{
  "slug": "mind",
  "term": "MIND",
  "aliases": [
    "MMU In-Network for Disaggregated architectures"
  ],
  "definition": "MIND is a research memory-disaggregation system that places address translation, protection and cache-coherence management in a programmable network switch.",
  "note": "Placement: MIND moves allocation policy to a switch CPU and address translation, protection and coherence metadata to its programmable data plane. Compute blades retain local DRAM; misses trigger page faults and RDMA requests. It is a shared-memory research system, not an SSD interface. [project]\n\nCoherence trade-off: An MSI directory tracks regions that can contain multiple pages. A write can invalidate an unrelated page in the same region: false invalidation trades network work against directory capacity. [paper]\n\nBounded splitting: A region's false-invalidation count above a threshold within an epoch splits a region in half, down to 4 KB pages. The analysis assumes stable access patterns and allocated pages over O(log2 M) epochs, with M measured in pages. This is not an unconditional bound for arbitrary changing workloads. [paper]\n\nEvaluation scope: Five physical servers emulate memory and compute blades with 100 Gbit/s connections. Fastswap and adapted GAM are comparison systems. Read-write contention and finite switch directory capacity limit scaling; the design targets one rack and one switch. [paper]\n\nFailure boundary: The paper discusses switch-state recovery and retransmitted invalidations, but does not introduce CPU/memory-blade fault tolerance. Inference: cache coherence is not a promise of crash-durable storage. [paper]\n\nArtifact limits: The pinned instructions require suitable programmable-switch and RDMA hardware, an NDA for switch programs and agreement to the RDMA driver's license terms. Trace-based experiments and PSO/PSO+ estimates are separate evidence; shortened traces need not reproduce the paper's exact values. [artifact]",
  "status": "research",
  "advantages": [],
  "limitations": [],
  "related": [
    "fastswap",
    "infiniswap",
    "legoos"
  ],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-11-15",
  "citations": [
    {
      "id": "paper",
      "title": "Lee et al. MIND. SOSP 2021, pp. 488-504; sections 4.3-5, 7-8. DOI: 10.1145/3477132.3483561.",
      "url": "https://www.anuragkhandelwal.com/papers/mind.pdf",
      "accessed": "2026-11-15"
    },
    {
      "id": "project",
      "title": "MIND authors: control-plane, data-plane and local-DRAM architecture",
      "url": "https://yale-nova.github.io/mind/",
      "accessed": "2026-11-15"
    },
    {
      "id": "artifact",
      "title": "MIND authors: artifact evaluation, hardware, licensing prerequisites and simulation scope; pinned revision",
      "url": "https://github.com/yale-nova/mind/blob/5b27121a4e5bb2db64886429e84484a3d9a0a13e/artifacts/readme.md",
      "accessed": "2026-11-15"
    },
    {
      "id": "dependencies",
      "title": "MIND authors: tested switch software dependencies; pinned revision",
      "url": "https://github.com/yale-nova/mind/blob/5b27121a4e5bb2db64886429e84484a3d9a0a13e/mind_switch_ctrl/dependencies.md",
      "accessed": "2026-11-15"
    }
  ],
  "provenance": [
    "Primary-source synthesis and pinned artifact inspection, not a native MIND run, switch benchmark or failure-recovery experiment.",
    "Coherence and durability answer different questions. The storage-durability distinction is an inference, not a reported MIND crash test.",
    "The pinned guide tested Barefoot SDE 9.2 with grpc and thrift; it requires an Intel NDA and Mellanox OFED terms. These are historical prerequisites, not a current support contract. [dependencies] [artifact]"
  ]
}
