SA260324R-0163_r1

SA260324R-0163

① SA Source

• Source: 開啟完整 SA 文章
• Section: LPU Network
• Line hint: 197

Context Before

The LPU network can be divided into the scale-up ‘C2C’ network and scale-out network which interacts with the Nvidia GPUs through Spectrum-X. First let’s discuss the scale-up network which can be divided into 3 portions: intra-node, inter-node/intra-rack, inter-rack. For C2C within the rack Nvidia announced a total of 640TB/s of scale up bandwidth per rack which comes from 256 LPUs x 90 lanes x 112Gbps/8 x 2 directions = 645TB/s.

Evidence

Note that Nvidia uses the total 112G line rate rather than 100G of effective data rate.

Context After

② Atomic Claim

要注意的是，Nvidia 採用總 112G line rate，而不是 100G effective data rate。

• Epistemic Mode: ASSERTED
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "attribute": "BANDWIDTH_ACCOUNTING_RATE",
  "context_nodes": [
    {
      "id": "04_knowledge_base/100G",
      "label": "100G"
    }
  ],
  "entity": {
    "id": "02_companies/NVDA",
    "label": "Nvidia"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": "112G 在此 claim 沒有 canonical entity",
    "numeric_mentions": [
      "112G",
      "100G"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "112G",
      "100G"
    ],
    "value_text": "採用 112G line rate，而不是 100G effective data rate。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	Nvidia	NVDA
context_node	100G	100G

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。