Using Vulkan C API
This commit is contained in:
mklefrancois
parent
b3e6d84807
commit
e642e9dc3a
83 changed files with 8015 additions and 8163 deletions
|
|
@ -43,7 +43,7 @@ The directory structure should be looking like:
|
|||
**********************************************************
|
||||
|
||||
|
||||
!!! Warning
|
||||
!!! Warning CMake
|
||||
**Run CMake** in vk_raytracing_tutorial_KHR.
|
||||
|
||||
!!! Warning Beta Vulkan SDK
|
||||
|
|
|
|||
|
|
@ -202,18 +202,18 @@ void HelloVulkan::createLanternIndirectBuffer()
|
|||
|
||||
// m_alloc behind the scenes uses cmdBuf to transfer data to the buffer.
|
||||
nvvk::CommandPool cmdBufGet(m_device, m_graphicsQueueIndex);
|
||||
vk::CommandBuffer cmdBuf = cmdBufGet.createCommandBuffer();
|
||||
VkCommandBuffer cmdBuf = cmdBufGet.createCommandBuffer();
|
||||
|
||||
using Usage = vk::BufferUsageFlagBits;
|
||||
m_lanternIndirectBuffer =
|
||||
m_alloc.createBuffer(sizeof(LanternIndirectEntry) * m_lanternCount,
|
||||
Usage::eIndirectBuffer | Usage::eTransferDst
|
||||
| Usage::eShaderDeviceAddress | Usage::eStorageBuffer,
|
||||
vk::MemoryPropertyFlagBits::eDeviceLocal);
|
||||
using Usage = VkBufferUsageFlagBits;
|
||||
m_lanternIndirectBuffer = m_alloc.createBuffer(sizeof(LanternIndirectEntry) * m_lanternCount,
|
||||
VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT
|
||||
| VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
|
||||
VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
|
||||
|
||||
std::vector<LanternIndirectEntry> entries(m_lanternCount);
|
||||
for (size_t i = 0; i < m_lanternCount; ++i) entries[i].lantern = m_lanterns[i];
|
||||
cmdBuf.updateBuffer(m_lanternIndirectBuffer.buffer, 0, entries.size() * sizeof entries[0], entries.data());
|
||||
for(size_t i = 0; i < m_lanternCount; ++i)
|
||||
entries[i].lantern = m_lanterns[i];
|
||||
vkCmdUpdateBuffer(cmdBuf, m_lanternIndirectBuffer.buffer, 0, entries.size() * sizeof entries[0], entries.data());
|
||||
|
||||
cmdBufGet.submitAndWait(cmdBuf);
|
||||
}
|
||||
|
|
@ -370,12 +370,12 @@ to allocate one descriptor as the `LanternIndirectEntry` array never changes.
|
|||
`hello_vulkan.h`:
|
||||
|
||||
```` C
|
||||
nvvk::DescriptorSetBindings m_lanternIndirectDescSetLayoutBind;
|
||||
vk::DescriptorPool m_lanternIndirectDescPool;
|
||||
vk::DescriptorSetLayout m_lanternIndirectDescSetLayout;
|
||||
vk::DescriptorSet m_lanternIndirectDescSet;
|
||||
vk::PipelineLayout m_lanternIndirectCompPipelineLayout;
|
||||
vk::Pipeline m_lanternIndirectCompPipeline;
|
||||
nvvk::DescriptorSetBindings m_lanternIndirectDescSetLayoutBind;
|
||||
VkDescriptorPool m_lanternIndirectDescPool;
|
||||
VkDescriptorSetLayout m_lanternIndirectDescSetLayout;
|
||||
VkDescriptorSet m_lanternIndirectDescSet;
|
||||
VkPipelineLayout m_lanternIndirectCompPipelineLayout;
|
||||
VkPipeline m_lanternIndirectCompPipeline;
|
||||
````
|
||||
|
||||
`hello_vulkan.cpp`:
|
||||
|
|
@ -385,26 +385,25 @@ to allocate one descriptor as the `LanternIndirectEntry` array never changes.
|
|||
// The compute shader just needs read/write access to the buffer of LanternIndirectEntry.
