Metal kernel
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Metal kernel has 10 facts recorded in Dontopedia across 6 references, with 1 live disagreement.
Mostly:is fused update plus readout(2), references apple metal framework(1), has python einsum fallback(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (8)
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.
comparedSuperiorToCompared Superior to(1)
- Cuda
ex:cuda
essentiallyEquivalentToEssentially Equivalent to(1)
- Wgsl Shader
ex:wgsl-shader
isDirectTranslationOfIs Direct Translation of(1)
- Wgsl Shader
ex:wgsl-shader
referencesLoheSyncPrototypeReferences Lohe Sync Prototype(1)
- Benchmarks
ex:benchmarks
superiorInGridSupportSuperior in Grid Support(1)
- Cuda
ex:cuda
translationSourceTranslation Source(1)
- Wgsl Shader
ex:wgsl-shader
usesMetalKernelsUses Metal Kernels(1)
- Gpu Decode Pipeline
ex:gpu-decode-pipeline
willBuildWill Build(1)
- Xenonfun
ex:xenonfun
Other facts (9)
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 |
|---|---|---|
| Is Fused Update Plus Readout | Python Einsum Fallback | [1] |
| Is Fused Update Plus Readout | Metal Kernel Fused Update Readout | [1] |
| References Apple Metal Framework | Gpu Compute | [1] |
| Has Python Einsum Fallback | Python Einsum Fallback | [1] |
| Implements Fused Strang Step | {} | [2] |
| Is1d Only | 1d Only | [3] |
| Contextualized As Native Baseline | Apple Metal | [4] |
| Implements | Eb Cross Term Table | [5] |
| Rdf:type | Software Component | [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-77ctx:discord/blah/watt-activation/part-528ctx:discord/blah/watt-activation/part-536ctx:discord/blah/watt-activation/part-550ctx:discord/blah/watt-activation/525- full textwatt-activation-525text/plain3 KB
doc:agent/watt-activation-525/133fb518-fad6-4e16-a093-f95c1d94dda4Show excerpt
[2026-03-23 01:57] xenonfun: ⏺ 16.7 million grid points, 384 MB, 104M point-updates/s, 13.1 GFLOP/s. That's 10x the original single-core throughput at scale. Rayon is fully saturating all M4 performance cores. The scaling curve shows we'…
ctx:discord/blah/watt-activation/547- full textwatt-activation-547text/plain2 KB
doc:agent/watt-activation-547/5df4b8d4-896d-4a30-bbd9-886176abaf0cShow excerpt
[2026-03-23 06:10] xenonfun: ⏺ Yes — the current design handles that naturally: Joining: A worker registers at any time via POST /api/resonate/register, gets an immediate assignment if there's work available, and starts computing. Mid-…
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.