SA260324R-0074_r1

SA260324R-0074

① SA Source

• Source: 開啟完整 SA 文章
• Section: SRAM and Memory Hierarchy
• Line hint: 85

Context Before

LPU 3’s near reticle size die layout is very similar to LPU 1. a significant amount of area taken is up by the 500MB of on-chip SRAM, with

Evidence

a very small amount of area dedicated to MatMul cores that offer 1.2 PFLOPs of FP8 compute – a fraction of compute compared to Nvidia GPUs.

Context After

This compares to LPU 1 with 230MB of SRAM and 750 TFLOPs of INT8, with the performance increase mostly driven by node migration from GF16 to SF4. As a single monolithic die, advanced packaging isn’t required.

② Atomic Claim

只有很小一部分 die area 配置給 MatMul cores，提供 1.2 PFLOPs 的 FP8 compute；相較 Nvidia GPU，其運算能力僅是一小部分。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "comparison_expression": "LPU 3 的 MatMul cores 提供 1.2 PFLOPs FP8 compute，僅為 Nvidia GPU compute 的一小部分。",
  "entities": [
    {
      "id": "04_knowledge_base/Groq LPU",
      "label": "LPU 3"
    },
    {
      "id": "04_knowledge_base/GPU",
      "label": "Nvidia GPU"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "FP8_COMPUTE",
  "operator": "FRACTION_OF",
  "qualifiers": {
    "condition_text": "very small die area dedicated to MatMul cores",
    "numeric_mentions": [
      "1.2 PFLOPs"
    ],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	LPU 3	04_knowledge_base/Groq LPU
entity	Nvidia GPU	GPU

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。