clm_35e91e9b00634992b3012aace8effac6_r1

VR2-0764

① SA Source

• Source: 開啟完整 SA 文章
• Section: VR NVL72 TCO: BoM and Power Budget Analysis
• Line hint: 967

Context Before

Source: SemiAnalysis AI TCO Model ↗

The MI4XX currently has a performance per TCO advantage based on marketed dense FLOPS over VR. VR has a higher TCO per GPU compared to MI4XX, yet VR marketed PFLOPs are lower vs MI4XX resulting in a TCO per PFLOP disadvantage for the VR vs MI4XX.

Evidence

Harnessing the 50 PFLOPS sparse vs 35 PFLOPS dense drops the cost per perf in units of $/hr per Marketed PFLOP by 35% – a valid comparison if AI Labs can indeed successfully harness Sparse FP4 on the VR NVL72

Context After

As always, one caveat is that this comparison is done based on a marketed dense PFLOP basis. Effective dense PFLOP (i.e. the real world chip throughput) can differ based on Model Flops Utilization % (MFU), and in general we have seen NVIDIA chip operate at a higher MFU % vs AMD chips, suggesting that performance per TCO based on effective dense PFLOPs could be better for NVIDIA systems vs AMD – however, MFU is dependent on actual workloads with no one-size-fits-all MFU % that is consistently applicable to either systems.

Indeed, real world use of FP4 Sparsity will probably not reach 50 PFLOPS but it will probably deliver better effective FLOPs than FP4 Dense, but we have yet to evaluate what that real-world performance could be. Running VR NVL72 on 1800W would probably mean lower FP4 Sparse FLOPs than on 2300W.

② Atomic Claim

若能實際利用 50 PFLOPS sparse、而非 35 PFLOPS dense，則以 $/hr per Marketed PFLOP 衡量的 cost per performance 可降低 35%；前提是 AI Labs 確實能在 VR NVL72 成功利用 Sparse FP4。

• Epistemic Mode: HYPOTHETICAL
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "COMPUTE_PERFORMANCE",
  "context_nodes": [
    {
      "id": "04_knowledge_base/FP4",
      "label": "FP4"
    }
  ],
  "entity": {
    "id": "04_knowledge_base/VR NVL72",
    "label": "VR NVL72"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "50 PFLOPS",
      "35 PFLOPS",
      "35%"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "50 PFLOPS",
      "35 PFLOPS",
      "35%"
    ],
    "value_text": "若能實際利用 50 PFLOPS sparse、而非 35 PFLOPS dense，則以 $/hr per Marketed PFLOP 衡量的 cost per performance 可降低 35%；前提是 AI Labs 確實能在 VR NVL72 成功利用 Sparse FP4。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	VR NVL72	04_knowledge_base/VR NVL72
context_0	FP4	FP4

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。