NIEK2-0231

① SA Source

  • Source: 開啟完整 SA 文章
  • Section: Oberon and Kyber Updates, Larger World Sizes Introduced, More Networking Updates
  • Line hint: 283

Context Before

image

Kyber midplane PCB (GPU side). Source: Nvidia, SemiAnalysis

Evidence

Scale-up CPO will first be used for the Rubin Ultra NVL 576 system to connect between 8 Oberon form factor racks, forming a two-layer all-to-all network

Context After

Moving back to the Kyber Rack, each Rubin Ultra logical GPU offers 14.4Tbit/s uni-di of scale-up bandwidth, using an 80DP connector (72 DPs used x 200Gbit/s bi-di channel = 14.4Tbit/s) per GPU for connectivity to the midplane board. Connecting all 144 GPUs in an all-to-all network will require 72 NVLink 7.0 Switch Chips running at 28.8Tbit/s uni-di of aggregate bandwidth each.

image

② Atomic Claim

Scale-up CPO 首先會用在 Rubin Ultra NVL576,連接 8 個 Oberon form factor racks,形成兩層 all-to-all network。

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/CPO",
        "label": "CPO"
      },
      "role": "endpoint_or_system"
    },
    {
      "node": {
        "id": "04_knowledge_base/Rubin Ultra",
        "label": "Rubin Ultra"
      },
      "role": "connected_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA Oberon",
        "label": "Oberon form factor"
      },
      "role": "connected_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVL576",
        "label": "NVL576"
      },
      "role": "context_entity"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "8"
    ],
    "temporal_mentions": []
  },
  "relation_type": "CONNECTS_TO"
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
endpoint_or_systemCPOCPO
connected_entityRubin Ultra04_knowledge_base/Rubin Ultra
connected_entityOberon form factor04_knowledge_base/NVIDIA Oberon
context_entityNVL576NVL576

⑤ Human Review

請在 Properties 逐項確認:

  • 原文 → Atomic Claim 是否忠實
  • Atomic Claim → Semantic Frame 是否忠實
  • Canonical Entity mapping 是否正確
  • Epistemic mode 是否保留原文語氣
  • 最後選擇 review_action

Review state

Markdown 內文不是正式 approval。只有 Apply bridge 寫入的 Decision Ledger event 才是正式決策。