VR2-0611
① SA Source
- Source: 開啟完整 SA 文章
- Section:
GB200 Hardware Architecture - Component Supply Chain & BOM - Line hint:
735
Context Before
While the VR NVL72 system features GPUs and scale-up switches that are connected by copper cables, the VR HGX system features servers consisting of eight Rubin GPUs and four NVLink Switch chips. The second meaningful difference between the NVL72 and HGX deployments is that the former has a scale-out bandwidth of 1.6T per GPU while the latter only has a scale-out bandwidth of 800G per GPU. How is it that all Rubin 200 deployments use CX-9 NICs even though some deployments have half the per GPU scale-out bandwidth?
The HGX Rubin NVL8 server consists of eight 800G CX-9 NIC packages – one NIC per GPU – which means that the scale-out bandwidth does not increase from its predecessor, the HGX B300 server. The Vera Rubin NVL72 deployment on the other hand doubles the per GPU scale-out bandwidth to 1.6T, but not by doubling the bandwidth per NIC. Rather, the “1.6T NIC” attached to each Rubin chip is comprised of two 800G CX-9 packages that is connected to the Vera CPU by PCIe Gen 6.0 lanes.
Evidence
there are two possibilities for the number of OSFP cages - either one 1.6T OSFP cage per GPU for a total of 4 per compute tray, or two 800G OSFP cages per GPU for a total of 8 cages per compute tray
Context After
Source: Nvidia VR NVL72 Component BoM and Power Budget Model
② Atomic Claim
OSFP cages 有兩種可能配置：每顆 GPU 1 個 1.6T OSFP cage、每個 compute tray 共 4 個；或每顆 GPU 2 個 800G OSFP cages、每個 compute tray 共 8 個。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/OSFP (Octal Small Form-factor Pluggable)",
"label": "OSFP"
},
"role": "system_or_subject"
},
{
"node": {
"id": "04_knowledge_base/GPU",
"label": "GPU"
},
"role": "component"
},
{
"node": {
"id": "04_knowledge_base/1.6T",
"label": "1.6T"
},
"role": "component"
},
{
"node": {
"id": "04_knowledge_base/Compute Tray",
"label": "compute tray"
},
"role": "component"
},
{
"node": {
"id": "04_knowledge_base/800G",
"label": "800G"
},
"role": "component"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"1",
"1.6",
"4",
"2",
"800",
"8"
],
"temporal_mentions": []
},
"relation_type": "HAS_COMPONENT"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| system_or_subject | OSFP | 04_knowledge_base/OSFP (Octal Small Form-factor Pluggable) |
| component | GPU | GPU |
| component | 1.6T | 1.6T |
| component | compute tray | 04_knowledge_base/Compute Tray |
| component | 800G | 800G |
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。