acdream/tests/AcDream.App.Tests/Rendering/Gpu/RecordingGpuDeviceTests.cs
Erik 621b16364b feat(render): Campaign V slice V0 — pin the Vulkan-shaped RHI contract
Campaign V migrates the renderer from OpenGL 4.3+extensions to a single
Vulkan 1.3 backend on Windows x64 and Linux x64, then deletes the GL path.
Motivation is compatibility and efficiency, not rescue: mandatory
GL_ARB_bindless_texture is the exact floor that parked Slice L (Mesa
D3D12/llvmpipe lack it) while Vulkan descriptor indexing is core, and
per-frame data can be written straight into mapped memory rather than
copied through BufferSubData.

V0 pins the contract every later slice codes against. Nothing consumes it
yet, so this commit changes no runtime behavior.

The seam is a minimal Vulkan-shaped RHI implemented FIRST on GL. That
ordering is the point: the twelve renderers then port one at a time under a
strict pixel gate on the still-shipping backend, so a divergence is
attributed to one slice instead of surfacing at a big-bang integration.
Duplicating renderers per backend was rejected because WbDrawDispatcher is
4,449 lines holding only ~62 GL call sites — the API surface is small and
the retail-fidelity CPU logic is large, and forking the latter is how subtle
regressions enter.

Contract highlights:
  - GpuBindingModel pins set/binding numbers dual-legal for GL and Vulkan
    GLSL. Storage bindings 0-8 keep today's shader numbering; UBOs move to
    their own set, which resolves the binding=1 collision GL only tolerates
    because it keeps SSBO and UBO tables separate.
  - GpuRingAllocation is a ref struct replacing every per-frame
    BufferSubData; the compiler forbids outliving the owning frame.
  - GpuTextureSlot replaces bindless handles. Unassigned is a loud
    uint.MaxValue sentinel rather than a silent resolve to slot 0 — the
    failure mode behind the magenta 1x1 UI placeholder bug. Renderers
    needing a fallback take the device's really-registered default slot.
  - Renderers always speak GL winding/viewport conventions; the Vulkan
    backend compensates with a negative viewport height in exactly one
    mapping function.

Verified while writing the plan: acdream's cameras already build
[0,1]-NDC projections (PortalProjection.cs:12-13), which is Vulkan's
convention. No projection rework is needed and depth precision improves,
at the cost of shifted z-fight patterns — the one pre-approved divergence
class, registered per instance at V7.

Gate: Release build green; App suite 3,785 passed / 3 skipped (3,763
baseline plus 22 new contract tests). Note for later slices, recorded in
the plan: run the suite in Release. LandblockBuildOriginTests'
far-strip test asserts behavior that LandblockStreamer.cs:505 deliberately
turns into a loud Debug.Assert in Debug builds, so a Debug run shows one
pre-existing failure that is not a regression.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 14:26:26 +02:00

