acdream/src/AcDream.App/Rendering/TerrainModernRenderer.Rhi.cs

using System.Collections.Immutable;
using System.Numerics;
using System.Runtime.InteropServices;
using AcDream.App.Rendering.Gpu;
using AcDream.App.Rendering.Wb;
using AcDream.Core.Terrain;

namespace AcDream.App.Rendering;

/// <summary>
/// Campaign V slice V6j: terrain's RHI submission arm.
///
/// <para>This is V4d-2's content, re-landed as a SECOND arm rather than as a
/// replacement. §5.5.6 selected option (B) after NVIDIA rendered the V4c binary
/// 10/10 and AMD's GL stack did not: GL keeps its raw world path through to V10
/// as a documented, scoped fork confined to the submission seam, and the RHI
/// world path ships on Vulkan. So every GL statement in the sibling file is
/// untouched, and everything here runs only when there is no GL context.</para>
///
/// <para>Three things differ from V4d-2, each because the tree moved under it.
/// The texture slots come from <c>TerrainAtlas</c>'s device table (V4t) rather
/// than a per-renderer bindless table, so there is no binding-9 table to bind at
/// all — the Vulkan texture table is set 2 and the encoder binds it. The tiling
/// block is the shared <c>TerrainTextureTilingTable</c> constants (V6f-2) rather
/// than locals. And the pass is BORROWED from <see cref="IWorldPassScope"/>
/// rather than opened, because the frame's one backbuffer pass resolves and a
/// second pass could not load what it left.</para>
/// </summary>
public sealed unsafe partial class TerrainModernRenderer
{
    /// <summary>
    /// Terrain's vertex layout: the same 40-byte record <c>ConfigureVao</c>
    /// describes with <c>glVertexAttribPointer</c>/<c>glVertexAttribIPointer</c>.
    ///
    /// <para>Locations 2–5 are <see cref="GpuVertexFormat.UByte4UInt"/>, not
    /// <c>UByte4Normalized</c>. They are <c>uvec4</c> in the shader and carry
    /// terrain-type, road and split-direction codes; normalising them would not
    /// be an approximation, it would be garbage.</para>
    /// </summary>
    internal static readonly GpuVertexLayout TerrainVertexLayout = GpuVertexLayout.Interleaved(
        strideBytes: VertexSize,
        ImmutableArray.Create(
            new GpuVertexAttribute(0, GpuVertexFormat.Float3, 0),
            new GpuVertexAttribute(1, GpuVertexFormat.Float3, 12),
            new GpuVertexAttribute(2, GpuVertexFormat.UByte4UInt, 24),
            new GpuVertexAttribute(3, GpuVertexFormat.UByte4UInt, 28),
            new GpuVertexAttribute(4, GpuVertexFormat.UByte4UInt, 32),
            new GpuVertexAttribute(5, GpuVertexFormat.UByte4UInt, 36)));

    private readonly IGpuDevice? _device;
    private readonly ICurrentGpuFrameSource? _frames;
    private readonly IWorldPassScope? _scope;
    private IGpuPipeline? _pipeline;
    private IGpuBuffer? _vertexStore;
    private IGpuBuffer? _indexStore;
    private IGpuBuffer? _tilingBuffer;

    /// <summary>
    /// The RHI arm's constructor. No GL context, no <c>Shader</c>, no
    /// <c>BindlessSupport</c>: the pipeline compiles <c>terrain_modern</c> from
    /// the committed SPIR-V and the atlas's slots index the device's one table.
    /// </summary>
    internal TerrainModernRenderer(
        IGpuDevice device,
        ICurrentGpuFrameSource frames,
        IWorldPassScope scope,
        TerrainAtlas atlas,
        IGpuResourceRetirementQueue resourceRetirement,
        int initialSlotCapacity = 64)
    {
        _device = device ?? throw new ArgumentNullException(nameof(device));
        _frames = frames ?? throw new ArgumentNullException(nameof(frames));
        _scope = scope ?? throw new ArgumentNullException(nameof(scope));
        _atlas = atlas ?? throw new ArgumentNullException(nameof(atlas));
        ArgumentNullException.ThrowIfNull(resourceRetirement);
        _retirementLedger = new GpuRetirementLedger(resourceRetirement);
        _alloc = new GpuRetiredTerrainSlotAllocator(initialSlotCapacity, resourceRetirement);
        _slots = new SlotData?[initialSlotCapacity];

