NIEK2-0201
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Nvidia’s CPO Roadmap - Line hint:
219
Context Before
When we reach the Feynman Generation, CPO usage will expand via another large world size rack, the NVL1152 which is formed by combining 8 Kyber racks. While the Nvidia Technical Blog ↗ that outlines the rack configuration roadmap states that “NVIDIA Kyber will scale up into a massive all-to-all NVL1152 supercomputer using similar direct optical interconnects for rack-to-rack scale-up”, Jensen Huang in a Financial Analyst Q+A session did say that NVL1152 in Feynman would be “all CPO”. There is some disagreement on whether copper will still be used for scale-up within the rack or whether CPO will replace copper.
Nvidia’s approach has been to use copper where they can, and optics where they must. The architecture of NVL1152 in the Feynman generation will follow the same principle. It is clear that the NVL1152 will adopt CPO to connect between racks, but from GPUs to NVLink Switches is currently copper POR. Nvidia is unable to achieve another doubling of electrical lane speed from 224Gbit/s bi-di to 448Gbit/s uni-di means bandwidth isn’t that amazing.
Evidence
power versus using a die-to-die connection to an optical engine, the manufacturing challenges, cost, and reliability for Feynman necessitate using copper to the Switch
Context After
With that said, the NVL1152 SKU is years out – and the roadmap is highly likely to shift. For now, our base case stands at copper being used within each rack and CPO between the racks, but this could easily change.
For now – our best estimate of Nvidia’s CPO roadmap is as follows:
② Atomic Claim
相較以 die-to-die 方式連接 optical engine，448G 高速 SerDes 在功耗方面也有重大挑戰；考量 Feynman 的製造難度、成本與可靠性，系統仍需要以 copper 連到 Switch。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"comparison_expression": "相較以 die-to-die 方式連接 optical engine，448G 高速 SerDes 在功耗方面也有重大挑戰；考量 Feynman 的製造難度、成本與可靠性，系統仍需要以 copper 連到 Switch。",
"entities": [
{
"id": "04_knowledge_base/Die-to-die interconnect",
"label": "die-to-die"
},
{
"id": "04_knowledge_base/Optical Engine",
"label": "optical engine"
},
{
"id": "04_knowledge_base/SerDes",
"label": "SerDes"
},
{
"id": "04_knowledge_base/NVIDIA Feynman Architecture",
"label": "Feynman"
},
{
"id": "04_knowledge_base/Copper",
"label": "copper"
}
],
"frame_type": "COMPARISON",
"metric": "POWER",
"operator": "COMPARES_WITH",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"448"
],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | die-to-die | 04_knowledge_base/Die-to-die interconnect |
| comparison_entity_1 | optical engine | 04_knowledge_base/Optical Engine |
| comparison_entity_2 | SerDes | SerDes |
| comparison_entity_3 | Feynman | 04_knowledge_base/NVIDIA Feynman Architecture |
| comparison_entity_4 | copper | Copper |
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。