GB2-0003
① SA Source
- Source: 開啟完整 SA 文章
- Section:
The 4 Rack Scale Form Factors of Blackwell - Line hint:
153
Context Before
Source: SemiAnalysis
Evidence
The GB200 NVL72 racks consists of 18 1U compute trays and 9 NVSwitch trays.
Context After
With the exception of one hyperscaler who plans to deploy this as the primary variant, we believe that this version will be rarely deployed until Blackwell Ultra as most datacenter infrastructure cannot support this high of a rack density even with direct-to-chip liquid cooling (DLC).
The next form factor is the GB200 NVL36 * 2 which is two racks side by side interconnected together. Most of the GB200 racks will use this form factor. ↗ Each rack contains 18 Grace CPUs and 36 Blackwell GPUs. Between the 2 racks, it still maintains being non-blocking all-to-all between all the 72 GPUs found in NVL72. Each compute tray is 2U in height and contains 2 Bianca boards. Each NVSwitch tray has two 28.8Tb/s NVSwitch5 ASIC chips. Each chip has 14.4Tb/s pointing backward toward the backplane and 14.4Tb/s pointing toward the front plate. Each NVswitch tray has 18 1.6T twin-port OSFP cages which connect horizontally to a pair NVL36 rack.
② Atomic Claim
GB200 NVL72 rack 由 18 個 1U compute trays 與 9 個 NVSwitch trays 組成。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/GB200 NVL72",
"label": "GB200 NVL72"
},
"role": "system"
},
{
"node": {
"id": "04_knowledge_base/NVSwitch",
"label": "NVSwitch"
},
"role": "switch_component"
}
],
"qualifiers": {
"condition_text": "18 compute trays; 9 NVSwitch trays",
"numeric_mentions": [
"18",
"1U",
"9"
],
"temporal_mentions": []
},
"relation_type": "RACK_COMPOSITION"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| system | GB200 NVL72 | 04_knowledge_base/GB200 NVL72 |
| switch_component | NVSwitch | NVSwitch |
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。