        _pipeline = device.CreatePipeline(new GpuPipelineDescription
        {
            Name = "terrain",
            Shaders = new GpuShaderSet("terrain_modern"),
            VertexLayout = TerrainVertexLayout,
            Topology = GpuPrimitiveTopology.TriangleList,
            Blend = GpuBlendMode.None,
            // GL_LESS, not the contract's LessOrEqual default: the world frame
            // runs under GL_LESS and terrain never called glDepthFunc, so it
            // inherited it. LessOrEqual would change which of two coplanar retail
            // surfaces wins — visible exactly where terrain meets roads and
            // building footings, which is what zFightTerrainAdjust is about.
            Depth = new GpuDepthState(Test: true, Write: true, GpuCompareOp.Less),
            // #108-residual: retail terrain is SINGLE-SIDED. See the GL arm's
            // Draw for the full reasoning; this bakes the same triple.
            Cull = GpuCullMode.Back,
            FrontFace = GpuFrontFace.CounterClockwise,
            AlphaToCoverage = false,
            ColorWrite = true,
            SampleCount = scope.SampleCount,
        });
        AllocateRhiBuffers(initialSlotCapacity);
    }

    private void AllocateRhiBuffers(int capacitySlots)
    {
        long vertexBytes = checked((long)capacitySlots * VertsPerLandblock * VertexSize);
        long indexBytes = checked((long)capacitySlots * IndicesPerLandblock * IndexSize);
        IGpuDevice device = RequireDevice();
        _vertexStore = device.CreateBuffer(new GpuBufferDescription(
            "terrain-vertices",
            vertexBytes,
            GpuBufferUsage.Vertex
                | GpuBufferUsage.TransferSource
                | GpuBufferUsage.TransferDestination,
            GpuMemoryResidency.DeviceLocal));
        _globalVboCapacityBytes = vertexBytes;
        _indexStore = device.CreateBuffer(new GpuBufferDescription(
            "terrain-indices",
            indexBytes,
            GpuBufferUsage.Index
                | GpuBufferUsage.TransferSource
                | GpuBufferUsage.TransferDestination,
            GpuMemoryResidency.DeviceLocal));
        _globalEboCapacityBytes = indexBytes;
    }

    /// <summary>
    /// Grow-and-copy, device-side. <see cref="IGpuBuffer.CopyTo"/> keeps resident
    /// landblock meshes from round-tripping through system memory, exactly as the
    /// GL arm's <c>glCopyBufferSubData</c> does.
    /// </summary>
    private void EnsureRhiCapacity(int newCapacitySlots)
    {
        if (newCapacitySlots <= _alloc.Capacity)
            return;

        long vertexBytes = checked((long)newCapacitySlots * VertsPerLandblock * VertexSize);
        long indexBytes = checked((long)newCapacitySlots * IndicesPerLandblock * IndexSize);
        IGpuDevice device = RequireDevice();
        IGpuBuffer oldVertices = RequireVertexStore();
        IGpuBuffer oldIndices = RequireIndexStore();

        IGpuBuffer newVertices = device.CreateBuffer(new GpuBufferDescription(
            "terrain-vertices",
            vertexBytes,
            GpuBufferUsage.Vertex
                | GpuBufferUsage.TransferSource
                | GpuBufferUsage.TransferDestination,
            GpuMemoryResidency.DeviceLocal));
        IGpuBuffer newIndices;
        try
        {
            newIndices = device.CreateBuffer(new GpuBufferDescription(
                "terrain-indices",
                indexBytes,
                GpuBufferUsage.Index
                    | GpuBufferUsage.TransferSource
                    | GpuBufferUsage.TransferDestination,
                GpuMemoryResidency.DeviceLocal));
        }
        catch
        {
            newVertices.Dispose();
            throw;
        }

        oldVertices.CopyTo(newVertices, 0, 0, _globalVboCapacityBytes);
        oldIndices.CopyTo(newIndices, 0, 0, _globalEboCapacityBytes);

        _vertexStore = newVertices;
        _indexStore = newIndices;
        _globalVboCapacityBytes = vertexBytes;
        _globalEboCapacityBytes = indexBytes;

        // Dispose routes the physical free through the device's retirement queue,
        // so the old arena outlives every frame that can still reference it.
        oldVertices.Dispose();
        oldIndices.Dispose();

        var grownSlots = new SlotData?[newCapacitySlots];
        Array.Copy(_slots, grownSlots, _slots.Length);
        _slots = grownSlots;
        _alloc.GrowTo(newCapacitySlots);
    }

    private void UploadRhiLandblock(
        int slot,
        TerrainVertex[] bakedVerts,
        uint[] bakedIndices)
    {
        RequireVertexStore().Upload(
            (long)slot * VertsPerLandblock * VertexSize,
            MemoryMarshal.AsBytes<TerrainVertex>(bakedVerts));
        RequireIndexStore().Upload(
            (long)slot * IndicesPerLandblock * IndexSize,
            MemoryMarshal.AsBytes<uint>(bakedIndices));
    }

