VR2-0060
① SA Source
- Source: 開啟完整 SA 文章
- Section:
Rubin - Line hint:
113
Context Before
Increasing clock speed 25% from 1.90GHz to 2.38GHz
Additionally, Nvidia claims up to an effective 50 PFLOPS of FP4 performance can be achieved with an updated 3rd generation Transformer Engine that replaces 2:4 structured sparsity from prior generations. We will detail this architectural feature for Rubin below.
Evidence
the Tensor core width doubling only applies to FP4 and FP8
Context After
On the memory front, the move to HBM4 means double the bus width per stack, running at 10.8 GT/s for 22TB/s total bandwidth or 2.75x Blackwell at the same 288GB capacity as GB300. Memory bandwidth has been upgraded significantly from the original 13TB/s advertised at GTC 2025. In order to catch up to AMD MI450’s memory bandwidth, Nvidia requested much higher HBM4 pin speeds from the DRAM suppliers - well above the speeds that was in the JEDEC specification for HBM4.
While Nvidia is targeting 22TB/s, we understand that memory suppliers are having challenges hitting Nvidia’s requirements and we see it likely that initial shipments will come in slightly below at closer to 20TB/s. We have discussed the implications to SK Hynix, Samsung, and Micron extensively for Accelerator and HBM model subscribers. ↗ Micron is well behind Samsung and Hynix and we believe they are effectively out of the picture for Rubin HBM4. ↗ We have more details on qualifications and pin speeds in the Accelerator and HBM model ↗
② Atomic Claim
Rubin 的 Tensor Core width 加倍僅適用於 FP4 與 FP8。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"comparison_expression": "Rubin 的 Tensor Core width 加倍僅適用於 FP4 與 FP8。",
"entities": [
{
"id": "04_knowledge_base/Tensor Core",
"label": "Tensor Core"
},
{
"id": "04_knowledge_base/FP4",
"label": "FP4"
},
{
"id": "04_knowledge_base/FP8",
"label": "FP8"
}
],
"frame_type": "COMPARISON",
"metric": "UNSPECIFIED_METRIC",
"operator": "MULTIPLE_OF",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | Tensor Core | 04_knowledge_base/Tensor Core |
| comparison_entity_1 | FP4 | FP4 |
| comparison_entity_2 | FP8 | FP8 |
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。