2025-12-04_aws-trainium3-deep-dive-a-potential::TRN3-0024
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Compute Tray - Line hint:
305
Context Before
Source: SemiAnalysis
Evidence
Liquid cooling is used to cool the Trainium3 modules, the NeuronLinkv4 x32 lanes PCIe 6.0 switch, and the Graviton4 CPU.
Context After
Turning to the host CPU, Graviton4 will be the only time to market CPU option for Trainium3 NL72x2 Switched. The CPU can be upgraded later to the next generation of Graviton during the Trainium3’s lifecycle. In theory, x86 CPUs are also supported as these can also interface with other components via PCIe, but we don’t believe that they will plan to have an x86 Trainium3 NL72x2 Switched SKU and will only offer an x86 Trainium NL32x2 Switched SKU. Because Trainium3 uses PCIe 6.0 and Graviton4 uses PCIe 5.0, two PCIe gearboxes must be placed next to the CPU to convert from PCIe 6.0 to PCIE 5.0 for communication between the CPU and GPUs. For CPU memory, 12 DDR5 DIMM slots are placed next to the CPU with DDR5 DIMM modules of 64GB and 128GB capacities to be used for the mainstream SKU. Two 8TB local NVMe drives per compute tray will be used for local storage.
Trainium3 NL72x2 Switched Scale Out Networking
② Atomic Claim
NL72x2 的 liquid cooling 直接冷卻 Trainium3 modules、NeuronLinkv4 PCIe 6.0 switch 與 Graviton4 CPU。
- Epistemic Mode:
ASSERTED - Mapping Status:
COMPLETE
③ Semantic Frame
{
"frame_type": "NARY_RELATION",
"participants": [
{
"node": {
"id": "04_knowledge_base/液冷散熱",
"label": "Liquid cooling"
},
"role": "cooling"
},
{
"node": {
"id": "04_knowledge_base/Trainium",
"label": "Trainium3"
},
"role": "accelerator"
},
{
"node": {
"id": "04_knowledge_base/NeuronLink",
"label": "NeuronLinkv4"
},
"role": "interconnect"
},
{
"node": {
"id": "04_knowledge_base/Graviton4",
"label": "Graviton4"
},
"role": "cpu"
}
],
"qualifiers": {
"condition_text": "NL72x2",
"numeric_mentions": [
"x32"
],
"temporal_mentions": []
},
"relation_type": "LIQUID_COOLED_COMPONENTS"
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| cooling | Liquid cooling | 04_knowledge_base/液冷散熱 |
| accelerator | Trainium3 | Trainium |
| interconnect | NeuronLinkv4 | NeuronLink |
| cpu | Graviton4 | Graviton4 |
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。