clm_e07329a370bd4d429c93006168559819_r1

IX2-0167

① SA Source

• Source: 開啟完整 SA 文章
• Section: Nvidia versus AMD Disagg Prefill
• Line hint: 276

Context Before

Source: SemiAnalysis InferenceX ↗

Evidence

when we compare AMD FP4 disagg prefill to Nvidia, performance is subpar and the MI355X gets absolutely mogged by Nvidia’s B200

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

但比較 AMD FP4 disagg prefill 與 Nvidia 時，MI355X 表現明顯不佳，遠落後 Nvidia 的 B200。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "MATURITY",
  "context_nodes": [
    {
      "id": "04_knowledge_base/FP4",
      "label": "FP4"
    },
    {
      "id": "04_knowledge_base/Prefill",
      "label": "prefill"
    },
    {
      "id": "02_companies/NVDA",
      "label": "Nvidia"
    },
    {
      "id": "04_knowledge_base/MI355X",
      "label": "MI355X"
    },
    {
      "id": "04_knowledge_base/NVIDIA B200",
      "label": "B200"
    }
  ],
  "entity": {
    "id": "02_companies/AMD",
    "label": "AMD"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [],
    "value_text": "但比較 AMD FP4 disagg prefill 與 Nvidia 時，MI355X 表現明顯不佳，遠落後 Nvidia 的 B200。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	AMD	AMD
context_0	FP4	FP4
context_1	prefill	Prefill
context_2	Nvidia	NVDA
context_3	MI355X	MI355X
context_4	B200	04_knowledge_base/NVIDIA B200

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。