2026-07-22 18:09:06 +02:00
|
|
|
//SPDX-License-Identifier: LGPL-3.0-only
|
|
|
|
|
//SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®
|
2026-03-09 20:10:19 +01:00
|
|
|
|
2026-06-17 19:44:33 +00:00
|
|
|
module;
|
|
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
#include "vulkan/vulkan.h"
|
|
|
|
|
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM
|
2026-05-01 23:35:37 +02:00
|
|
|
export module Crafter.Graphics:RenderPass;
|
2026-03-09 20:10:19 +01:00
|
|
|
import std;
|
2026-05-18 04:58:52 +02:00
|
|
|
import :GraphicsTypes;
|
2026-03-09 20:10:19 +01:00
|
|
|
|
2026-05-01 23:35:37 +02:00
|
|
|
export namespace Crafter {
|
|
|
|
|
struct Window;
|
2026-03-09 20:10:19 +01:00
|
|
|
|
2026-06-17 19:44:33 +00:00
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
// Conservative union of every pipeline stage that can write the swapchain
|
|
|
|
|
// storage image: a compute pass via COMPUTE_SHADER, a ray-tracing pass via
|
|
|
|
|
// RAY_TRACING_SHADER, plus TRANSFER for any blit/copy writer. Used as the
|
|
|
|
|
// RenderPass default (a pass that doesn't narrow its own stage) and as the
|
|
|
|
|
// fallback when there are no passes to derive a real union from. Far tighter
|
|
|
|
|
// than ALL_COMMANDS, but never under-synchronises a polymorphic pass.
|
|
|
|
|
inline constexpr VkPipelineStageFlags kSwapchainWriterStages =
|
|
|
|
|
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT
|
|
|
|
|
| VK_PIPELINE_STAGE_RAY_TRACING_SHADER_BIT_KHR
|
|
|
|
|
| VK_PIPELINE_STAGE_TRANSFER_BIT;
|
|
|
|
|
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
|
2026-05-01 23:35:37 +02:00
|
|
|
struct RenderPass {
|
2026-05-18 04:58:52 +02:00
|
|
|
virtual void Record(GraphicsCommandBuffer cmd, std::uint32_t frameIdx, Window& window) = 0;
|
2026-05-01 23:35:37 +02:00
|
|
|
virtual ~RenderPass() = default;
|
2026-06-17 19:44:33 +00:00
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
// Pipeline stage at which this pass reads and writes the swapchain
|
|
|
|
|
// storage image. The frame loop uses this to scope the inter-pass and
|
|
|
|
|
// frame-edge barriers to the stages that actually touch the image
|
|
|
|
|
// instead of ALL_COMMANDS. A subclass MUST narrow this to its real
|
|
|
|
|
// stage (RTPass -> RAY_TRACING_SHADER, a compute pass -> COMPUTE_SHADER):
|
|
|
|
|
// the default is the conservative writer union so an un-overridden pass
|
|
|
|
|
// can never be under-synchronised, only over-synchronised.
|
|
|
|
|
virtual VkPipelineStageFlags SwapchainStage() const { return kSwapchainWriterStages; }
|
|
|
|
|
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM
|
2026-05-01 23:35:37 +02:00
|
|
|
};
|
2026-06-17 19:44:33 +00:00
|
|
|
|
|
|
|
|
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
|
|
|
|
|
// Union of the swapchain-access stages declared by `passes` — the "real"
|
|
|
|
|
// per-pass stage union the frame-edge barriers (acquire dst / present src)
|
|
|
|
|
// narrow to: an all-compute frame yields COMPUTE_SHADER only, a frame with
|
|
|
|
|
// any RT pass folds in RAY_TRACING_SHADER, and so on. Falls back to the
|
|
|
|
|
// conservative writer union when there are no passes (the image is still
|
|
|
|
|
// transitioned, just never written), so the barrier is always well-formed.