|
||||
void HelloVulkan::createLanternIndirectDescriptorSet()
|
||||
{
|
||||
using vkDT = vk::DescriptorType;
|
||||
using vkSS = vk::ShaderStageFlagBits;
|
||||
using vkDSLB = vk::DescriptorSetLayoutBinding;
|
||||
|
||||
// Lantern buffer (binding = 0)
|
||||
m_lanternIndirectDescSetLayoutBind.addBinding( //
|
||||
vkDSLB(0, vkDT::eStorageBuffer, 1, vkSS::eCompute));
|
||||
m_lanternIndirectDescSetLayoutBind.addBinding(0, VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 1, VK_SHADER_STAGE_COMPUTE_BIT);
|
||||
|
||||
m_lanternIndirectDescPool = m_lanternIndirectDescSetLayoutBind.createPool(m_device);
|
||||
m_lanternIndirectDescSetLayout = m_lanternIndirectDescSetLayoutBind.createLayout(m_device);
|
||||
m_lanternIndirectDescSet =
|
||||
m_device.allocateDescriptorSets({m_lanternIndirectDescPool, 1, &m_lanternIndirectDescSetLayout})[0];
|
||||
|
||||
VkDescriptorSetAllocateInfo allocateInfo{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO};
|
||||
allocateInfo.descriptorPool = m_lanternIndirectDescPool;
|
||||
allocateInfo.descriptorSetCount = 1;
|
||||
allocateInfo.pSetLayouts = &m_lanternIndirectDescSetLayout;
|
||||
vkAllocateDescriptorSets(m_device, &allocateInfo, &m_lanternIndirectDescSet);
|
||||
|
||||
|
||||
assert(m_lanternIndirectBuffer.buffer);
|
||||
vk::DescriptorBufferInfo lanternBufferInfo{
|
||||
m_lanternIndirectBuffer.buffer, 0, m_lanternCount * sizeof(LanternIndirectEntry)};
|
||||
VkDescriptorBufferInfo lanternBufferInfo{m_lanternIndirectBuffer.buffer, 0, m_lanternCount * sizeof(LanternIndirectEntry)};
|
||||
|
||||
std::vector<vk::WriteDescriptorSet> writes;
|
||||
std::vector<VkWriteDescriptorSet> writes;
|
||||
writes.emplace_back(m_lanternIndirectDescSetLayoutBind.makeWrite(m_lanternIndirectDescSet, 0, &lanternBufferInfo));
|
||||
m_device.updateDescriptorSets(static_cast<uint32_t>(writes.size()), writes.data(), 0, nullptr);
|
||||
vkUpdateDescriptorSets(m_device, static_cast<uint32_t>(writes.size()), writes.data(), 0, nullptr);
|
||||
}
|
||||
|
||||
// Create compute pipeline used to fill m_lanternIndirectBuffer with parameters
|
||||
|
|
@ -412,32 +411,31 @@ void HelloVulkan::createLanternIndirectDescriptorSet()
|
|||
void HelloVulkan::createLanternIndirectCompPipeline()
|
||||
{
|
||||
// Compile compute shader and package as stage.
|
||||
vk::ShaderModule computeShader =
|
||||
nvvk::createShaderModule(m_device, //
|
||||
nvh::loadFile("shaders/lanternIndirect.comp.spv", true, defaultSearchPaths, true));
|
||||
vk::PipelineShaderStageCreateInfo stageInfo;
|
||||
stageInfo.setStage(vk::ShaderStageFlagBits::eCompute);
|
||||
stageInfo.setModule(computeShader);
|
||||
stageInfo.setPName("main");
|
||||
VkShaderModule computeShader =
|
||||
nvvk::createShaderModule(m_device, nvh::loadFile("spv/lanternIndirect.comp.spv", true, defaultSearchPaths, true));
|
||||
VkPipelineShaderStageCreateInfo stageInfo{VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO};
|
||||
stageInfo.stage = VK_SHADER_STAGE_COMPUTE_BIT;
|
||||
stageInfo.module = computeShader;
|
||||
stageInfo.pName = "main";
|
||||
|
||||
// Set up push constant and pipeline layout.
|
||||
constexpr auto pushSize = static_cast<uint32_t>(sizeof(m_lanternIndirectPushConstants));
|
||||
vk::PushConstantRange pushCRange = {vk::ShaderStageFlagBits::eCompute, 0, pushSize};
|
||||
constexpr auto pushSize = static_cast<uint32_t>(sizeof(m_lanternIndirectPushConstants));
|
||||
VkPushConstantRange pushCRange = {VK_SHADER_STAGE_COMPUTE_BIT, 0, pushSize};
|
||||
static_assert(pushSize <= 128, "Spec guarantees only 128 byte push constant");
|
||||
vk::PipelineLayoutCreateInfo layoutInfo;
|
||||
layoutInfo.setSetLayoutCount(1);
|
||||
layoutInfo.setPSetLayouts(&m_lanternIndirectDescSetLayout);
|
||||
layoutInfo.setPushConstantRangeCount(1);
|
||||
layoutInfo.setPPushConstantRanges(&pushCRange);
|
||||
m_lanternIndirectCompPipelineLayout = m_device.createPipelineLayout(layoutInfo);
|
||||
VkPipelineLayoutCreateInfo layoutInfo{VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO};
|
||||
layoutInfo.setLayoutCount = 1;
|
||||
layoutInfo.pSetLayouts = &m_lanternIndirectDescSetLayout;
|
||||
layoutInfo.pushConstantRangeCount = 1;
|
||||
layoutInfo.pPushConstantRanges = &pushCRange;
|
||||
vkCreatePipelineLayout(m_device, &layoutInfo, nullptr, &m_lanternIndirectCompPipelineLayout);
|
||||
|
||||
// Create compute pipeline.
|
||||
vk::ComputePipelineCreateInfo pipelineInfo;
|
||||
pipelineInfo.setStage(stageInfo);
|
||||
pipelineInfo.setLayout(m_lanternIndirectCompPipelineLayout);
|
||||
m_lanternIndirectCompPipeline = static_cast<const vk::Pipeline&>(m_device.createComputePipeline({}, pipelineInfo));
|
||||
VkComputePipelineCreateInfo pipelineInfo{VK_STRUCTURE_TYPE_COMPUTE_PIPELINE_CREATE_INFO};
|
||||
pipelineInfo.stage = stageInfo;
|
||||
pipelineInfo.layout = m_lanternIndirectCompPipelineLayout;
|
||||
vkCreateComputePipelines(m_device, {}, 1, &pipelineInfo, nullptr, &m_lanternIndirectCompPipeline);
|
||||
|
||||
m_device.destroy(computeShader);
|
||||
vkDestroyShaderModule(m_device, computeShader, nullptr);
|
||||
}
|
||||
````
|
||||
|
||||
|
|
@ -464,61 +462,72 @@ pipeline barrier synchronizing access to the `LanternIndirectEntry` array
|
|||
between the compute shader and indirect draw stages.
