- Converted header metadata to YAML frontmatter format
- Added categories and tags for documentation site compatibility
- Preserved all existing content (only header format changed)
- Status: IMPLEMENTED, Phase: Phase 1B
- Links to benchmark: element_immutability_benchmark.jl
Implements compatibility layer to allow old test code to run with new
immutable element design (though fields won't actually update).
src/elements/elements.jl:
- Replaced has_dfield/get_dfield to work with new fields API
- Fixed get_sfield/get_dfield to handle empty Tuple{} fields
- All dfield functions now map to element.fields (immutable NamedTuple)
src/topology/*.jl (seg2, tri3, quad4, tet4, hex8):
- Added nnodes() implementation for each topology type
- Returns corner node count (backwards compatibility)
- Example: nnodes(::Triangle) = 3, nnodes(::Hexahedron) = 8
- Note: Actual node count depends on basis degree in new architecture
Test Results:
- test_topology_standalone.jl: 36/36 tests passing ✓
- Full test suite: 43 errors (same as before)
- Error breakdown:
* 40+ tests: Problem types not defined (Elasticity, Heat, Mortar)
* 2 tests: Mesh readers not defined (aster_read_mesh)
* 1 test: Tries to mutate empty element (test_elasticity_1d)
Next Steps:
- Tests that create empty elements then mutate need rewriting
- Pattern: Element(Seg2, (1,2)) + update!() → not compatible
- New pattern: Element(..., fields=(geometry=X, displacement=u))
- See docs/design/IMMUTABILITY.md for migration guide
Created comprehensive documentation and benchmark demonstrating why immutable
elements with type-stable fields are 40-130x faster than mutable Dict-based
elements.
benchmarks/element_immutability_benchmark.jl:
- Compares mutable (Dict) vs immutable (NamedTuple) implementations
- Measures field access, updates, assembly loops, large-scale meshes
- Results: 40x faster field access, 130x faster assembly, zero allocations
docs/design/IMMUTABILITY.md:
- Explains counterintuitive API change: element = update(element, ...)
- Benchmarks show 40-130x speedup despite 'copying' elements
- Key insight: Type stability >> mutation, compiler optimizes away copies
- Migration guide: old mutable API → new immutable API
- GPU/HPC rationale: Only bits types work on GPU (no pointers)
Key Results:
- Field access: 1ns vs 45ns (40x faster)
- Assembly: 9ns vs 1124ns per element (130x faster)
- Large mesh: 0.01ms vs 1.2ms for 1000 elements (120x faster)
- Memory: 0 allocations vs 70,000 allocations
- GPU: Compatible (bits types) vs Incompatible (pointers)
This documents a fundamental architectural decision for JuliaFEM 1.0.
Jukka Aho