SA260324R-0279_r1

SA260324R-0279

① SA Source

• Source: 開啟完整 SA 文章
• Section: Vera ETL256
• Line hint: 348

Context Before

CPU demand is rising as AI workloads require more data handling, preprocessing, and orchestration beyond GPU compute. Reinforcement learning further increases demand, with CPUs running simulations, executing code, and verifying outputs in parallel. As GPUs scale faster than CPUs, larger CPU clusters are needed to keep them fully utilized, making CPUs a growing bottleneck.

Evidence

The Vera standalone rack addresses this directly, achieving unprecedented density by fitting 256 CPUs into a single rack — a feat that necessitates liquid cooling.

Context After

The underlying rationale mirrors the NVL rack design philosophy: pack compute tightly enough that copper interconnects can reach everything within the rack, eliminating the need for optical transceivers on the spine. The cost savings from copper more than offset the additional cooling overhead.

② Atomic Claim

Vera standalone rack 透過單一 rack 容納 256 顆 CPU 提升密度，而這種密度需要 liquid cooling。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "frame_type": "NARY_RELATION",
  "participants": [
    {
      "node": {
        "id": "04_knowledge_base/Vera ETL256",
        "label": "Vera standalone rack"
      },
      "role": "rack"
    },
    {
      "node": {
        "id": "04_knowledge_base/CPU",
        "label": "CPU"
      },
      "role": "compute_device"
    },
    {
      "node": {
        "id": "04_knowledge_base/液冷散熱",
        "label": "liquid cooling"
      },
      "role": "cooling"
    }
  ],
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "256"
    ],
    "temporal_mentions": []
  },
  "relation_type": "VERA_ETL256_DENSITY_AND_COOLING"
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
rack	Vera standalone rack	04_knowledge_base/Vera ETL256
compute_device	CPU	CPU
cooling	liquid cooling	04_knowledge_base/液冷散熱

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。