|
||||
|
||||
```` C
|
||||
void HelloVulkan::raytrace(const vk::CommandBuffer& cmdBuf, const nvmath::vec4f& clearColor)
|
||||
//--------------------------------------------------------------------------------------------------
|
||||
// Ray Tracing the scene
|
||||
//
|
||||
// The raytracing is split into multiple passes:
|
||||
//
|
||||
// First pass fills in the initial values for every pixel in the output image.
|
||||
// Illumination and shadow rays come from the main light.
|
||||
//
|
||||
// Subsequently, one lantern pass is run for each lantern in the scene. We run
|
||||
// a compute shader to calculate a bounding scissor rectangle for each lantern's light
|
||||
// effect. This is stored in m_lanternIndirectBuffer. Then an indirect trace rays command
|
||||
// is run for every lantern within its scissor rectangle. The lanterns' light
|
||||
// contribution is additively blended into the output image.
|
||||
void HelloVulkan::raytrace(const VkCommandBuffer& cmdBuf, const nvmath::vec4f& clearColor)
|
||||
{
|
||||
// Before tracing rays, we need to dispatch the compute shaders that
|
||||
// fill in the ray trace indirect parameters for each lantern pass.
|
||||
|
||||
// First, barrier before, ensure writes aren't visible to previous frame.
|
||||
vk::BufferMemoryBarrier bufferBarrier;
|
||||
bufferBarrier.setSrcAccessMask(vk::AccessFlagBits::eIndirectCommandRead);
|
||||
bufferBarrier.setDstAccessMask(vk::AccessFlagBits::eShaderWrite);
|
||||
bufferBarrier.setSrcQueueFamilyIndex(VK_QUEUE_FAMILY_IGNORED);
|
||||
bufferBarrier.setDstQueueFamilyIndex(VK_QUEUE_FAMILY_IGNORED);
|
||||
bufferBarrier.setBuffer(m_lanternIndirectBuffer.buffer);
|
||||
bufferBarrier.offset = 0;
|
||||
bufferBarrier.size = m_lanternCount * sizeof m_lanterns[0];
|
||||
cmdBuf.pipelineBarrier( //
|
||||
vk::PipelineStageFlagBits::eDrawIndirect, //
|
||||
vk::PipelineStageFlagBits::eComputeShader,//
|
||||
vk::DependencyFlags(0), //
|
||||
{}, {bufferBarrier}, {});
|
||||
VkBufferMemoryBarrier bufferBarrier{VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER};
|
||||
bufferBarrier.srcAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
|
||||
bufferBarrier.dstAccessMask = VK_ACCESS_SHADER_WRITE_BIT;
|
||||
bufferBarrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
|
||||
bufferBarrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
|
||||
bufferBarrier.buffer = m_lanternIndirectBuffer.buffer;
|
||||
bufferBarrier.offset = 0;
|
||||
bufferBarrier.size = m_lanternCount * sizeof m_lanterns[0];
|
||||
vkCmdPipelineBarrier(cmdBuf,
|
||||
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, //
|
||||
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, //
|
||||
VkDependencyFlags(0), //
|
||||
0, nullptr, 1, &bufferBarrier, 0, nullptr);
|
||||
|
||||
// Bind compute shader, update push constant and descriptors, dispatch compute.
|
||||
cmdBuf.bindPipeline(vk::PipelineBindPoint::eCompute, m_lanternIndirectCompPipeline);
|
||||
nvmath::mat4 view = getViewMatrix();
|
||||
m_lanternIndirectPushConstants.viewRowX = view.row(0);
|
||||
m_lanternIndirectPushConstants.viewRowY = view.row(1);
|
||||
m_lanternIndirectPushConstants.viewRowZ = view.row(2);
|
||||
m_lanternIndirectPushConstants.proj = getProjMatrix();
|
||||
m_lanternIndirectPushConstants.nearZ = nearZ;
|
||||
m_lanternIndirectPushConstants.screenX = m_size.width;
|
||||
m_lanternIndirectPushConstants.screenY = m_size.height;
|
||||
m_lanternIndirectPushConstants.lanternCount = m_lanternCount;
|
||||
cmdBuf.pushConstants<LanternIndirectPushConstants>(
|
||||
m_lanternIndirectCompPipelineLayout,
|
||||
vk::ShaderStageFlagBits::eCompute,
|
||||
0, m_lanternIndirectPushConstants);
|
||||
cmdBuf.bindDescriptorSets(
|
||||
vk::PipelineBindPoint::eCompute, m_lanternIndirectCompPipelineLayout, 0, {m_lanternIndirectDescSet}, {});
|
||||
cmdBuf.dispatch(1, 1, 1);
|
||||
vkCmdBindPipeline(cmdBuf, VK_PIPELINE_BIND_POINT_COMPUTE, m_lanternIndirectCompPipeline);
|
||||
nvmath::mat4 view = getViewMatrix();
|
||||
m_lanternIndirectPushConstants.viewRowX = view.row(0);
|
||||
m_lanternIndirectPushConstants.viewRowY = view.row(1);
|
||||
m_lanternIndirectPushConstants.viewRowZ = view.row(2);
|
||||
m_lanternIndirectPushConstants.proj = getProjMatrix();
|
||||
m_lanternIndirectPushConstants.nearZ = nearZ;
|
||||
m_lanternIndirectPushConstants.screenX = m_size.width;
|
||||
m_lanternIndirectPushConstants.screenY = m_size.height;
|
||||
m_lanternIndirectPushConstants.lanternCount = int32_t(m_lanternCount);
|
||||
vkCmdPushConstants(cmdBuf, m_lanternIndirectCompPipelineLayout, VK_SHADER_STAGE_COMPUTE_BIT, 0,
|
||||
sizeof(LanternIndirectPushConstants), &m_lanternIndirectPushConstants);
|
||||
vkCmdBindDescriptorSets(cmdBuf, VK_PIPELINE_BIND_POINT_COMPUTE, m_lanternIndirectCompPipelineLayout, 0, 1,
|
||||
&m_lanternIndirectDescSet, 0, nullptr);
|
||||
vkCmdDispatch(cmdBuf, 1, 1, 1);
|
||||
|
||||
// Ensure compute results are visible when doing indirect ray trace.