|
|
|
|
|
inline VkPipelineStageFlags SwapchainStageUnion(std::span<RenderPass* const> passes) {
|
|
|
|
|
if (passes.empty()) return kSwapchainWriterStages;
|
|
|
|
|
VkPipelineStageFlags stages = 0;
|
|
|
|
|
for (RenderPass* pass : passes) stages |= pass->SwapchainStage();
|
|
|
|
|
return stages;
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-18 18:04:25 +00:00
|
|
|
// The access mask matching a swapchain-writer stage union, for the
|
|
|
|
|
// frame-edge barriers (acquire dst / present src). A barrier's access mask
|
|
|
|
|
// must only contain access flags supported by its accompanying stage mask
|
|
|
|
|
// (VUID-vkCmdPipelineBarrier-pImageMemoryBarriers-02820): TRANSFER_WRITE is
|
|
|
|
|
// not a valid access for COMPUTE/RAY_TRACING stages, so hardcoding both
|
|
|
|
|
// SHADER_WRITE and TRANSFER_WRITE fires the VUID every frame on an
|
|
|
|
|
// all-compute frame. The swapchain image is written as a storage image by
|
|
|
|
|
// compute/RT passes (SHADER_WRITE) and only via TRANSFER_WRITE when a
|
|
|
|
|
// transfer-stage pass is present, so derive the access bits from the same
|
|
|
|
|
// per-pass stage union the barrier's stage mask uses instead of hardcoding.
|
|
|
|
|
inline VkAccessFlags SwapchainWriterAccess(VkPipelineStageFlags stages) {
|
|
|
|
|
VkAccessFlags access = 0;
|
|
|
|
|
if (stages & (VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT
|
|
|
|
|
| VK_PIPELINE_STAGE_RAY_TRACING_SHADER_BIT_KHR))
|
|
|
|
|
access |= VK_ACCESS_SHADER_WRITE_BIT;
|
|
|
|
|
if (stages & VK_PIPELINE_STAGE_TRANSFER_BIT)
|
|
|
|
|
access |= VK_ACCESS_TRANSFER_WRITE_BIT;
|
|
|
|
|
return access;
|
|
|
|
|
}
|
|
|
|
|
|
feat: windows on their own clock, deferred deletion for every handle owner, staged re-uploads, and RTPass push data
Window
- updateInterval runs Update on the window's own clock while the
compositor sends no frame callbacks (hidden, minimized): the Wayland loop
is a poll() loop, and the Win32 loop sleeps until the next update. Both
read the interval each pass.
- SetPresentMode (FIFO, Mailbox, Immediate). A mode the surface lacks, or
whose swapchain has other than numFrames images (Mesa's Mailbox has four),
falls back to FIFO until the mode is set again.
- AddPollFd / RemovePollFd wake the Wayland loop on the app's descriptors.
- The swapchain has TRANSFER_DST where the surface allows it.
- CaptureNextFrame replaces SaveFrame: it records the copy in the frame,
before the present, where SaveFrame read an image already presented. A
frame unwound past before the write still frees the readback buffer.
- Inter-pass barriers on the swapchain image carry the access masks of the
stages the passes use.
Deferred deletion (issue #101)
- VulkanBuffer, Mesh, VulkanShader, ComputeShader and PipelineRTVulkan hand
their handles to the deletion queue from their destructors and moves, as
a frame in flight may still use them; a static owner goes after the
driver has torn down. VulkanShader and PipelineRTVulkan move and can't be
copied; re-Load and re-Init queue the old pipeline.
- The queue and its mutex are never destroyed, and the queue takes handles
from any thread; Device::frameCounter is atomic. Both the queue and the
staging rings count frames as one window renders them (documented).
- DrainDeletions also lets every buffer's staging ring start over: without
a Window nothing else reclaims either, so an app without one calls it
after waiting for its work.
Meshes and buffers
- A Mesh rebuild queues the old acceleration structure and builds into the
same storage after a barrier, so the BLAS address stays put when it fits.
The refit and rebuild barriers cover compute ray queries too.
- RTBuildOptions::noDuplicateAnyHit. Mesh::geometryFlags replaces opaque,
and the refit and rebuild fallbacks keep the flags.
- A re-upload into a buffer a frame in flight may read (UploadDeviceLocal
of the same size, UploadDeviceLocalRange) copies on the GPU, after those
reads, through a per-frame staging ring; on ReBAR it used to write the
buffer in place. Empty uploads record nothing.
- A compressed Mesh::Build that keeps its buffers decompresses into them
after the reads of frames in flight, and the hit shaders and ray queries
wait for the decompress as well as the BLAS build. Its vertex buffer
takes a ranged refit's copies.
- Mesh move-assigns (queueing the BLAS it replaces), so it can be replaced
in place or erased from a vector.
- VulkanBuffer::Create asks for a device address only for buffers with
SHADER_DEVICE_ADDRESS usage, as vkGetBufferDeviceAddress requires; the
others have address 0. UIRenderer::RegisterBuffer refuses those.
- Build inputs are synchronized as shader reads.
