clm_7dd3036a6d2a46e682145e9b313cc795_r1

NIEK2-0235

① SA Source

• Source: 開啟完整 SA 文章
• Section: Oberon and Kyber Updates, Larger World Sizes Introduced, More Networking Updates
• Line hint: 285

Context Before

Kyber midplane PCB (GPU side). Source: Nvidia, SemiAnalysis

For Rubin Ultra NVL144 Kyber, there will be no CPO used for scale up as we have told clients multiple times ↗, despite rumors from other analysts suggesting scale-up CPO introduction for Kyber. However, optics for NVLink are coming and will be progressively phased in. Scale-up CPO will first be used for the Rubin Ultra NVL 576 system to connect between 8 Oberon form factor racks, forming a two-layer all-to-all network. A copper backplane will still be used for scale-up networking within the racks however. This is still for low volume / testing purposes.

Evidence

Connecting all 144 GPUs in an all-to-all network will require 72 NVLink 7.0 Switch Chips running at 28.8Tbit/s uni-di of aggregate bandwidth each

Context After

Source: SemiAnalysis

② Atomic Claim

要將全部 144 顆 GPUs 以 all-to-all network 連接，需要 72 顆 NVLink 7.0 Switch chips，每顆提供 28.8Tbit/s uni-di aggregate bandwidth。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/NVLink",
    "label": "NVLink"
  },
  "predicate": "CONNECTS_TO",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "144",
      "72",
      "7.0 S",
      "28.8Tb"
    ],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/GPU",
    "label": "GPUs"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
subject	GPUs	GPU
object	NVLink	NVLink

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。