|
||||
bufferBarrier.setSrcAccessMask(vk::AccessFlagBits::eShaderWrite);
|
||||
bufferBarrier.setDstAccessMask(vk::AccessFlagBits::eIndirectCommandRead);
|
||||
cmdBuf.pipelineBarrier( //
|
||||
vk::PipelineStageFlagBits::eComputeShader, //
|
||||
vk::PipelineStageFlagBits::eDrawIndirect, //
|
||||
vk::DependencyFlags(0), //
|
||||
{}, {bufferBarrier}, {});
|
||||
bufferBarrier.srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT;
|
||||
bufferBarrier.dstAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
|
||||
vkCmdPipelineBarrier(cmdBuf,
|
||||
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, //
|
||||
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, //
|
||||
VkDependencyFlags(0), //
|
||||
0, nullptr, 1, &bufferBarrier, 0, nullptr);
|
||||
|
||||
|
||||
// Now move on to the actual ray tracing.
|
||||
m_debug.beginLabel(cmdBuf, "Ray trace");
|
||||
````
|
||||
|
||||
!!! TIP `eDrawIndirect`
|
||||
`vk::PipelineStageFlagBits::eDrawIndirect` (`VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT`)
|
||||
!!! TIP `VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT`
|
||||
`VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT`
|
||||
covers the stage that sources indirect paramaters for compute and ray trace
|
||||
indirect commands, not just graphics draw indirect commands.
|
||||
|
||||
|
|
@ -542,7 +551,7 @@ they were factored out to common code in `hello_vulkan.h`.
|
|||
The function for updating the uniform buffer is tweaked to match.
|
||||
|
||||
```` C
|
||||
void HelloVulkan::updateUniformBuffer(const vk::CommandBuffer& cmdBuf)
|
||||
void HelloVulkan::updateUniformBuffer(const VkCommandBuffer& cmdBuf)
|
||||
{
|
||||
const float aspectRatio = m_size.width / static_cast<float>(m_size.height);
|
||||
|
||||
|
|
@ -579,40 +588,40 @@ In order to focus on the ray tracing, I omit the code for generating those verte
|
|||
buffers. The relevent code in `HelloVulkan::createLanternModel` for creating the `BlasInput` is
|
||||
|
||||
```` C
|
||||
// Package vertex and index buffers as BlasInput.
|
||||
vk::DeviceAddress vertexAddress = m_device.getBufferAddress({m_lanternVertexBuffer.buffer});
|
||||
vk::DeviceAddress indexAddress = m_device.getBufferAddress({m_lanternIndexBuffer.buffer});
|
||||
// Package vertex and index buffers as BlasInput.
|
||||
VkDeviceAddress vertexAddress = nvvk::getBufferDeviceAddress(m_device, m_lanternVertexBuffer.buffer);
|
||||
VkDeviceAddress indexAddress = nvvk::getBufferDeviceAddress(m_device, m_lanternIndexBuffer.buffer);
|
||||
|
||||
uint32_t maxPrimitiveCount = uint32_t(indices.size() / 3);
|
||||
auto maxPrimitiveCount = uint32_t(indices.size() / 3);
|
||||
|
||||
// Describe buffer as packed array of float vec3.
|
||||
vk::AccelerationStructureGeometryTrianglesDataKHR triangles;
|
||||
triangles.setVertexFormat(vk::Format::eR32G32B32Sfloat); // vec3 vertex position data.
|
||||
triangles.setVertexData(vertexAddress);
|
||||
triangles.setVertexStride(sizeof(nvmath::vec3f));
|
||||
// Describe index data (32-bit unsigned int)
|
||||
triangles.setIndexType(vk::IndexType::eUint32);
|
||||
triangles.setIndexData(indexAddress);
|
||||
// Indicate identity transform by setting transformData to null device pointer.
|
||||
triangles.setTransformData({});
|
||||
triangles.setMaxVertex(vertices.size());
|
||||
// Describe buffer as packed array of float vec3.
|
||||
VkAccelerationStructureGeometryTrianglesDataKHR triangles{VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_GEOMETRY_TRIANGLES_DATA_KHR};
|
||||
triangles.vertexFormat = VK_FORMAT_R32G32B32_SFLOAT; // vec3 vertex position data.
