VR2R-0120
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Vera - Line hint:
97
Context Before
Evidence
Context After
Core count increases from 72 to 88, with 91 cores printed on die to leave redundancy for yield improvement. These cores mark the return of NVIDIA’s custom ARM CPU designs, with the ‘Olympus’ core now supporting SMT multi-threading for a total of 176 processing threads.
② Atomic Claim
NVIDIA 在 CPU 方面採取積極設計:Vera 相較 Grace 效能加倍,透過 3nm reticle-sized compute die,並將 memory controllers 與 I/O 拆分到 chiplets。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "02_companies/NVDA",
"label": "NVIDIA"
},
"role": "vendor"
},
{
"node": {
"id": "04_knowledge_base/CPU",
"label": "CPU"
},
"role": "processor_category"
},
{
"node": {
"id": "04_knowledge_base/NVIDIA Grace",
"label": "Grace"
},
"role": "prior_cpu"
},
{
"node": {
"id": "04_knowledge_base/Chiplet architecture",
"label": "chiplets"
},
"role": "architecture"
}
],
"qualifiers": {
"condition_text": "Vera 名稱在此 claim 未 canonical-link;memory controller/I/O 未 canonicalized",
"numeric_mentions": [
"2x",
"3nm"
],
"temporal_mentions": []
},
"relation_type": "VERA_CPU_PERFORMANCE_AND_DISAGGREGATION"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| vendor | NVIDIA | NVDA |
| processor_category | CPU | CPU |
| prior_cpu | Grace | 04_knowledge_base/NVIDIA Grace |
| architecture | chiplets | 04_knowledge_base/Chiplet architecture |
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。