SA260324R-0326_r1

SA260324R-0326

① SA Source

• Source: 開啟完整 SA 文章
• Section: Feynman NVL1152 Networking Topologies
• Line hint: 412

Context Before

To double the scale-up bandwidth using copper interconnect, NVIDIA would have to achieve a per lane bandwidth of 448Gbit/s uni-di (and implemented with simultaneous bi-directional SerDes so that each physical channel carries 448G of RX and 448G of TX). However, this is a challenging feat as they would first have to prove the feasibility of 448Gb/s PAM4 SerDes at large volumes, then implement echo cancellation to achieve bidirectional bandwidth, which is in itself extremely difficult. We believe Nvidia is going for 448G uni-di only.

Evidence

Feynman could use in-rack optics, where switch blades are blind-mated to the midplane using optical connectors

Context After

and thin fiber strands can be used to connect the optical connectors to the NVLink 8 Switches in place of flyover cables, but we believe this is very unlikely.

② Atomic Claim

Feynman 可能採用 in-rack optics，讓 switch blade 透過 optical connector blind-mate 到 midplane。

• Epistemic Mode: HYPOTHETICAL
• Mapping Status: PARTIAL

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/NVIDIA Feynman Architecture",
        "label": "Feynman"
      },
      "role": "generation"
    },
    {
      "node": {
        "id": "04_knowledge_base/Midplane",
        "label": "midplane"
      },
      "role": "midplane"
    }
  ],
  "qualifiers": {
    "condition_text": "switch blade, optics, and optical connector are not canonical-linked in this atomic claim",
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "relation_type": "HYPOTHETICAL_FEYNMAN_IN_RACK_OPTICS"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
generation	Feynman	04_knowledge_base/NVIDIA Feynman Architecture
midplane	midplane	Midplane

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。