|
||||
triangles.vertexData.deviceAddress = vertexAddress;
|
||||
triangles.vertexStride = sizeof(nvmath::vec3f);
|
||||
// Describe index data (32-bit unsigned int)
|
||||
triangles.indexType = VK_INDEX_TYPE_UINT32;
|
||||
triangles.indexData.deviceAddress = indexAddress;
|
||||
// Indicate identity transform by setting transformData to null device pointer.
|
||||
//triangles.transformData = {};
|
||||
triangles.maxVertex = uint32_t(vertices.size());
|
||||
|
||||
// Identify the above data as containing opaque triangles.
|
||||
vk::AccelerationStructureGeometryKHR asGeom;
|
||||
asGeom.setGeometryType(vk::GeometryTypeKHR::eTriangles);
|
||||
asGeom.setFlags(vk::GeometryFlagBitsKHR::eOpaque);
|
||||
asGeom.geometry.setTriangles(triangles);
|
||||
// Identify the above data as containing opaque triangles.
|
||||
VkAccelerationStructureGeometryKHR asGeom{VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_GEOMETRY_KHR};
|
||||
asGeom.geometryType = VK_GEOMETRY_TYPE_TRIANGLES_KHR;
|
||||
asGeom.flags = VK_GEOMETRY_OPAQUE_BIT_KHR;
|
||||
asGeom.geometry.triangles = triangles;
|
||||
|
||||
// The entire array will be used to build the BLAS.
|
||||
vk::AccelerationStructureBuildRangeInfoKHR offset;
|
||||
offset.setFirstVertex(0);
|
||||
offset.setPrimitiveCount(maxPrimitiveCount);
|
||||
offset.setPrimitiveOffset(0);
|
||||
offset.setTransformOffset(0);
|
||||
// The entire array will be used to build the BLAS.
|
||||
VkAccelerationStructureBuildRangeInfoKHR offset;
|
||||
offset.firstVertex = 0;
|
||||
offset.primitiveCount = maxPrimitiveCount;
|
||||
offset.primitiveOffset = 0;
|
||||
offset.transformOffset = 0;
|
||||
|
||||
// Our blas is made from only one geometry, but could be made of many geometries
|
||||
m_lanternBlasInput.asGeometry.emplace_back(asGeom);
|
||||
m_lanternBlasInput.asBuildOffsetInfo.emplace_back(offset);
|
||||
// Our blas is made from only one geometry, but could be made of many geometries
|
||||
m_lanternBlasInput.asGeometry.emplace_back(asGeom);
|
||||
m_lanternBlasInput.asBuildOffsetInfo.emplace_back(offset);
|
||||
````
|
||||
|
||||
The principle difference from before is that the vertex array is now a packed array of
|
||||
|
|
@ -647,7 +656,7 @@ void HelloVulkan::createBottomLevelAS()
|
|||
m_lanternBlasId = allBlas.size();
|
||||
allBlas.emplace_back(m_lanternBlasInput);
|
||||
|
||||
m_rtBuilder.buildBlas(allBlas, vk::BuildAccelerationStructureFlagBitsKHR::ePreferFastTrace);
|
||||
m_rtBuilder.buildBlas(allBlas, VK_BUILD_ACCELERATION_STRUCTURE_PREFER_FAST_TRACE_BIT_KHR);
|
||||
}
|
||||
````
|
||||
|
||||
|
|
@ -696,7 +705,7 @@ void HelloVulkan::createTopLevelAS()
|
|||
tlas.emplace_back(lanternInstance);
|
||||
}
|
||||
|
||||
m_rtBuilder.buildTlas(tlas, vk::BuildAccelerationStructureFlagBitsKHR::ePreferFastTrace);
|
||||
m_rtBuilder.buildTlas(tlas, VK_BUILD_ACCELERATION_STRUCTURE_PREFER_FAST_TRACE_BIT_KHR);
|
||||
}
|
||||
````
|
||||
|
||||
|
|
@ -749,25 +758,21 @@ The last task is done in `HelloVulkan::createRtDescriptorSet`
|
|||
//
|
||||
void HelloVulkan::createRtDescriptorSet()
|
||||
{
|
||||
using vkDT = vk::DescriptorType;
|
||||
using vkSS = vk::ShaderStageFlagBits;
|
||||
using vkDSLB = vk::DescriptorSetLayoutBinding;
|
||||
|
||||
// ...
|
||||
|
||||
// Lantern buffer (binding = 2)
|
||||
m_rtDescSetLayoutBind.addBinding( //
|
||||
vkDSLB(2, vkDT::eStorageBuffer, 1, vkSS::eRaygenKHR | vkSS::eClosestHitKHR));
|
||||
m_rtDescSetLayoutBind.addBinding(2, VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, 1,
|
||||
VK_SHADER_STAGE_RAYGEN_BIT_KHR | VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR);
|
||||
assert(m_lanternCount > 0);
|
||||
|
||||
// ...
|
||||
|
||||
std::vector<vk::WriteDescriptorSet> writes;
|
||||
std::vector<VkWriteDescriptorSet> writes;
|
||||
|
||||
// ...