Other
- RTPass pushes the app's own push data and traces at an explicit size.
- DescriptorHeapVulkan hands freed slot ranges out again (they leaked), and
keeps its free lists sorted.
- ImageVulkan's mip chain clamps each level to 1 texel: a non-square
image's shorter side went to 0.
- VulkanShader throws on a missing file instead of failing in bad_alloc.
- CRAFTER_GRAPHICS_DEVICE picks the GPU by its number among the distinct
GPUs Vulkan lists; anything but such a number is an error.
- The debug messenger prints info messages only with
CRAFTER_GRAPHICS_VALIDATION set.
- Windows: the WinRT gamepad code moved to a C file (mingw-w64's WinRT
headers don't compile as C++), -lcombase dropped, a reference leak fixed.
- project.cpp honours --local for Crafter.Event, Math and Asset, as Asset
does for Math, and builds every test through one helper, projectArgs
included.
- Tests: DebugMessengerSeverity, DeletionQueueThreads, DeviceSelection,
HeapSlotReuse, MeshLifetime, MipChainNonSquare, PipelineLifetime,
RTPassPushData, SwapchainTransferDst, UploadInFlight, VulkanBufferAddress,
VulkanShaderLifetime, WindowUpdateClock; others extended.
Breaking: SaveFrame is CaptureNextFrame; Mesh::opaque is geometryFlags; a
buffer without SHADER_DEVICE_ADDRESS usage has no address; frameCounter is
std::atomic.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 19:07:54 +02:00
|
|
|
// Read and write access for the stages a pass touches the swapchain image
|
|
|
|
|
// in: the next pass after an inter-pass barrier may read the image as well
|
|
|
|
|
// as write it, through shaders or through transfers.
|
|
|
|
|
inline VkAccessFlags SwapchainPassAccess(VkPipelineStageFlags stages) {
|
|
|
|
|
VkAccessFlags access = 0;
|
|
|
|
|
if (stages & (VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT
|
|
|
|
|
| VK_PIPELINE_STAGE_RAY_TRACING_SHADER_BIT_KHR))
|
|
|
|
|
access |= VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
|
|
|
|
|
if (stages & VK_PIPELINE_STAGE_TRANSFER_BIT)
|
|
|
|
|
access |= VK_ACCESS_TRANSFER_READ_BIT | VK_ACCESS_TRANSFER_WRITE_BIT;
|
|
|
|
|
return access;
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-17 19:44:33 +00:00
|
|
|
// The inter-pass swapchain barrier (replacing the old queue-wide
|
|
|
|
|
// VkMemoryBarrier at the #115 location). Scoped to the swapchain image's
|
|
|
|
|
// single colour subresource so only that image's shader caches round-trip —
|
|
|
|
|
// unrelated buffers/images stay resident — exactly as the intra-pass UI
|
|
|
|
|
// barrier already does. The image is bound as a storage image and stays in
|
|
|
|
|
// VK_IMAGE_LAYOUT_GENERAL, so this is a pure memory dependency (no layout
|
feat: windows on their own clock, deferred deletion for every handle owner, staged re-uploads, and RTPass push data
Window
- updateInterval runs Update on the window's own clock while the
compositor sends no frame callbacks (hidden, minimized): the Wayland loop
is a poll() loop, and the Win32 loop sleeps until the next update. Both
read the interval each pass.
- SetPresentMode (FIFO, Mailbox, Immediate). A mode the surface lacks, or
whose swapchain has other than numFrames images (Mesa's Mailbox has four),
falls back to FIFO until the mode is set again.
- AddPollFd / RemovePollFd wake the Wayland loop on the app's descriptors.
- The swapchain has TRANSFER_DST where the surface allows it.
- CaptureNextFrame replaces SaveFrame: it records the copy in the frame,
before the present, where SaveFrame read an image already presented. A
frame unwound past before the write still frees the readback buffer.
- Inter-pass barriers on the swapchain image carry the access masks of the
stages the passes use.
Deferred deletion (issue #101)
- VulkanBuffer, Mesh, VulkanShader, ComputeShader and PipelineRTVulkan hand
their handles to the deletion queue from their destructors and moves, as
a frame in flight may still use them; a static owner goes after the
driver has torn down. VulkanShader and PipelineRTVulkan move and can't be
copied; re-Load and re-Init queue the old pipeline.
- The queue and its mutex are never destroyed, and the queue takes handles
from any thread; Device::frameCounter is atomic. Both the queue and the
staging rings count frames as one window renders them (documented).
