VR2R-0057_r1

VR2R-0057

① SA Source

• Source: 開啟完整 SA 文章
• Section: Extreme Co-design: 6 Silicon Product Offerings under the Rubin Platform - Chip Floorplans & Specifications
• Line hint: 49

Context Before

Rubin’s dense FP4 and FP8 FLOPs increase by roughly ~3.5× versus GB200, while FP16 FLOPs rise by a more modest ~1.6x, underscoring NVIDIA’s continued emphasis on FP4/FP8 as the primary scaling vector.

Evidence

On the memory side, HBM capacity remains flat from GB300, while HBM bandwidth scales more aggressively at ~2.8x.

Context After

Overall, the architecture prioritizes bandwidth and low-precision compute.

② Atomic Claim

在 memory 方面，HBM capacity 與 GB300 持平，但 HBM bandwidth 約提升 2.8 倍。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "comparison_expression": "HBM capacity 相較 GB300 持平，而 HBM bandwidth 約提升 2.8x。",
  "entities": [
    {
      "id": "04_knowledge_base/HBM",
      "label": "HBM"
    },
    {
      "id": "04_knowledge_base/GB300",
      "label": "GB300"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "MEMORY_CAPACITY_AND_BANDWIDTH_SCALING",
  "operator": "MIXED_SCALING",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "2.8x"
    ],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	HBM	HBM
entity	GB300	GB300

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。