VR2-0277

① SA Source

Context Before

Source: Nvidia VR NVL72 BoM and Power Budget Model ↗

Firstly, the connection between the GPU and the ConnectX NICs evolved from GB200 to GB300 then to Vera Rubin. For GB200, the GPU does not have direct access to the ConnectX-7. Instead, B200 connects to Grace CPU via C2C connection then the Grace CPU talks to the ConnectX-7 over PCIe 5. For GB300, Nvidia introduced NIC direct to ConnectX-8, which allows the B300 GPU to communicate directly with the ConnectX-8 NIC without going through the Grace CPU.

Evidence

Essentially, this means ConnectX-8 has two hosts, Grace CPU and B300 GPU

Context After

Secondly, the local NVMe storage for Rubin has been moved to a different location from that of NVMe storage in Grace Blackwell. Previously, local NVMe storage was managed by BlueField-3. For VR NVL72, the local NVMe storage is physically on the Orchid module managed by the ConnectX-9.

image

② Atomic Claim

ConnectX-8 的另一個 host 是 B300 GPU。

  • Epistemic Mode: ASSERTED
  • Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/ConnectX-8",
        "label": "ConnectX-8"
      },
      "role": "endpoint_or_system"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA B300",
        "label": "B300"
      },
      "role": "connected_entity"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "connected_entity"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "8"
    ],
    "temporal_mentions": []
  },
  "relation_type": "CONNECTS_TO"
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
endpoint_or_systemConnectX-8ConnectX-8
connected_entityB30004_knowledge_base/NVIDIA B300
connected_entityGPUGPU

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。