- DrainDeletions also lets every buffer's staging ring start over: without
a Window nothing else reclaims either, so an app without one calls it
after waiting for its work.
Meshes and buffers
- A Mesh rebuild queues the old acceleration structure and builds into the
same storage after a barrier, so the BLAS address stays put when it fits.
The refit and rebuild barriers cover compute ray queries too.
- RTBuildOptions::noDuplicateAnyHit. Mesh::geometryFlags replaces opaque,
and the refit and rebuild fallbacks keep the flags.
- A re-upload into a buffer a frame in flight may read (UploadDeviceLocal
of the same size, UploadDeviceLocalRange) copies on the GPU, after those
reads, through a per-frame staging ring; on ReBAR it used to write the
buffer in place. Empty uploads record nothing.
- A compressed Mesh::Build that keeps its buffers decompresses into them
after the reads of frames in flight, and the hit shaders and ray queries
wait for the decompress as well as the BLAS build. Its vertex buffer
takes a ranged refit's copies.
- Mesh move-assigns (queueing the BLAS it replaces), so it can be replaced
in place or erased from a vector.
- VulkanBuffer::Create asks for a device address only for buffers with
SHADER_DEVICE_ADDRESS usage, as vkGetBufferDeviceAddress requires; the
others have address 0. UIRenderer::RegisterBuffer refuses those.
- Build inputs are synchronized as shader reads.
Other
- RTPass pushes the app's own push data and traces at an explicit size.
- DescriptorHeapVulkan hands freed slot ranges out again (they leaked), and
keeps its free lists sorted.
- ImageVulkan's mip chain clamps each level to 1 texel: a non-square
image's shorter side went to 0.
- VulkanShader throws on a missing file instead of failing in bad_alloc.
- CRAFTER_GRAPHICS_DEVICE picks the GPU by its number among the distinct
GPUs Vulkan lists; anything but such a number is an error.
- The debug messenger prints info messages only with
CRAFTER_GRAPHICS_VALIDATION set.
- Windows: the WinRT gamepad code moved to a C file (mingw-w64's WinRT
headers don't compile as C++), -lcombase dropped, a reference leak fixed.
- project.cpp honours --local for Crafter.Event, Math and Asset, as Asset
does for Math, and builds every test through one helper, projectArgs
included.
- Tests: DebugMessengerSeverity, DeletionQueueThreads, DeviceSelection,
HeapSlotReuse, MeshLifetime, MipChainNonSquare, PipelineLifetime,
RTPassPushData, SwapchainTransferDst, UploadInFlight, VulkanBufferAddress,
VulkanShaderLifetime, WindowUpdateClock; others extended.
Breaking: SaveFrame is CaptureNextFrame; Mesh::opaque is geometryFlags; a
buffer without SHADER_DEVICE_ADDRESS usage has no address; frameCounter is
std::atomic.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 19:07:54 +02:00
|
|
|
// transition). The stages are the two passes' SwapchainStage(), which the
|
|
|
|
|
// caller also hands vkCmdPipelineBarrier, and the access masks follow
|
|
|
|
|
// them: a transfer pass (a clear, a blit) writes with TRANSFER_WRITE, which
|
|
|
|
|
// SHADER_WRITE would not cover, and an access a stage can't perform is
|
|
|
|
|
// invalid in its barrier (VUID-vkCmdPipelineBarrier-pImageMemoryBarriers-02818/02820).
|
|
|
|
|
inline VkImageMemoryBarrier BuildSwapchainInterPassBarrier(VkImage image, VkPipelineStageFlags srcStages, VkPipelineStageFlags dstStages) {
|
2026-06-17 19:44:33 +00:00
|
|
|
return {
|
|
|
|
|
.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
|
feat: windows on their own clock, deferred deletion for every handle owner, staged re-uploads, and RTPass push data
Window
- updateInterval runs Update on the window's own clock while the
compositor sends no frame callbacks (hidden, minimized): the Wayland loop
is a poll() loop, and the Win32 loop sleeps until the next update. Both
read the interval each pass.
- SetPresentMode (FIFO, Mailbox, Immediate). A mode the surface lacks, or
whose swapchain has other than numFrames images (Mesa's Mailbox has four),
falls back to FIFO until the mode is set again.
- AddPollFd / RemovePollFd wake the Wayland loop on the app's descriptors.
- The swapchain has TRANSFER_DST where the surface allows it.
- CaptureNextFrame replaces SaveFrame: it records the copy in the frame,
before the present, where SaveFrame read an image already presented. A
frame unwound past before the write still frees the readback buffer.