|
||||
|
||||
writes.emplace_back(m_rtDescSetLayoutBind.makeWrite(m_rtDescSet, 2, &lanternBufferInfo));
|
||||
m_device.updateDescriptorSets(static_cast<uint32_t>(writes.size()), writes.data(), 0, nullptr);
|
||||
vkUpdateDescriptorSets(m_device, static_cast<uint32_t>(writes.size()), writes.data(), 0, nullptr);
|
||||
}
|
||||
````
|
||||
|
||||
|
|
@ -809,34 +814,36 @@ group after the OBJ hit group, to match the `hitGroupId`s assigned earlier in th
|
|||
TLAS build.
|
||||
|
||||
```` C
|
||||
// OBJ Primary Ray Hit Group - Closest Hit + AnyHit (not used)
|
||||
vk::ShaderModule chitSM =
|
||||
nvvk::createShaderModule(m_device, //
|
||||
nvh::loadFile("shaders/raytrace.rchit.spv", true, paths, true));
|
||||
|
||||
vk::RayTracingShaderGroupCreateInfoKHR hg{vk::RayTracingShaderGroupTypeKHR::eTrianglesHitGroup,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR};
|
||||
hg.setClosestHitShader(static_cast<uint32_t>(stages.size()));
|
||||
stages.push_back({{}, vk::ShaderStageFlagBits::eClosestHitKHR, chitSM, "main"});
|
||||
m_rtShaderGroups.push_back(hg);
|
||||
enum StageIndices
|
||||
{
|
||||
// ...
|
||||
eClosestHit,
|
||||
eClosestHitLantern,
|
||||
eShaderGroupCount
|
||||
};
|
||||
// ...
|
||||
|
||||
// Lantern Primary Ray Hit Group
|
||||
vk::ShaderModule lanternChitSM =
|
||||
nvvk::createShaderModule(m_device, //
|
||||
nvh::loadFile("shaders/lantern.rchit.spv", true, paths, true));
|
||||
// OBJ Primary Ray Hit Group - Closest Hit
|
||||
stage.module = nvvk::createShaderModule(m_device, nvh::loadFile("spv/raytrace.rchit.spv", true, defaultSearchPaths, true));
|
||||
stage.stage = VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR;
|
||||
stages[eClosestHit] = stage;
|
||||
|
||||
vk::RayTracingShaderGroupCreateInfoKHR lanternHg{
|
||||
vk::RayTracingShaderGroupTypeKHR::eTrianglesHitGroup,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR};
|
||||
lanternHg.setClosestHitShader(static_cast<uint32_t>(stages.size()));
|
||||
stages.push_back({{}, vk::ShaderStageFlagBits::eClosestHitKHR, lanternChitSM, "main"});
|
||||
m_rtShaderGroups.push_back(lanternHg);
|
||||
|
||||
// ...
|
||||
|
||||
m_device.destroy(lanternChitSM);
|
||||
// Lantern Primary Ray Hit Group
|
||||
stage.module = nvvk::createShaderModule(m_device, nvh::loadFile("spv/lantern.rchit.spv", true, defaultSearchPaths, true));
|
||||
stage.stage = VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR;
|
||||
stages[eClosestHitLantern] = stage;
|
||||
|
||||
// ...
|
||||
|
||||
// closest hit shader
|
||||
group.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_TRIANGLES_HIT_GROUP_KHR;
|
||||
group.generalShader = VK_SHADER_UNUSED_KHR;
|
||||
group.closestHitShader = eClosestHit;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
group.closestHitShader = eClosestHitLantern;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
````
|
||||
|
||||
We don't have to modify `HelloVulkan::createRtShaderBindingTable`. Changes to the number of
|
||||
|
|
@ -1102,41 +1109,53 @@ groups for primary rays. Add the following code to `HelloVulkan::createRtPipelin
|
|||
after loading `raytraceShadow.rmiss.spv`.
|
||||
|
||||
```` C
|
||||
// Miss shader 2 is invoked when a shadow ray for lantern lighting misses the
|
||||
// lantern. It shouldn't be invoked, but I include it just in case.
|
||||
vk::ShaderModule lanternmissSM = nvvk::createShaderModule(
|
||||
m_device, nvh::loadFile("shaders/lanternShadow.rmiss.spv", true, paths, true));
|
||||
// Miss shader 2 is invoked when a shadow ray for lantern lighting misses the
|
||||
// lantern. It shouldn't be invoked, but I include it just in case.
|
||||
stage.module = nvvk::createShaderModule(m_device, nvh::loadFile("spv/lanternShadow.rmiss.spv", true, defaultSearchPaths, true));
|
||||
stage.stage = VK_SHADER_STAGE_MISS_BIT_KHR;
|
||||
stages[eMissLantern] = stage;
|
||||
````
|
||||
|
||||
and add this code for loading the last 2 closest hit shaders after loading
|
||||
`lantern.rchit.spv`:
|
||||
|
||||
```` C
|
||||
// OBJ Lantern Shadow Ray Hit Group
|
||||
vk::ShaderModule lanternShadowObjChitSM =
|
||||
nvvk::createShaderModule(m_device, //
|
||||
nvh::loadFile("shaders/lanternShadowObj.rchit.spv", true, paths, true));
|
||||
// Lantern Primary Ray Hit Group
|
||||
stage.module = nvvk::createShaderModule(m_device, nvh::loadFile("spv/lantern.rchit.spv", true, defaultSearchPaths, true));
|
||||
stage.stage = VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR;
|
||||
stages[eClosestHitLantern] = stage;
|
||||
|
||||
// OBJ Lantern Shadow Ray Hit Group
|
||||
stage.module =
|
||||
nvvk::createShaderModule(m_device, nvh::loadFile("spv/lanternShadowObj.rchit.spv", true, defaultSearchPaths, true));
|
||||
stage.stage = VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR;
|
||||
stages[eClosestHitLanternShdObj] = stage;
|
||||
|
||||
// ...
