metal gpu
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
metal gpu has 29 facts recorded in Dontopedia across 16 references, with 2 live disagreements.
Mostly:rdf:type(6), enabled on(1), references apple metal api(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (43)
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.
usesBackendUses Backend(2)
- Grid Size 128 Squared
ex:grid-size-128-squared - Grid Size 256 Squared
ex:grid-size-256-squared
usesComputeFrameworkUses Compute Framework(2)
- Metal Gpu 1m Peak
ex:metal-gpu-1m-peak - Metal Gpu 256k
ex:metal-gpu-256k
usesF64VsF32Uses F64 Vs F32(2)
- 1024 Squared Rotor32 Parallel
ex:1024-squared-rotor32-parallel - 512 Squared Rotor32 Parallel
ex:512-squared-rotor32-parallel
buildFeatureBuild Feature(1)
- Software Push 1
ex:software-push-1
competitiveWithGpuLargeScaleCompetitive With Gpu Large Scale(1)
- Cpu
ex:cpu
enablesTrainingEnables Training(1)
- Candle Autograd
ex:candle-autograd
evaluatedAsBorderlineEvaluated As Borderline(1)
- Grid Size 256 Squared
ex:grid-size-256-squared
executedOnExecuted on(1)
- Full Training Run
ex:full-training-run
fasterThanFaster Than(1)
- Cpu Rotor32 Parallel Path
ex:cpu-rotor32-parallel-path
featureGatesMetalFeature Gates Metal(1)
- Freshly Landed Commit
ex:freshly-landed-commit
featuresFeatures(1)
- Macos Platform
ex:macos-platform
handledByHandled by(1)
- One Hundred Million Points Simulation
ex:one-hundred-million-points-simulation
hardDependsOnHard Depends on(1)
- Symbiogenesis Feature
ex:symbiogenesis-feature
hasBestPathHas Best Path(1)
- Grid Le 256 Squared
ex:grid-le-256-squared
higherPrecisionThanHigher Precision Than(1)
- Cpu Rotor32 Parallel Path
ex:cpu-rotor32-parallel-path
historicalAlternativeToMetalHistorical Alternative to Metal(1)
- Cuda
ex:cuda
implementsImplements(1)
- Commit 3
ex:commit-3
implicatesDependencyIssueImplicates Dependency Issue(1)
- Symbiogenesis Feature
ex:symbiogenesis-feature
implicatureNoBenefitImplicature No Benefit(1)
- Gpu
ex:gpu
improvesPerformanceImproves Performance(1)
- Push 2026 04 04
ex:push-2026-04-04
includesFeatureIncludes Feature(1)
- Push 2026 04 04
ex:push-2026-04-04
initializedGpuInitialized Gpu(1)
- Hardware Event 1
ex:hardware-event-1
isFasterThanIs Faster Than(1)
- Cpu Rotor32
ex:cpu-rotor32
optimizedByOptimized by(1)
- Sgemm
ex:sgemm
preferredOverMetalPreferred Over Metal(1)
- Cuda Specific Wins
ex:cuda-specific-wins
prioritizesPrioritizes(1)
- Macos Default
ex:macos-default
processesTilesOnProcesses Tiles on(1)
- Tiled Mode
ex:tiled-mode
runsOnMetalGpuRuns on Metal Gpu(1)
- Compute Kernels
ex:compute-kernels
scalesBetterThanGpuForLargeGridsScales Better Than Gpu for Large Grids(1)
- Rotor32 Parallel
ex:rotor32-parallel
successorToMetalGpuSuccessor to Metal Gpu(1)
- Cuda Gpu
ex:cuda-gpu
superiorInPrecisionSuperior in Precision(1)
- Cpu Rotor32
ex:cpu-rotor32
superiorInSpeedSuperior in Speed(1)
- Cpu Rotor32
ex:cpu-rotor32
supportsGpuAccelerationSupports Gpu Acceleration(1)
- Fedsym Project
ex:fedsym-project
targetPlatformTarget Platform(1)
- Metal Gpu Kernel Correctness
ex:metal-gpu-kernel-correctness
targetsPlatformTargets Platform(1)
- Metal Gpu Kernels
ex:metal-gpu-kernels
usesGpuUses Gpu(1)
- Training
ex:training
usesGpuAccelerationUses Gpu Acceleration(1)
- First Training Run
ex:first-training-run
usesGpuFrameworkUses Gpu Framework(1)
- Harmonic Rust
ex:harmonic-rust
usesMetalGpuUses Metal Gpu(1)
- Dense Commutator Table
ex:dense-commutator-table
usesTechnologyUses Technology(1)
- Dense Commutator Table Setup
ex:dense-commutator-table-setup
Other facts (24)
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 | Hardware | [10] |
| Rdf:type | Hardware Platform | [11] |
| Rdf:type | Hardware Platform | [12] |
