Meshlets

struct Meshlet
{
    // Meshlet data.
    uint VertexOffset;
    uint VertexCount;
    uint PrimitiveOffset;
    uint PrimitiveCount;

    // Culling data.
    ...
};

std::vector<MyVertex> Vertices;
std::vector<Meshlet>  Meshlets;
std::vector<uint16_t> UniqueVertexIndices;
std::vector<uint8_t>  PrimitiveIndices;

#define MAX_MESHLET_SIZE 128

StructureBuffer<MyVertex>   Vertices;
StructureBuffer<Meshlet>    Meshlets;
StructuredBuffer<uint>      UniqueVertexIndices;
StructureBuffer<uint3>      PrimitiveIndices;

VertexOut TransformVertex(MyVertex v) { ... }

[NumThreads(MAX_MESHLET_SIZE, 1, 1)]
[OutputTopology("triangle")]
void main(
    uint groupThreadId : SV_GroupIndex,
    uint groupId : SV_GroupID,
    out vertices VertexOut verts[MAX_MESHLET_SIZE],
    out indices uint3 tris[MAX_MESHLET_SIZE])
{
    Meshlet m = Meshlets[groupId];

    SetMeshOutputCounts(m.VertCount, m.PrimCount);

    if (groupThreadId < m.PrimCount) 
    {
        tris[groupThreadId] = PrimitiveIndices[m.PrimOffset + groupThreadId];
    }

    if (groupThreadId < m.VertCount) 
    {
        uint index = UniqueVertexIndices[m.VertOffset + groupThreadId];
        MyVertex vin = Vertices[index];

        verts[groupThreadId] = TransformVertex(vin);
    }
}