VR2-0777
① SA Source
- Source: 開啟完整 SA 文章
- Section:
VR NVL72 TCO: BoM and Power Budget Analysis - Line hint:
983
Context Before
Source: SemiAnalysis AI TCO Model ↗
Inference throughput too can diverge materially from marketed peak FLOPS, meaning spec-sheet compute does not directly translate into real-world token generation performance. While the B300 is rated at 4,500 Dense FP8 TFLOPs versus 5,000 Dense FP8 TFLOPs for MI355, implying a 10% theoretical compute disadvantage and with same marketed memory bandwidth of 8TB/s measured inference token throughput from our InferenceX ↗ benchmarks shows B300 delivering roughly 6.3x the performance at 100 interactivity for Deepseek R1, using 8k input tokens and 1k output tokens.
Evidence
Given that total cost of ownership is only 1.75x higher, this results in a superior performance-per-TCO profile for B300 despite the more modest marketed figures
Context After
Rubin and MI4XX will ship with new microarchitectures, real world performance is especially difficult to predict without and benchmarking like we do with InferenceX.
Notably, both operating modes share identical memory bandwidth specifications at 8TB/s. Yet, despite the parity in memory bandwidth inference performance still diverges materially.
② Atomic Claim
由於 total cost of ownership 只高 1.75 倍，因此儘管 marketed figures 較保守，B300 仍具有更佳 performance-per-TCO。
- Epistemic Mode:
ASSERTED - Mapping Status:
PARTIAL
③ Semantic Frame
{
"comparison_expression": "由於 total cost of ownership 只高 1.75 倍，因此儘管 marketed figures 較保守，B300 仍具有更佳 performance-per-TCO。",
"entities": [
{
"id": "04_knowledge_base/NVIDIA B300",
"label": "B300"
}
],
"frame_type": "COMPARISON",
"metric": "COST",
"operator": "MULTIPLE_OF",
"qualifiers": {
"condition_text": null,
"numeric_mentions": [
"1.75"
],
"temporal_mentions": []
}
}④ Canonical Entity Mapping
| Role | Surface Label | Canonical Target |
|---|---|---|
| comparison_entity_0 | B300 | 04_knowledge_base/NVIDIA B300 |
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。