VR2R-0135_r1

VR2R-0135

① SA Source

• Source: 開啟完整 SA 文章
• Section: ConnectX-9
• Line hint: 109

Context Before

The ConnectX-9 is largely iterative from ConnectX-8, with the same 800G networking bandwidth and 48-lane PCIe6 switch capability. However, CX-9 now supports 800G Ethernet with 4x200G PAM4 SerDes, compared to CX-8 that only supported it on InfiniBand.

Evidence

For the Rubin platform, NVIDIA is doubling the number of NICs per GPU to achieve 2x scale-out bandwidth.

Context After

② Atomic Claim

在 Rubin platform 上，NVIDIA 將每顆 GPU 對應的 NIC 數量加倍，以達到 2 倍 scale-out bandwidth。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/Vera Rubin",
        "label": "Rubin"
      },
      "role": "platform"
    },
    {
      "node": {
        "id": "02_companies/NVDA",
        "label": "NVIDIA"
      },
      "role": "vendor"
    },
    {
      "node": {
        "id": "04_knowledge_base/NIC",
        "label": "NIC"
      },
      "role": "network_device"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "compute_device"
    }
  ],
  "qualifiers": {
    "condition_text": "goal is 2x scale-out bandwidth",
    "numeric_mentions": [
      "2x"
    ],
    "temporal_mentions": []
  },
  "relation_type": "DOUBLES_NIC_PER_GPU_FOR_SCALEOUT"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
platform	Rubin	04_knowledge_base/Vera Rubin
vendor	NVIDIA	NVDA
network_device	NIC	NIC
compute_device	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。