VR2R-0573
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Scale-Up Network - NVLink 6 - Line hint:
476
Context Before
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.
Evidence
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.
Context After
Each compute tray on the VR NVL72 has eight 800G CX-9 NICs, but 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. We think that the latter would be the more popular deployment assumption.
② Atomic Claim
每顆 Rubin chip 所連接的「1.6T NIC」其實由 2 個 800G CX-9 packages 組成,並透過 PCIe Gen 6.0 lanes 連接到 Vera CPU。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/Vera Rubin",
"label": "Rubin"
},
"role": "processor"
},
{
"node": {
"id": "04_knowledge_base/NIC",
"label": "NIC"
},
"role": "network_interface"
},
{
"node": {
"id": "04_knowledge_base/ConnectX-9",
"label": "CX-9"
},
"role": "nic_package"
},
{
"node": {
"id": "04_knowledge_base/NVIDIA Vera CPU",
"label": "Vera CPU"
},
"role": "host_cpu"
},
{
"node": {
"id": "04_knowledge_base/PCIe",
"label": "PCIe Gen 6.0"
},
"role": "host_link"
}
],
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"1.6T",
"2",
"800G",
"6.0"
],
"temporal_mentions": []
},
"relation_type": "RUBIN_1_6T_NIC_COMPOSED_OF_DUAL_800G_CX9"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| processor | Rubin | 04_knowledge_base/Vera Rubin |
| network_interface | NIC | NIC |
| nic_package | CX-9 | ConnectX-9 |
| host_cpu | Vera CPU | 04_knowledge_base/NVIDIA Vera CPU |
| host_link | PCIe Gen 6.0 | PCIe |
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。