| Rdf:type | Platform | [13] |
| Rdf:type | Hardware | [14] |
| Rdf:type | Hardware Interface | [15] |
| Enabled on | Device Metal Deviceid 1 | [1] |
| References Apple Metal Api | true | [2] |
| Gated by Cfg Feature | Cfg Feature Metal Gpu | [3] |
| Handles10m in | ~5s | [4] |
| Is Apple Hardware | null | [4] |
| Adds No Value | Cl 6 0 Metropolis Experiments | [5] |
| Apple Framework | Gpu Compute | [5] |
| Criticized As Useless | Xenonfun | [5] |
| Duration For512x512 | 8.6s | [5] |
| Gpu Optimized | null | [6] |
| Suitable for Small Grids | Grid Le 256 Squared | [6] |
| Does Not Bridge Gap | True | [7] |
| Initialized | Apple M3 Ultra | [8] |
| Enabled on Device | Metal Device Deviceid 1 | [9] |
| :targets Use Case | Larger Models | [11] |
| Processes Tile Size | Tile Size 10m | [14] |
| Processing Time for Tile | ~5s | [14] |
| Fails to Bridge Gap | Calculation 1 | [16] |
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 (16)
ctx:discord/blah/random/part-26ctx:discord/blah/watt-activation/part-529ctx:discord/blah/watt-activation/part-536ctx:discord/blah/watt-activation/part-565ctx:discord/blah/watt-activation/part-601ctx:discord/blah/watt-activation/part-602ctx:discord/blah/watt-activation/part-657ctx:discord/blah/watt-activation/part-676ctx:discord/blah/random/part-24ctx:discord/blah/random/27- full textrandom-27text/plain2 KB
doc:agent/random-27/e650c997-da27-4878-ba9f-a405e95b956aShow excerpt
[2026-02-17 18:23] xenonfun: yeah is with bpe, 7.5M model, with ~40MB of data on that (Gutenburg free library) I am going to do full training that should be enouge sample data now: ``` It's running! 55.7M tokens — so 1 epoch = 50.1M / 4096…
ctx:discord/blah/watt-activation/454- full textwatt-activation-454text/plain3 KB
doc:agent/watt-activation-454/4f6603bc-7db5-4694-932b-2c38bbe4bc5bShow excerpt
[2026-03-21 06:17] xenonfun: Back to Rust ``` 1 - [project_vision.md](project_vision.md) — HarmonicRust replaces Python HarmonicMLX + Phase Hub with Rust 2 - [user_profile.md](user_profile.md) — User builds novel manifold-based ML architect…
ctx:discord/blah/watt-activation/458- full textwatt-activation-458text/plain2 KB
doc:agent/watt-activation-458/de149b38-35c3-463f-b547-cd05f36c46d2Show excerpt
[2026-03-21 14:35] xenonfun: --- ## NEEDS TESTING (builds, untested) - [ ] LoheSphericalComplexAttention (lohe_complex.rs) - [ ] LoheSphericalComplexSplitAttention (lohe_complex_split.rs) - [ ] QuaternionEncoder (quaternion_enc.rs) - [ ] …
ctx:discord/blah/watt-activation/462- full textwatt-activation-462text/plain3 KB
doc:agent/watt-activation-462/febf8ec9-a379-45c7-a43f-2ebdaf74b41fShow excerpt
[2026-03-21 17:58] xenonfun: ``` ⏺ Pushed. Here's the full status across 3 commits today: Commit 1 — Core FedSym port (8,069 lines, 106 tests) Commit 2 — MNIST, rayon parallel, ManifoldUnit forward (1,157 lines, 14 new tests) Commit …
ctx:discord/blah/watt-activation/562- full textwatt-activation-562text/plain2 KB
doc:agent/watt-activation-562/97a8c793-55ed-43da-8e79-b25f63134bfaShow excerpt
[2026-03-23 16:02] xenonfun: ``` ⏺ Great results so far. Here's what we know: Magnetar simulation scaling: ┌───────────┬──────┬──────────────┬─────────────┬────────────────┐ │ Grid size │ Time │ Energy drift │ Order param │ Regime…
ctx:discord/blah/watt-activation/599ctx:discord/blah/watt-activation/654- full textwatt-activation-654text/plain3 KB
doc:agent/watt-activation-654/64b35524-e5cb-4a0b-b1df-4ce474f68552Show excerpt
[2026-04-18 07:57] xenonfun: ``` Standalone signing — this is a much better story NA-PDE-Sig Cl(5,0) grade-even is structurally different from the DH leg: - Different hardness assumption. Non-abelian conjugacy in Cl⁺(5,0) ≅ M₄(F_p) — …
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.