mhtirogla
Home
Systems
API
Pricing
About
Log in
← Back
Home
›
Systems
›
Games
world-streaming
open-world asset streaming
Unreal World Partition
System
Techniques · 9
Primitives · 30
world-streaming
Work-stealing deque
concurrency · medium: Per-worker deque: the owner pushes and pops at the bottom without contention, idle workers steal from the top; the core of Rayon, Tokio and Go.
›
Asset streaming priority
graphics · medium: Prioritized async loading of assets by distance and visibility under a memory budget with eviction
Frustum occlusion culling
graphics · medium: Frustum tests on bounds, hierarchical-Z occlusion and GPU culling passes
Gpu asset decompression
graphics · medium: Decompress assets on the GPU (GDeflate, DirectStorage) straight from NVMe to VRAM
Mesh simplification quadric
graphics · medium: Edge collapse with quadric error metrics to build mesh LODs
Meshlet cluster lod
graphics · medium: Split meshes into small clusters with a LOD DAG for fine-grained culling and streaming (Nanite-style)
Virtual texturing
graphics · medium: Sparse virtual textures: page tables, feedback buffers and streaming of mip tiles
LRU and CLOCK
systems · low: LRU evicts the least recently used entry via hash map plus linked list; CLOCK approximates it with a reference bit, so hits take no lock.
›
LZ4
compression · low: Byte-aligned LZ77 with no entropy stage; compresses at hundreds of MB/s and decompresses at several GB/s per core, for when speed beats ratio.
›
Zstandard (zstd)
compression · low: LZ77 plus Huffman and FSE entropy coding, with levels from LZ4-like speed to xz-like ratio, all decoding at about 1-2 GB/s.
›
Quadtree octree
geometry · low: Adaptive spatial subdivision trees for queries and level of detail; loose and linear variants
Floating origin rebasing
graphics · low: Shift the world origin near the camera to keep float precision in huge worlds
io_uring
networking · low: Linux async I/O through two shared-memory rings (submissions in, completions out), batching or eliminating syscalls for sockets and files alike.
›
Spatial hashing
physics · low: Uniform grid stored in a hash table: bucket objects by cell, test only neighbouring cells; O(n) neighbour search for many similar-sized objects such as particles.
›
Buddy allocator
systems · low: Power-of-two block splitting and coalescing; base of kernel page and GPU heap allocators
Epoch-based reclamation
concurrency · low: Threads announce a global epoch while touching shared lock-free data; garbage retired in epoch e is freed once the epoch reaches e + 2.
›
Memory ordering
concurrency · low: What Relaxed, Acquire, Release and SeqCst atomics actually guarantee, what they cost on x86 and ARM, and which one each pattern needs.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
Buffer pools for zero-allocation I/O
hardware-os · low: Preallocate a fixed set of aligned I/O buffers and recycle them through a free list, so the hot path never mallocs, faults or unmaps. The bounded count doubles as back pressure.
›
Homogeneous transforms
geometry · low: 4x4 affine and projective matrices, homogeneous coordinates, view and projection, normal matrices
Image pyramids
graphics · low: Gaussian/Laplacian pyramids and tiled multi-resolution images for zoom and blending
GPU compute shaders
ml-training · low: The vendor-neutral GPU launch model of Metal, Vulkan and WebGPU: a grid of workgroups, shared memory, barriers and subgroups, driven by recorded command buffers.
›
Bounding volume hierarchy
physics · low: Binary tree of nested bounding boxes; prunes overlap and ray queries to O(log n) for any size distribution, and supports cheap insert/remove for moving objects.
›
+ 2 more techniques
+ 14 more primitives
System
Techniques · 9
Primitives · 30
world-streaming
Work-stealing deque
concurrency · medium: Per-worker deque: the owner pushes and pops at the bottom without contention, idle workers steal from the top; the core of Rayon, Tokio and Go.
›
Asset streaming priority
graphics · medium: Prioritized async loading of assets by distance and visibility under a memory budget with eviction
Frustum occlusion culling
graphics · medium: Frustum tests on bounds, hierarchical-Z occlusion and GPU culling passes
Gpu asset decompression
graphics · medium: Decompress assets on the GPU (GDeflate, DirectStorage) straight from NVMe to VRAM
Mesh simplification quadric
graphics · medium: Edge collapse with quadric error metrics to build mesh LODs
Meshlet cluster lod
graphics · medium: Split meshes into small clusters with a LOD DAG for fine-grained culling and streaming (Nanite-style)
Virtual texturing
graphics · medium: Sparse virtual textures: page tables, feedback buffers and streaming of mip tiles
Gpu driven indirect rendering
graphics · medium: GPU culls and builds draw lists for indirect multi-draw, removing CPU draw-call cost
Graph partitioning
graphs · medium: Split a graph into k balanced parts with few edges between them; multilevel coarsen-partition-refine (METIS, KaHIP) for quality, streaming heuristics (LDG, Fennel) for one-pass scale.
