VR2R-0262_r1

VR2R-0262

① SA Source

• Source: 開啟完整 SA 文章
• Section: Compute Tray Topology
• Line hint: 230

Context Before

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

This improves latency in the backend network. However, for VR NVL72, the direct connection between Rubin GPU and ConnectX-9 is reverted back to the same design as GB200, as Rubin does not have PCIe bandwidth for two ConnectX-9. Rubin connects to Vera via C2C link, then Vera will connect to ConnectX-9 via PCIe6 lanes.

② Atomic Claim

這代表 ConnectX-8 有兩個 hosts：Grace CPU 與 B300 GPU。

• Epistemic Mode: INFERRED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/ConnectX-8",
        "label": "ConnectX-8"
      },
      "role": "network_device"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA Grace",
        "label": "Grace CPU"
      },
      "role": "host"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA B300",
        "label": "B300"
      },
      "role": "host"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "host_type"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "two"
    ],
    "temporal_mentions": []
  },
  "relation_type": "CONNECTX8_DUAL_HOSTS"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
network_device	ConnectX-8	ConnectX-8
host	Grace CPU	04_knowledge_base/NVIDIA Grace
host	B300	04_knowledge_base/NVIDIA B300
host_type	GPU	GPU

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。