221 lines
7.5 KiB
C#

using System.Numerics;
using AcDream.App.Rendering.Gpu;
namespace AcDream.App.Tests.Rendering.Gpu;
/// <summary>
/// Campaign V slice V0 — the test double every later renderer-port slice asserts
/// against. If the double misreports ordering or ring alignment, the migration
/// slices inherit false confidence, so it gets its own tests.
/// </summary>
public sealed class RecordingGpuDeviceTests
{
[Fact]
public void FramePassAndDrawCallsAreRecordedInSubmissionOrder()
{
using RecordingGpuDevice device = new();
IGpuPipeline pipeline = device.CreatePipeline(new GpuPipelineDescription
{
Name = "mesh-opaque",
Shaders = new GpuShaderSet("mesh_modern"),
VertexLayout = GpuVertexLayout.WorldMesh,
});
IGpuBuffer indirect = device.CreateBuffer(new GpuBufferDescription(
"indirect", 4096, GpuBufferUsage.Indirect, GpuMemoryResidency.HostWritable));
device.Clear();
using (IGpuFrame frame = device.BeginFrame())
{
using (IGpuPassEncoder pass = frame.BeginPass(
GpuPassDescription.BackbufferClear("world", Vector4.Zero, sampleCount: 1)))
{
pass.BindPipeline(pipeline);
pass.SetCullMode(GpuCullMode.None);
pass.MultiDrawIndexedIndirect(indirect, offsetBytes: 0, drawCount: 12, strideBytes: 20);
}
frame.End();
}
Assert.Collection(
device.Calls,
call => Assert.Equal(new GpuRecordedFrameBegin(1, 0), call),
call => Assert.Equal(new GpuRecordedPassBegin("world", 1), call),
call => Assert.Equal(new GpuRecordedPipelineBind("mesh-opaque"), call),
call => Assert.Equal(new GpuRecordedCullMode(GpuCullMode.None), call),
call => Assert.Equal(new GpuRecordedMultiDrawIndirect("indirect", 0, 12, 20), call),
call => Assert.Equal(new GpuRecordedPassEnd("world"), call),
call => Assert.Equal(new GpuRecordedFrameEnd(1), call));
}
[Fact]
public void RingAllocationsAreAlignedForTheirUsageAndReadableAfterWriting()
{
using RecordingGpuDevice device = new();
uint storageAlignment = device.Capabilities.MinStorageBufferOffsetAlignment;
using IGpuFrame frame = device.BeginFrame();
GpuRingAllocation first = frame.AllocateRing(12, GpuRingUsage.Indirect);
Assert.Equal(0u, first.OffsetBytes);
Assert.Equal(12, first.Data.Length);
GpuRingAllocation second = frame.AllocateRing(64, GpuRingUsage.Storage);
Assert.Equal(0u, second.OffsetBytes % storageAlignment);
Assert.True(second.OffsetBytes >= 12);
Span<Matrix4x4> transforms = second.AsSpan<Matrix4x4>();
Assert.Equal(1, transforms.Length);
transforms[0] = Matrix4x4.CreateTranslation(1f, 2f, 3f);
frame.End();
// The bytes a renderer writes are the bytes a driver would read; a test can
// therefore verify upload content without a GPU.
ReadOnlySpan<byte> ring = device.RingBytes;
Matrix4x4 written = System.Runtime.InteropServices.MemoryMarshal.Read<Matrix4x4>(
ring.Slice((int)second.OffsetBytes, 64));
Assert.Equal(Matrix4x4.CreateTranslation(1f, 2f, 3f), written);
}
[Fact]
public void RingIsRewoundEachFrameSoPerFrameDataDoesNotAccumulate()
{
using RecordingGpuDevice device = new();
using (IGpuFrame first = device.BeginFrame())
{
first.AllocateRing(256, GpuRingUsage.Storage);
first.End();
}
uint afterFirst = device.RingBytesAllocated;
using (IGpuFrame second = device.BeginFrame())
{
GpuRingAllocation allocation = second.AllocateRing(256, GpuRingUsage.Storage);
Assert.Equal(0u, allocation.OffsetBytes);
second.End();
}
Assert.Equal(afterFirst, device.RingBytesAllocated);
}
[Fact]
public void OverlargeRingRequestThrowsRatherThanTruncating()
{
using RecordingGpuDevice device = new(ringCapacityBytes: 1024);
using IGpuFrame frame = device.BeginFrame();
// Silently shortening an allocation would corrupt the frame invisibly.
Assert.Throws<InvalidOperationException>(() =>
{
frame.AllocateRing(4096, GpuRingUsage.Storage);
});
}
[Fact]
public void OverlappingFramesAreRejected()
{
using RecordingGpuDevice device = new();
using IGpuFrame frame = device.BeginFrame();
Assert.Throws<InvalidOperationException>(device.BeginFrame);
}
[Fact]
public void FrameSlotsAlternateAcrossTwoFramesInFlight()
{
using RecordingGpuDevice device = new();
int[] slots = new int[4];
for (int i = 0; i < slots.Length; i++)
{
using IGpuFrame frame = device.BeginFrame();
slots[i] = frame.SlotIndex;
frame.End();
}
Assert.Equal([0, 1, 0, 1], slots);
Assert.Equal(0, device.OpenFrameCount);
}
[Fact]
public void ReleasedTextureSlotsAreRecycledRatherThanLeaked()
{
using RecordingGpuDevice device = new();
IGpuSampler sampler = device.CreateSampler(GpuSamplerDescription.WorldRepeat);
IGpuTexture texture = device.CreateTexture(new GpuTextureDescription(
"wall", GpuTextureKind.Texture2DArray, GpuTextureFormat.Bc1Unorm, 64, 64, 4, 1));
int liveBefore = device.LiveTextureSlotCount;
GpuTextureSlot slot = device.RegisterTexture(texture, sampler);
Assert.True(slot.IsAssigned);
Assert.Equal(liveBefore + 1, device.LiveTextureSlotCount);
device.ReleaseTextureSlot(slot);
Assert.Equal(liveBefore, device.LiveTextureSlotCount);
GpuTextureSlot reused = device.RegisterTexture(texture, sampler);
Assert.Equal(slot.Index, reused.Index);
}
[Fact]
public void ReleasingAnUnassignedSlotIsRejected()
{
using RecordingGpuDevice device = new();
Assert.Throws<ArgumentException>(() => device.ReleaseTextureSlot(GpuTextureSlot.Unassigned));
}
[Fact]
public void DefaultTextureSlotIsRegisteredAndUsable()
{
using RecordingGpuDevice device = new();
// Renderers needing a fallback take this, rather than assuming slot 0
// resolves to something sensible.
Assert.True(device.DefaultTextureSlot.IsAssigned);
}
[Fact]
public void SamplersAreDeduplicatedByValue()
{
using RecordingGpuDevice device = new();
IGpuSampler first = device.CreateSampler(GpuSamplerDescription.WorldRepeat);
IGpuSampler second = device.CreateSampler(GpuSamplerDescription.WorldRepeat);
IGpuSampler other = device.CreateSampler(GpuSamplerDescription.UiNearest);
Assert.Same(first, second);
Assert.NotSame(first, other);
}
[Fact]
public void QueuedDeviceActionsRunOnlyWhenProcessed()
{
using RecordingGpuDevice device = new();
int ran = 0;
device.QueueDeviceAction(() => ran++);
Assert.Equal(0, ran);
device.ProcessDeviceActions();
Assert.Equal(1, ran);
device.ProcessDeviceActions();
Assert.Equal(1, ran);
}
[Fact]
public void DisposingAFrameClosesItExactlyOnce()
{
using RecordingGpuDevice device = new();
IGpuFrame frame = device.BeginFrame();
frame.End();
frame.Dispose();
Assert.Single(device.OfKind<GpuRecordedFrameEnd>());
Assert.Equal(0, device.OpenFrameCount);
}
}