›
LRU and CLOCK
systems · low: LRU evicts the least recently used entry via hash map plus linked list; CLOCK approximates it with a reference bit, so hits take no lock.
›
LZ4
compression · low: Byte-aligned LZ77 with no entropy stage; compresses at hundreds of MB/s and decompresses at several GB/s per core, for when speed beats ratio.
›
Zstandard (zstd)
compression · low: LZ77 plus Huffman and FSE entropy coding, with levels from LZ4-like speed to xz-like ratio, all decoding at about 1-2 GB/s.
›
Quadtree octree
geometry · low: Adaptive spatial subdivision trees for queries and level of detail; loose and linear variants
Floating origin rebasing
graphics · low: Shift the world origin near the camera to keep float precision in huge worlds
io_uring
networking · low: Linux async I/O through two shared-memory rings (submissions in, completions out), batching or eliminating syscalls for sockets and files alike.
›
Spatial hashing
physics · low: Uniform grid stored in a hash table: bucket objects by cell, test only neighbouring cells; O(n) neighbour search for many similar-sized objects such as particles.
›
Buddy allocator
systems · low: Power-of-two block splitting and coalescing; base of kernel page and GPU heap allocators
Epoch-based reclamation
concurrency · low: Threads announce a global epoch while touching shared lock-free data; garbage retired in epoch e is freed once the epoch reaches e + 2.
›
Memory ordering
concurrency · low: What Relaxed, Acquire, Release and SeqCst atomics actually guarantee, what they cost on x86 and ARM, and which one each pattern needs.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
Buffer pools for zero-allocation I/O
hardware-os · low: Preallocate a fixed set of aligned I/O buffers and recycle them through a free list, so the hot path never mallocs, faults or unmaps. The bounded count doubles as back pressure.
›
Homogeneous transforms
geometry · low: 4x4 affine and projective matrices, homogeneous coordinates, view and projection, normal matrices
Image pyramids
graphics · low: Gaussian/Laplacian pyramids and tiled multi-resolution images for zoom and blending
GPU compute shaders
ml-training · low: The vendor-neutral GPU launch model of Metal, Vulkan and WebGPU: a grid of workgroups, shared memory, barriers and subgroups, driven by recorded command buffers.
›
Bounding volume hierarchy
physics · low: Binary tree of nested bounding boxes; prunes overlap and ray queries to O(log n) for any size distribution, and supports cheap insert/remove for moving objects.
›
Deflate
compression · low: DEFLATE/gzip: LZ77 + Huffman, the format behind HTTP gzip, zip and PNG
DMA and IOMMU
hardware-os · low: How devices move data by direct memory access, and how an IOMMU gives each device its own address space, faults on stray accesses and lets user space or guests own a device safely.
›
Nvme queues
hardware-os · low: NVMe submission and completion queue pairs, doorbells and polling from a driver
Half edge mesh
graphics · low: Half-edge mesh connectivity for editable polygon meshes
LU and Cholesky factorization
numerics · low: Factor A = PLU (any square matrix, partial pivoting) or A = LLᵀ (SPD) once in O(n³), then solve each right-hand side in O(n²).
›
Mipmapping texture filtering
graphics · low: Mip pyramids, trilinear and anisotropic filtering, LOD selection from derivatives
Texture tiling swizzling
graphics · low: Tiled and swizzled GPU image layouts and address computation
GPU command buffers
graphics · low: Record GPU work as a flat list of commands on the CPU, submit it in batches, and reuse its memory through a ring of frames in flight guarded by fences.
›
Parallel prefix sum
search-sort · low: Work-efficient scan (Blelloch, decoupled look-back) on CPU SIMD and GPUs; stream compaction
PRNGs (PCG, xoshiro)
numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.
›
Sparse matrices (CSR)
numerics · low: Compressed sparse row stores only nonzeros as row pointers, column indices and values; SpMV streams them once, so it is memory-bandwidth bound.
›
Fast hash functions
data-structures · low: Non-cryptographic hashes built from 64×64→128-bit multiplies and xor-shifts; pick by key size, trust level and whether the hash is persisted.
›
Gpu synchronization fences
graphics · low: Fences, timeline semaphores and sync files between GPU queues, CPU and processes
fsync, O_DSYNC and O_DIRECT
hardware-os · low: What fsync, fdatasync, O_DSYNC, O_DIRECT and F_FULLFSYNC really guarantee on Linux and macOS, and the exact call sequences for crash-safe files.
›
Copy for AI
Similar systems
Share the most building blocks with this one.
voxel-engine
15 %