- Inter-pass barriers on the swapchain image carry the access masks of the
stages the passes use.
Deferred deletion (issue #101)
- VulkanBuffer, Mesh, VulkanShader, ComputeShader and PipelineRTVulkan hand
their handles to the deletion queue from their destructors and moves, as
a frame in flight may still use them; a static owner goes after the
driver has torn down. VulkanShader and PipelineRTVulkan move and can't be
copied; re-Load and re-Init queue the old pipeline.
- The queue and its mutex are never destroyed, and the queue takes handles
from any thread; Device::frameCounter is atomic. Both the queue and the
staging rings count frames as one window renders them (documented).
- DrainDeletions also lets every buffer's staging ring start over: without
a Window nothing else reclaims either, so an app without one calls it
after waiting for its work.
Meshes and buffers
- A Mesh rebuild queues the old acceleration structure and builds into the
same storage after a barrier, so the BLAS address stays put when it fits.
The refit and rebuild barriers cover compute ray queries too.
- RTBuildOptions::noDuplicateAnyHit. Mesh::geometryFlags replaces opaque,
and the refit and rebuild fallbacks keep the flags.
- A re-upload into a buffer a frame in flight may read (UploadDeviceLocal
of the same size, UploadDeviceLocalRange) copies on the GPU, after those
reads, through a per-frame staging ring; on ReBAR it used to write the
buffer in place. Empty uploads record nothing.
- A compressed Mesh::Build that keeps its buffers decompresses into them
after the reads of frames in flight, and the hit shaders and ray queries
wait for the decompress as well as the BLAS build. Its vertex buffer
takes a ranged refit's copies.
- Mesh move-assigns (queueing the BLAS it replaces), so it can be replaced
in place or erased from a vector.
- VulkanBuffer::Create asks for a device address only for buffers with
SHADER_DEVICE_ADDRESS usage, as vkGetBufferDeviceAddress requires; the
others have address 0. UIRenderer::RegisterBuffer refuses those.
- Build inputs are synchronized as shader reads.
Other
- RTPass pushes the app's own push data and traces at an explicit size.
- DescriptorHeapVulkan hands freed slot ranges out again (they leaked), and
keeps its free lists sorted.
- ImageVulkan's mip chain clamps each level to 1 texel: a non-square
image's shorter side went to 0.
- VulkanShader throws on a missing file instead of failing in bad_alloc.
- CRAFTER_GRAPHICS_DEVICE picks the GPU by its number among the distinct
GPUs Vulkan lists; anything but such a number is an error.
- The debug messenger prints info messages only with
CRAFTER_GRAPHICS_VALIDATION set.
- Windows: the WinRT gamepad code moved to a C file (mingw-w64's WinRT
headers don't compile as C++), -lcombase dropped, a reference leak fixed.
- project.cpp honours --local for Crafter.Event, Math and Asset, as Asset
does for Math, and builds every test through one helper, projectArgs
included.
- Tests: DebugMessengerSeverity, DeletionQueueThreads, DeviceSelection,
HeapSlotReuse, MeshLifetime, MipChainNonSquare, PipelineLifetime,
RTPassPushData, SwapchainTransferDst, UploadInFlight, VulkanBufferAddress,
VulkanShaderLifetime, WindowUpdateClock; others extended.
Breaking: SaveFrame is CaptureNextFrame; Mesh::opaque is geometryFlags; a
buffer without SHADER_DEVICE_ADDRESS usage has no address; frameCounter is
std::atomic.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 19:07:54 +02:00
|
|
|
.srcAccessMask = SwapchainWriterAccess(srcStages),
|
|
|
|
|
.dstAccessMask = SwapchainPassAccess(dstStages),
|
2026-06-17 19:44:33 +00:00
|
|
|
.oldLayout = VK_IMAGE_LAYOUT_GENERAL,
|
|
|
|
|
.newLayout = VK_IMAGE_LAYOUT_GENERAL,
|
|
|
|
|
.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
|
|
|
|
|
.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
|
|
|
|
|
.image = image,
|
|
|
|
|
.subresourceRange = {
|
|
|
|
|
.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT,
|
|
|
|
|
.baseMipLevel = 0,
|
|
|
|
|
.levelCount = 1,
|
|
|
|
|
.baseArrayLayer = 0,
|
|
|
|
|
.layerCount = 1,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM
|
2026-05-01 23:35:37 +02:00
|
|
|
}
|