compute.rs
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
compute.rs has 22 facts recorded in Dontopedia across 6 references, with 2 live disagreements.
Mostly:rdf:type(5), implements cascade(2), gated by cfg in lib rs(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
enablesFallbackLogicEnables Fallback Logic(1)
- Gpu Backend Trait
ex:gpu-backend-trait
Other facts (20)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Source File | [3] |
| Rdf:type | Module | [4] |
| Rdf:type | Rust Source File | [5] |
| Rdf:type | Source Code Component | [5] |
| Rdf:type | Rust File | [6] |
| Implements Cascade | CUDA → Metal → CPU | [2] |
| Implements Cascade | Cuda Metal Cpu Cascade | [5] |
| Gated by Cfg in Lib Rs | Cfg Feature Metal Gpu | [1] |
| Picks Available Backend | Gpu Backend Trait | [1] |
| Wires Dispatch | All 8 dispatch functions | [2] |
| Has Accessor Alongside | gpu() for Metal | [2] |
| Has Singleton Accessor | cuda_gpu() | [2] |
| Selects Implementation | Available Backend | [3] |
| Dispatch Layer Ready for | Cuda Gpu Tier | [4] |
| Requires Configuration | #[cfg(feature = "cuda-gpu")] blocks | [4] |
| Has Existing Configuration | Metal ones | [4] |
| Defines Dispatch Count | 8 | [5] |
| Defines Accessor | Cuda Gpu Singleton | [5] |
| Part of Crate | Commutator Wasm | [6] |
| Implements Engine | Wgpu Engine | [6] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (6)
ctx:discord/blah/watt-activation/part-536ctx:discord/blah/watt-activation/part-544ctx:discord/blah/watt-activation/533- full textwatt-activation-533text/plain2 KB
doc:agent/watt-activation-533/f21f35b9-c68c-4b42-b156-d3af09550b6bShow excerpt
[2026-03-23 03:33] xenonfun: ● Here's the first-draft plan. Key highlights: ``` x86 SIMD (AVX2/AVX-512): - Biggest win: hand-unrolled commutator (24 nonzero FMAs, no branches) and fused Strang step (eliminates 3 separate passes + allo…
ctx:discord/blah/watt-activation/537- full textwatt-activation-537text/plain2 KB
doc:agent/watt-activation-537/015e1e22-a4c4-42d8-8c4b-c7d284b56ed8Show excerpt
[2026-03-23 04:09] xenonfun: ``` Tier: CPU scalar Coverage: Everything Status: Always available, all 671 tests pass ──────────────────────────────────────── Tier: CPU SIMD (x86 AVX2+FMA) Coverage: Bivector commutator + fused 1D S…
ctx:discord/blah/watt-activation/541- full textwatt-activation-541text/plain3 KB
doc:agent/watt-activation-541/86a1c23a-21e8-4b26-b4fa-83b3736cd902Show excerpt
[2026-03-23 04:48] xenonfun: ``` ● Here's what's now in place for CUDA: Kernel sources (3 files, ready for NVRTC runtime compilation): - cuda_kernels/compute.cu — 8 kernels: matmul, gated_cumsum, lohe_normalize, softmax, elementwise_ad…
ctx:discord/blah/watt-activation/580- full textwatt-activation-580text/plain2 KB
doc:agent/watt-activation-580/3af256af-1397-4d5a-a250-bbc6be8776feShow excerpt
[2026-03-29 03:45] xenonfun: ``` ● PR created: https://github.com/rsafier/HarmonicRust/pull/6 Here's what the prototype demonstrates: The core proof-of-concept: A single Rust crate (commutator-wasm) that compiles the same WGSL shaders…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.