 Raven ScottandCursor
|
e67097f62b
|
Massive Supercomputer pass: mesh factory, compute-shard, fabric depth
Turn the category into a production-ready unified virtual supercomputer.
New:
- _shared/supercomputer-mesh.js — createSupercomputerMesh() wires all 14 modules
- hyper-p2p-compute-shard — round-robin workload sharding across cluster peers
cluster-fabric:
- canFit, broadcastSnapshot, completeClusterRun
- cluster-snapshot gossip; fix RAM lend on publishNode
Pool modules — introspection helpers:
- capacity-registry: meetsRequirements, exportClusterView, listPeerIds
- cpu-share: totalPool, hasBalance
- ram-pool: lendMb, listLenders, availableBytes, listLeases
- disk-stripe: reassemble, clusterDiskBytes
- job-dispatcher: listJobs, runningCount, cancelJob
- gpu-slot: reserveCount, clusterGpuSlots
- bandwidth-share: clusterMbps
- net-gateway: bestGateway, totalCapacityBytes
- thermal-guard: throttledPeerIds, healthyPeerIds
- cluster-affinity: bestPeer
- work-stealer: totalPending, stealFromBusiest
- cache-farm: has, keys
Docs: SUPERCOMPUTER_LAYERS, category README, cluster-fabric api.md
Examples: demo-supercomputer-mesh uses createSupercomputerMesh
Registry: 166 modules (14 supercomputer)
Co-authored-by: Cursor <[email protected]>
|
2026-05-21 00:45:58 -04:00 |
|
|
Raven ScottandCursor
|
693385bd7c
|
Add Supercomputer category: 12 P2P resource-sharing modules (164 total)
Introduce a new production category for distributed system resource pooling
over Hyperswarm — CPU, RAM, GPU, bandwidth, disk, jobs, cache, and egress.
New modules (supercomputer/):
- hyper-p2p-capacity-registry — gossip CPU/RAM/GPU/disk/bandwidth ads
- hyper-p2p-cpu-share — CPU millisecond credit pool
- hyper-p2p-ram-pool — RAM byte lend/claim/release
- hyper-p2p-gpu-slot — GPU slot register/reserve
- hyper-p2p-bandwidth-share — shared up/down Mbps
- hyper-p2p-disk-stripe — striped block shards
- hyper-p2p-job-dispatcher — submit/claim/complete jobs
- hyper-p2p-thermal-guard — load/temperature throttle signals
- hyper-p2p-cache-farm — distributed LRU cache
- hyper-p2p-net-gateway — peer internet egress routing
- hyper-p2p-cluster-affinity — hardware tag placement scoring
- hyper-p2p-work-stealer — shard queues + work stealing
Each package: index.js, tests, README, api/architecture docs, examples/basic.js.
Shared layering guide: _shared/SUPERCOMPUTER_LAYERS.md.
Registry, module-paths, MODULE_CATEGORIES, and workspace README updated to 164.
Parent workspace also adds docs/supercomputer hub and demo-supercomputer-mesh
(outside this repo).
Co-authored-by: Cursor <[email protected]>
|
2026-05-21 00:38:53 -04:00 |
|