|
||||
|
||||
// Lantern Shadow Miss
|
||||
group.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_GENERAL_KHR;
|
||||
group.generalShader = eMissLantern;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
|
||||
// closest hit shader
|
||||
group.type = VK_RAY_TRACING_SHADER_GROUP_TYPE_TRIANGLES_HIT_GROUP_KHR;
|
||||
group.generalShader = VK_SHADER_UNUSED_KHR;
|
||||
group.closestHitShader = eClosestHit;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
group.closestHitShader = eClosestHitLantern;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
group.closestHitShader = eClosestHitLanternShdObj;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
group.closestHitShader = eClosestHitLanternShd;
|
||||
m_rtShaderGroups.push_back(group);
|
||||
|
||||
vk::RayTracingShaderGroupCreateInfoKHR lanternShadowObjHg{
|
||||
vk::RayTracingShaderGroupTypeKHR::eTrianglesHitGroup,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR};
|
||||
lanternShadowObjHg.setClosestHitShader(static_cast<uint32_t>(stages.size()));
|
||||
stages.push_back({{}, vk::ShaderStageFlagBits::eClosestHitKHR, lanternShadowObjChitSM, "main"});
|
||||
m_rtShaderGroups.push_back(lanternShadowObjHg);
|
||||
|
||||
// Lantern Lantern Shadow Ray Hit Group
|
||||
vk::ShaderModule lanternShadowLanternChitSM =
|
||||
nvvk::createShaderModule(m_device, //
|
||||
nvh::loadFile("shaders/lanternShadowLantern.rchit.spv", true, paths, true));
|
||||
|
||||
vk::RayTracingShaderGroupCreateInfoKHR lanternShadowLanternHg{
|
||||
vk::RayTracingShaderGroupTypeKHR::eTrianglesHitGroup,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR,
|
||||
VK_SHADER_UNUSED_KHR, VK_SHADER_UNUSED_KHR};
|
||||
lanternShadowLanternHg.setClosestHitShader(static_cast<uint32_t>(stages.size()));
|
||||
stages.push_back({{}, vk::ShaderStageFlagBits::eClosestHitKHR, lanternShadowLanternChitSM, "main"});
|
||||
m_rtShaderGroups.push_back(lanternShadowLanternHg);
|
||||
````
|
||||
|
||||
We need to destroy the added shader modules at the end of the function.
|
||||
|
|
@ -1386,7 +1405,7 @@ pass. There are minimal changes from before, we just have to
|
|||
to account for the added shaders.
|
||||
|
||||
```` C
|
||||
using Stride = vk::StridedDeviceAddressRegionKHR;
|
||||
using Stride = VkStridedDeviceAddressRegionKHR;
|
||||
std::array<Stride, 4> strideAddresses{
|
||||
Stride{sbtAddress + 0u * groupSize, groupStride, groupSize * 1}, // raygen
|
||||
Stride{sbtAddress + 1u * groupSize, groupStride, groupSize * 3}, // miss
|
||||
|
|
@ -1394,10 +1413,8 @@ pass. There are minimal changes from before, we just have to
|
|||
Stride{0u, 0u, 0u}}; // callable
|
||||
|
||||
// First pass, illuminate scene with global light.
|
||||
cmdBuf.traceRaysKHR(
|
||||
&strideAddresses[0], &strideAddresses[1], //
|
||||
&strideAddresses[2], &strideAddresses[3], //
|
||||
m_size.width, m_size.height, 1);
|
||||
vkCmdTraceRaysKHR(cmdBuf, &strideAddresses[0], &strideAddresses[1], &strideAddresses[2], &strideAddresses[3],
|
||||
m_size.width, m_size.height, 1);
|
||||
````
|
||||
|
||||
After that, we can open a loop for performing all lantern passes.
|
||||
|
|
@ -1412,25 +1429,23 @@ Because the additive blending in the shader requires read-modify-write operation
|
|||
we need a barrier between every pass.
|
||||
|
||||
```` C
|
||||
// Barrier to ensure previous pass finished.
|
||||
vk::Image offscreenImage{m_offscreenColor.image};
|
||||
vk::ImageSubresourceRange colorRange(
|
||||
vk::ImageAspectFlagBits::eColor, 0, VK_REMAINING_MIP_LEVELS, 0, VK_REMAINING_ARRAY_LAYERS
|
||||
);
|
||||
vk::ImageMemoryBarrier imageBarrier;
|
||||
imageBarrier.setOldLayout(vk::ImageLayout::eGeneral);
|
||||
imageBarrier.setNewLayout(vk::ImageLayout::eGeneral);
|
||||
imageBarrier.setSrcQueueFamilyIndex(VK_QUEUE_FAMILY_IGNORED);
|
||||
imageBarrier.setDstQueueFamilyIndex(VK_QUEUE_FAMILY_IGNORED);
|
||||
imageBarrier.setImage(offscreenImage);
|
||||
imageBarrier.setSubresourceRange(colorRange);
|
||||
imageBarrier.setSrcAccessMask(vk::AccessFlagBits::eShaderWrite);
|
||||
imageBarrier.setDstAccessMask(vk::AccessFlagBits::eShaderRead);
|
||||
cmdBuf.pipelineBarrier(
|
||||
vk::PipelineStageFlagBits::eRayTracingShaderKHR, //
|
||||
vk::PipelineStageFlagBits::eRayTracingShaderKHR, //
|
||||
vk::DependencyFlags(0), //
|
||||
{}, {}, {imageBarrier});
|
||||
// Barrier to ensure previous pass finished.
