Jorijn van der Graaf
0c55e76873
NEON backend for VectorF32 on AArch64: one float32x4_t per vector (Len * Packing <= 4), with a vectorised sin/cos port of the SSE helpers. VectorF16 gets a native float16x8_t path when the target has ARMv8.2-FP16 arithmetic. Without it VectorF16 aliases VectorF32, which converts fp16 <-> fp32 on Load/Store. The scalar fallback gains the batched Dot that MatrixRowMajor relies on. Test tiers added for armv8-a and armv8.2-a+fp16. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
75 lines
4.6 KiB
Markdown
75 lines
4.6 KiB
Markdown
# Crafter.Math
|
||
|
||
A C++23 math library for the Crafter engine, distributed as a set of C++ modules. Provides generic vector and matrix types alongside SIMD-specialized fixed-size vectors for `float` and `_Float16`, plus a small set of ray intersection routines.
|
||
|
||
The library is hardware-aware: it picks the widest SIMD path the target supports (SSE / AVX / AVX-512 on x86_64, NEON on AArch64, RVV on RISC-V, SIMD128 on WebAssembly) and falls back to scalar code elsewhere.
|
||
|
||
## Modules
|
||
|
||
`import Crafter.Math;` re-exports the following partitions:
|
||
|
||
| Partition | Contents |
|
||
| --- | --- |
|
||
| `:Basic` | `ToRadian`, plus the `VectorF16 → VectorF32` alias on x86_64 without AVX512-FP16 and on AArch64 without ARMv8.2-FP16. |
|
||
| `:Vector` | Generic `Vector<T, Len, Alignment>` with `.x/.y/.z/.w` and `.r/.g/.b/.a` accessors, arithmetic, comparison, and conversion operators. |
|
||
| `:MatrixRowMajor` | `MatrixRowMajor<T, ColumnSize, RowSize, Repeats>` — row-major matrices with packed-batch support via `Repeats`. |
|
||
| `:VectorF32` | `VectorF32<Len, Packing>` — SIMD-specialized 32-bit float vector with `Load`/`Store`, FMA, `Cross`, `Dot`, `Length`, `Normalize`, `Sin`/`Cos`, `Shuffle`, etc. |
|
||
| `:VectorF16` | `VectorF16<Len, Packing>` — same surface as `VectorF32` for `_Float16` when the target supports it. |
|
||
| `:Intersection` | `IntersectionTestRayTriangle`, `IntersectionTestRaySphere`, `IntersectionTestRayOrientedBox`. |
|
||
| `:Common` | Internal SIMD type selection (`__m128/256/512`, `__m128h/256h/512h`, `float32x4_t`, `float16x8_t`, `v128_t`, or scalar array) used by the F16/F32 vectors. |
|
||
|
||
`Len` is the logical vector width (1–4 for most graphics use) and `Packing` is the number of vectors packed into one SIMD register — e.g. `VectorF32<3, 4>` holds four 3-vectors in a single 512-bit register, which is what the batched `Dot`, `Length`, and `Normalize` overloads operate on.
|
||
|
||
## Example
|
||
|
||
```cpp
|
||
import Crafter.Math;
|
||
using namespace Crafter;
|
||
|
||
// Generic 3-vector of floats.
|
||
Vector<float, 3> a(1.0f, 2.0f, 3.0f);
|
||
Vector<float, 3> b(4.0f, 5.0f, 6.0f);
|
||
auto c = a + b;
|
||
|
||
// SIMD-specialized 4-vector with one element of padding.
|
||
VectorF32<4, 1> p(1.0f);
|
||
VectorF32<4, 1> q(2.0f);
|
||
auto r = VectorF32<3, 1>::Cross(p, q);
|
||
|
||
// Ray vs. triangle.
|
||
float t = IntersectionTestRayTriangle<float>(
|
||
{0,0,0}, {1,0,0}, {0,1,0},
|
||
{0.25f, 0.25f, -1.0f}, {0, 0, 1});
|
||
```
|
||
|
||
## Building
|
||
|
||
This project uses [Crafter.Build](https://forgejo.catcrafts.net/Catcrafts/Crafter.Build). The build script in [project.cpp](project.cpp) declares the library as a static C++ module library and registers three test executables targeting different ISAs:
|
||
|
||
- `Vector-sapphirerapids` — AVX-512 with FP16 (`-march=sapphirerapids`)
|
||
- `Vector-x86-64-v4` — AVX-512 baseline
|
||
- `Vector-x86-64-v3` — AVX2 baseline
|
||
- `Vector-rv64gcv_zvl512b` — RVV with VLEN≥512 (uses the 64-byte tier)
|
||
- `Vector-rv64gcv_zvl256b` — RVV with VLEN≥256 (32-byte tier)
|
||
- `Vector-rv64gcv` — RVA23 baseline ZVL128B (16-byte tier)
|
||
- `Vector-armv8.2-a+fp16` — AArch64 NEON with ARMv8.2-FP16 (native `VectorF16`)
|
||
- `Vector-armv8-a` — AArch64 baseline NEON
|
||
|
||
Build and run tests via your usual Crafter.Build entry point; `build/` and `bin/` are git-ignored.
|
||
|
||
## Target support
|
||
|
||
- **x86_64**: SSE / AVX / AVX-512F selected per target; AVX512-FP16 is required for native `VectorF16` (otherwise it aliases `VectorF32`). F16C is used for fp16 ↔ fp32 conversion when available.
|
||
- **RISC-V**: RVV 1.0 (the `V` extension, ratified Nov 2021, mandatory in the RVA23 profile). Storage is a 16/32/64-byte GNU vector picked at compile time from the guaranteed VLEN (`__riscv_v_fixed_vlen` from Clang's `-mrvv-vector-bits=`, else `__riscv_v_min_vlen` from the march's `Zvl*` suffix, else the ZVL128B baseline). `VectorF16` aliases `VectorF32` until a `Zvfh` path lands.
|
||
- **AArch64**: NEON (`arm_neon.h`) 128-bit path; SIMD width is capped at 16 bytes, so a vector holds at most 4 floats or 8 halves. `VectorF32` only needs the ARMv8-A baseline. ARMv8.2-FP16 (`-march=armv8.2-a+fp16`, or any `-march`/`-mcpu` that implies it) is required for native `VectorF16`; otherwise it aliases `VectorF32`, which converts fp16 ↔ fp32 on `Load`/`Store`. 32-bit ARM takes the scalar fallback.
|
||
- **WebAssembly**: `wasm_simd128.h` 128-bit path; SIMD width is capped at 16 bytes.
|
||
- **Other targets**: scalar fallback via `std::array<T, N>`.
|
||
|
||
## License
|
||
|
||
This library is licensed under the GNU Lesser General Public License, version 3 only (LGPL-3.0-only). See [LICENSE](LICENSE) for the license text. The LGPL supplements the GNU General Public License version 3, a copy of which is included as [LICENSE.GPL](LICENSE.GPL).
|
||
|
||
## Copyright
|
||
|
||
Copyright (C) 2026 Catcrafts®
|
||
catcrafts.net
|