    /// <summary>
    /// Records terrain's multi-draw into the borrowed world pass.
    ///
    /// <para>Order matters twice. <c>BindPipeline</c> re-issues the pipeline's own
    /// cull/front-face/depth-write defaults, so anything dynamic has to come
    /// after it. And the frame-global sections — SceneLighting and the terrain
    /// clip block — are bound HERE, after this renderer's own binds, because its
    /// own binds are what select the descriptor scope those sections must land in
    /// (plan §5.5.14 item 2).</para>
    /// </summary>
    private void DrawRhi(Matrix4x4 viewProjection, int drawCount)
    {
        IWorldPassScope scope = _scope!;
        IGpuPassEncoder encoder = scope.RequireEncoder();
        IGpuFrame frame = _frames!.CurrentFrame
            ?? throw new InvalidOperationException(
                "TerrainModernRenderer requires an open IGpuFrame (see GpuDeviceFrameLifetime).");

        // V6i-2's backend-neutral atlas registers both slots at construction, so
        // there is no per-draw acquire-and-reregister step and no binding-9 table
        // to flush — the Vulkan texture table is set 2 and the encoder binds it.
        (GpuTextureSlot terrainSlot, GpuTextureSlot alphaSlot) = _atlas.TextureSlots;

        var pushConstants = new GpuPushConstants
        {
            ViewProjection = viewProjection,
            DrawIdOffset = 0,
            LightingMode = 0,
            RenderPass = 0,
            LightDebug = 0,
            TextureIndexA = terrainSlot.Index,
            TextureIndexB = alphaSlot.Index,
            ParamA = 0f,
            ParamB = 0f,
        };

        encoder.BindPipeline(_pipeline!);
        encoder.SetPushConstants(in pushConstants);
        encoder.BindVertexBuffer(0, RequireVertexStore(), 0);
        encoder.BindIndexBuffer(RequireIndexStore(), 0, GpuIndexType.UInt32);
        BindTilingTable(encoder);
        WorldFrameSectionBinding.BindSceneLighting(encoder, scope.Sections, frame);
        WorldFrameSectionBinding.BindTerrainClip(encoder, scope.Sections, frame);

        GpuRingAllocation commands = frame.AllocateRing(
            drawCount * sizeof(DrawElementsIndirectCommand),
            GpuRingUsage.Indirect);
        MemoryMarshal.AsBytes(_deicScratch.AsSpan(0, drawCount))
            .CopyTo(commands.Data);
        encoder.MultiDrawIndexedIndirect(
            commands.Buffer,
            commands.OffsetBytes,
            (uint)drawCount,
            (uint)sizeof(DrawElementsIndirectCommand));
    }

    /// <summary>
    /// Binds the immutable 36-entry tiling table. Long-lived and written once, so
    /// its range never moves — which also keeps it out of the descriptor-scope
    /// key's moving parts.
    /// </summary>
    private void BindTilingTable(IGpuPassEncoder encoder)
    {
        if (_tilingBuffer is null)
        {
            if (_atlas.TilingByLayer.Count != TerrainTextureTilingTable.LayerCapacity)
            {
                throw new InvalidOperationException(
                    $"Terrain tiling table has {_atlas.TilingByLayer.Count} entries; " +
                    $"expected {TerrainTextureTilingTable.LayerCapacity}.");
            }

            Span<byte> block = stackalloc byte[TerrainTextureTilingTable.UniformBufferBytes];
            block.Clear();
            for (int i = 0; i < TerrainTextureTilingTable.LayerCapacity; i++)
            {
                BitConverter.TryWriteBytes(
                    block[(i * TerrainTextureTilingTable.UniformElementStrideBytes)..],
                    _atlas.TilingByLayer[i]);
            }

            IGpuBuffer buffer = RequireDevice().CreateBuffer(new GpuBufferDescription(
                "terrain-tiling",
                TerrainTextureTilingTable.UniformBufferBytes,
                GpuBufferUsage.Uniform | GpuBufferUsage.TransferDestination,
                GpuMemoryResidency.DeviceLocal));
            try
            {
                buffer.Upload(0, block);
            }
            catch
            {
                buffer.Dispose();
                throw;
            }
            _tilingBuffer = buffer;
        }

        encoder.BindUniformBuffer(
            GpuBindingModel.UniformTerrainTiling,
            _tilingBuffer,
            0,
            TerrainTextureTilingTable.UniformBufferBytes);
    }

    private IGpuDevice RequireDevice() =>
        _device ?? throw new InvalidOperationException(
            "TerrainModernRenderer's RHI arm was reached without an IGpuDevice.");

    private IGpuBuffer RequireVertexStore() =>
        _vertexStore ?? throw new InvalidOperationException(
            "The terrain vertex arena has not been created.");

    private IGpuBuffer RequireIndexStore() =>
        _indexStore ?? throw new InvalidOperationException(
            "The terrain index arena has not been created.");

    private void DisposeRhi()
    {
        _pipeline?.Dispose();
        _pipeline = null;
        _tilingBuffer?.Dispose();
        _tilingBuffer = null;
        _vertexStore?.Dispose();
        _vertexStore = null;
        _indexStore?.Dispose();
        _indexStore = null;
        _globalVboCapacityBytes = 0;
        _globalEboCapacityBytes = 0;
        _dynamicFrameStarted = false;
        _disposed = true;
    }
}