SA260324R-0039
① SA Source
- Source: 開啟完整 SA 文章
- Section:
LPU chip - Line hint:
51
Context Before
LPU gen 1 was designed on a legacy Global Foundries 14nm process, with Marvell responsible for the chip’s physical design.
Evidence
Context After
This made sense for an early product focused on proving out Groq’s architecture and bringing its inference-centric design to market.
② Atomic Claim
這個節點在 2020 年 tapeout 時,相較同業已成熟許多;當時主流 AI 晶片平台大多採用 TSMC 的 N7 平台。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"comparison_expression": "14nm 在 2020 年 tapeout 時,相較當時多數採用 TSMC N7 的 AI 晶片平台所使用節點更成熟。",
"entities": [
{
"id": "04_knowledge_base/14nm",
"label": "14nm"
},
{
"id": "04_knowledge_base/7nm",
"label": "N7"
}
],
"frame_type": "COMPARISON",
"metric": "PROCESS_NODE_MATURITY",
"operator": "MORE_MATURE_THAN",
"qualifiers": {
"condition_text": "當時 incumbent AI chip platforms mostly on TSMC N7",
"numeric_mentions": [
"2020"
],
"temporal_mentions": [
"2020"
]
}
}④ Canonical Entity Mapping
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。