|
||||
VkImage offscreenImage{m_offscreenColor.image};
|
||||
VkImageSubresourceRange colorRange{VK_IMAGE_ASPECT_COLOR_BIT, 0, VK_REMAINING_MIP_LEVELS, 0, VK_REMAINING_ARRAY_LAYERS};
|
||||
VkImageMemoryBarrier imageBarrier{VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER};
|
||||
imageBarrier.oldLayout = VK_IMAGE_LAYOUT_GENERAL;
|
||||
imageBarrier.newLayout = VK_IMAGE_LAYOUT_GENERAL;
|
||||
imageBarrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
|
||||
imageBarrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
|
||||
imageBarrier.image = offscreenImage;
|
||||
imageBarrier.subresourceRange = colorRange;
|
||||
imageBarrier.srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT;
|
||||
imageBarrier.dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
|
||||
vkCmdPipelineBarrier(cmdBuf,
|
||||
VK_PIPELINE_STAGE_RAY_TRACING_SHADER_BIT_KHR, //
|
||||
VK_PIPELINE_STAGE_RAY_TRACING_SHADER_BIT_KHR, //
|
||||
VkDependencyFlags(0), //
|
||||
0, nullptr, 0, nullptr, 1, &imageBarrier);
|
||||
````
|
||||
|
||||
Then, we can pass the number of the lantern pass being performed (`i`), and look
|
||||
|
|
@ -1443,17 +1458,18 @@ is the first member of `LanternIndirectEntry`.
|
|||
```` C
|
||||
// Set lantern pass number.
|
||||
m_rtPushConstants.lanternPassNumber = i;
|
||||
cmdBuf.pushConstants<RtPushConstant>(m_rtPipelineLayout,
|
||||
vk::ShaderStageFlagBits::eRaygenKHR
|
||||
| vk::ShaderStageFlagBits::eClosestHitKHR
|
||||
| vk::ShaderStageFlagBits::eMissKHR,
|
||||
0, m_rtPushConstants);
|
||||
vkCmdPushConstants(cmdBuf, m_rtPipelineLayout,
|
||||
VK_SHADER_STAGE_RAYGEN_BIT_KHR | VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR | VK_SHADER_STAGE_MISS_BIT_KHR,
|
||||
0, sizeof(RtPushConstant), &m_rtPushConstants);
|
||||
|
||||
|
||||
VkDeviceAddress indirectDeviceAddress =
|
||||
nvvk::getBufferDeviceAddress(m_device, m_lanternIndirectBuffer.buffer) + i * sizeof(LanternIndirectEntry);
|
||||
|
||||
// Execute lantern pass.
|
||||
cmdBuf.traceRaysIndirectKHR(
|
||||
&strideAddresses[0], &strideAddresses[1], //
|
||||
&strideAddresses[2], &strideAddresses[3], //
|
||||
m_device.getBufferAddress({m_lanternIndirectBuffer.buffer}) + i * sizeof(LanternIndirectEntry));
|
||||
vkCmdTraceRaysIndirectKHR(cmdBuf, &strideAddresses[0], &strideAddresses[1], //
|
||||
&strideAddresses[2], &strideAddresses[3], //
|
||||
indirectDeviceAddress);
|
||||
}
|
||||
````
|
||||
|
||||
|
|
@ -1480,10 +1496,10 @@ void HelloVulkan::destroyResources()
|
|||
|
||||
// #VKRay
|
||||
// ...
|
||||
m_device.destroy(m_lanternIndirectDescPool);
|
||||
m_device.destroy(m_lanternIndirectDescSetLayout);
|
||||
m_device.destroy(m_lanternIndirectCompPipeline);
|
||||
m_device.destroy(m_lanternIndirectCompPipelineLayout);
|
||||
vkDestroyDescriptorPool(m_device, m_lanternIndirectDescPool, nullptr);
|
||||
vkDestroyDescriptorSetLayout(m_device, m_lanternIndirectDescSetLayout, nullptr);
|
||||
vkDestroyPipeline(m_device, m_lanternIndirectCompPipeline, nullptr);
|
||||
vkDestroyPipelineLayout(m_device, m_lanternIndirectCompPipelineLayout, nullptr);
|
||||
m_alloc.destroy(m_lanternIndirectBuffer);
|
||||
m_alloc.destroy(m_lanternVertexBuffer);
|
||||
m_alloc.destroy(m_lanternIndexBuffer);
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@
|
|||
Licensed as public domain or BSD 2-clause, whichever is more convenient for you.
|
||||
Originally from https://github.com/aras-p/markdeep-docs-style */
|
||||
body {
|
||||
max-width: 50em;
|
||||
max-width: 80em;
|
||||
font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;
|
||||
text-align: left;
|
||||
/*margin: 1.5em;*/
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue