 +02:00
|
|
|
window.passes.push_back(&rtPass);
|
|
|
|
|
|
|
|
|
|
// ── Free camera: WASD + mouse-delta look ───────────────────────────
|
|
|
|
|
//
|
|
|
|
|
// Initial pose puts the camera near one end of the atrium at eye
|
|
|
|
|
// height, looking +X down the long axis (bbox: X[-1921..1800],
|
|
|
|
|
// Y[-126..1429], Z[-1183..1105]). The user can fine-tune from there.
|
|
|
|
|
struct CamState {
|
2026-05-31 20:16:04 +00:00
|
|
|
// 3/4 view from a corner aimed at the atrium centre.
|
|
|
|
|
Vector<float, 3, 4> position{ -1400.0f, 700.0f, -600.0f };
|
|
|
|
|
float yaw = 0.405f; // radians, around world +Y
|
|
|
|
|
float pitch = -0.317f; // radians, +pitch looks up
|
2026-05-19 00:27:09 +02:00
|
|
|
} cam;
|
|
|
|
|
|
|
|
|
|
Input::Map inputMap;
|
|
|
|
|
Input::Action& moveAct = inputMap.AddAction("Move", Input::ActionType::Vector2);
|
|
|
|
|
Input::Action& lookAct = inputMap.AddAction("Look", Input::ActionType::Vector2);
|
|
|
|
|
moveAct.bindings = {
|
|
|
|
|
Input::WASDBind{
|
|
|
|
|
Key(CrafterKeys::W), Key(CrafterKeys::S),
|
|
|
|
|
Key(CrafterKeys::A), Key(CrafterKeys::D),
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
lookAct.bindings = {
|
|
|
|
|
Input::MouseDeltaBind{ 1.0f },
|
|
|
|
|
};
|
|
|
|
|
inputMap.Attach(window);
|
|
|
|
|
|
|
|
|
|
constexpr float kMoveSpeed = 1200.0f; // Sponza units / second (room is ~3700 wide)
|
|
|
|
|
constexpr float kLookSens = 0.05f; // radians per mouse pixel
|
|
|
|
|
constexpr float kDt = 1.0f / 60.0f;
|
|
|
|
|
|
|
|
|
|
EventListener<void> camTick(&window.onBeforeUpdate, [&]() {
|
|
|
|
|
inputMap.Tick();
|
|
|
|
|
|
|
|
|
|
cam.yaw += lookAct.vector2.x * kLookSens;
|
|
|
|
|
cam.pitch -= lookAct.vector2.y * kLookSens;
|
|
|
|
|
// Keep pitch just shy of straight up/down so the basis vectors
|
|
|
|
|
// don't collapse (cross(forward, world_up) would go zero).
|
|
|
|
|
cam.pitch = std::clamp(cam.pitch, -1.55f, 1.55f);
|
|
|
|
|
|
|
|
|
|
const float cp = std::cos(cam.pitch), sp = std::sin(cam.pitch);
|
|
|
|
|
const float cy = std::cos(cam.yaw), sy = std::sin(cam.yaw);
|
|
|
|
|
Vector<float, 3, 4> forward { cp * cy, sp, cp * sy };
|
|
|
|
|
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 rLen = std::sqrt(right.x*right.x + right.y*right.y + right.z*right.z);
|
|
|
|
|
right.x /= rLen; right.y /= rLen; right.z /= rLen;
|
|
|
|
|
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 };
|
|
|
|
|
|
|
|
|
|
const float dx = moveAct.vector2.x * kMoveSpeed * kDt;
|
|
|
|
|
const float dy = moveAct.vector2.y * kMoveSpeed * kDt;
|
|
|
|
|
cam.position.x += right.x * dx + forward.x * dy;
|
|
|
|
|
cam.position.y += right.y * dx + forward.y * dy;
|
|
|
|
|
cam.position.z += right.z * dx + forward.z * dy;
|
|
|
|
|
|
|
|
|
|
CameraGPU& g = cameraBuf.value[0];
|
|
|
|
|
g.origin[0] = cam.position.x; g.origin[1] = cam.position.y; g.origin[2] = cam.position.z; g.pad0 = 0.0f;
|
|
|
|
|
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(70.0f * 3.14159265f / 360.0f);
|
|
|
|
|
g.pad1 = 0.0f;
|
|
|
|
|
cameraBuf.FlushDevice();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
window.Render();
|
|
|
|
|
window.StartUpdate();
|
|
|
|
|
window.StartSync();
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
#endif
|