SA260324R-0193_r1

SA260324R-0193

① SA Source

• Source: 開啟完整 SA 文章
• Section: Nvidia's CPO Roadmap
• Line hint: 233

Context Before

In the Rubin Generation, Nvidia will offer the Rubin GPU in an Oberon NVL72 form factor with an all-copper scale-up network. For Rubin Ultra, as we expected, there will only be a copper scale-up option for Rubin Ultra in the Oberon and Kyber Rack form factor.

Evidence

Rubin Ultra will also be offered in a larger world size system that connects 8 Oberon Racks of 72 Rubin Ultra GPUs to form what will be referred to as NVL576.

Context After

CPO scale-up will be used to build the larger world size, connecting between the racks in a two-tier all to all network, though scale-up inside the racks will remain copper-based.

② Atomic Claim

Rubin Ultra 也會提供較大 world-size 的系統：將 8 個 Oberon Rack、每櫃 72 顆 Rubin Ultra GPU 連在一起，形成 NVL576。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/Rubin Ultra",
        "label": "Rubin Ultra"
      },
      "role": "platform"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA Oberon",
        "label": "Oberon Rack"
      },
      "role": "rack"
    },
    {
      "node": {
        "id": "04_knowledge_base/GPU",
        "label": "GPU"
      },
      "role": "compute_device"
    },
    {
      "node": {
        "id": "04_knowledge_base/NVL576",
        "label": "NVL576"
      },
      "role": "system"
    }
  ],
  "qualifiers": {
    "condition_text": "8 個 Oberon Racks，每櫃 72 顆 Rubin Ultra GPU",
    "numeric_mentions": [
      "8",
      "72",
      "576"
    ],
    "temporal_mentions": []
  },
  "relation_type": "FORMS_LARGER_WORLD_SIZE_SYSTEM"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
platform	Rubin Ultra	04_knowledge_base/Rubin Ultra
rack	Oberon Rack	04_knowledge_base/NVIDIA Oberon
compute_device	GPU	GPU
system	NVL576	NVL576

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。