mirror of
https://github.com/Kelsidavis/WoWee.git
synced 2026-05-03 08:03:50 +00:00
d54e262048
M2 GPU instancing - M2InstanceGPU SSBO (96 B/entry, double-buffered, 16384 max) - Group opaque instances by (modelId, LOD); single vkCmdDrawIndexed per group - boneBase field indexes into mega bone SSBO via gl_InstanceIndex Indirect terrain drawing - 24 MB mega index buffer (6M uint32) + 64 MB mega vertex buffer - CPU builds VkDrawIndexedIndirectCommand per visible chunk - Single VB/IB bind per frame; shadow pass reuses mega buffers - Replaced vkCmdDrawIndexedIndirect with direct vkCmdDrawIndexed to fix host-mapped buffer race condition that caused terrain flickering GPU frustum culling (compute shader) - m2_cull.comp.glsl: 64-thread workgroups, sphere-vs-6-planes + distance cull - CullInstanceGPU SSBO input, uint visibility[] output, double-buffered - dispatchCullCompute() runs before main pass via render graph node Consolidated bone matrix SSBOs - 16 MB double-buffered mega bone SSBO (2048 instances × 128 bones) - Eliminated per-instance descriptor sets; one megaBoneSet_ per frame - prepareRender() packs bone matrices consecutively into current frame slot Render graph / frame graph - RenderGraph: RGResource handles, RGPass nodes, Kahn topological sort - Automatic VkImageMemoryBarrier/VkBufferMemoryBarrier between passes - Passes: minimap_composite, worldmap_composite, preview_composite, shadow_pass, reflection_pass, compute_cull - beginFrame() uses buildFrameGraph() + renderGraph_->execute(cmd) Pipeline derivatives - PipelineBuilder::setFlags/setBasePipeline for VK_PIPELINE_CREATE_DERIVATIVE_BIT - M2 opaque = base; alphaTest/alpha/additive are derivatives - Applied to terrain (wireframe) and WMO (alpha-test) renderers Rendering bug fixes: - fix(shadow): compute lightSpaceMatrix before updatePerFrameUBO to eliminate one-frame lag that caused shadow trails and flicker on moving objects - fix(shadow): scale depth bias with shadowDistance_ instead of hardcoded 0.8f to prevent acne at close range and gaps at far range - fix(visibility): WMO group distance threshold 500u → 1200u to match terrain view distance; buildings were disappearing on the horizon - fix(precision): camera near plane 0.05 → 0.5 (ratio 600K:1 → 60K:1), eliminating Z-fighting and improving frustum plane extraction stability - fix(streaming): terrain load radius 4 → 6 tiles (~2133u → ~3200u) to exceed M2 render distance (2800u) and eliminate pop-in when camera turns; unload radius 7 → 9; spawn radius 3 → 4 - fix(visibility): ground-detail M2 distance multiplier 0.75 → 0.9 to reduce early pop of grass and debris
76 lines
2.1 KiB
GLSL
76 lines
2.1 KiB
GLSL
#version 450
|
|
|
|
// Phase 2.3: GPU Frustum Culling for M2 doodads
|
|
// Each compute thread tests one M2 instance against 6 frustum planes.
|
|
// Input: per-instance bounding sphere + flags.
|
|
// Output: uint visibility array (1 = visible, 0 = culled).
|
|
|
|
layout(local_size_x = 64) in;
|
|
|
|
// Per-instance cull data (uploaded from CPU each frame)
|
|
struct CullInstance {
|
|
vec4 sphere; // xyz = world position, w = padded radius
|
|
float effectiveMaxDistSq; // adaptive distance cull threshold
|
|
uint flags; // bit 0 = valid, bit 1 = smoke, bit 2 = invisibleTrap
|
|
float _pad0;
|
|
float _pad1;
|
|
};
|
|
|
|
layout(std140, set = 0, binding = 0) uniform CullUniforms {
|
|
vec4 frustumPlanes[6]; // xyz = normal, w = distance
|
|
vec4 cameraPos; // xyz = camera position, w = maxPossibleDistSq
|
|
uint instanceCount;
|
|
uint _pad0;
|
|
uint _pad1;
|
|
uint _pad2;
|
|
};
|
|
|
|
layout(std430, set = 0, binding = 1) readonly buffer CullInput {
|
|
CullInstance cullInstances[];
|
|
};
|
|
|
|
layout(std430, set = 0, binding = 2) writeonly buffer CullOutput {
|
|
uint visibility[];
|
|
};
|
|
|
|
void main() {
|
|
uint id = gl_GlobalInvocationID.x;
|
|
if (id >= instanceCount) return;
|
|
|
|
CullInstance inst = cullInstances[id];
|
|
|
|
// Flag check: must be valid, not smoke, not invisible trap
|
|
uint f = inst.flags;
|
|
if ((f & 1u) == 0u || (f & 6u) != 0u) {
|
|
visibility[id] = 0u;
|
|
return;
|
|
}
|
|
|
|
// Early distance rejection (loose upper bound)
|
|
vec3 toCam = inst.sphere.xyz - cameraPos.xyz;
|
|
float distSq = dot(toCam, toCam);
|
|
if (distSq > cameraPos.w) {
|
|
visibility[id] = 0u;
|
|
return;
|
|
}
|
|
|
|
// Accurate per-instance distance cull
|
|
if (distSq > inst.effectiveMaxDistSq) {
|
|
visibility[id] = 0u;
|
|
return;
|
|
}
|
|
|
|
// Frustum cull: sphere vs 6 planes
|
|
float radius = inst.sphere.w;
|
|
if (radius > 0.0) {
|
|
for (int i = 0; i < 6; i++) {
|
|
float d = dot(frustumPlanes[i].xyz, inst.sphere.xyz) + frustumPlanes[i].w;
|
|
if (d < -radius) {
|
|
visibility[id] = 0u;
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
|
|
visibility[id] = 1u;
|
|
}
|