IX2-0518

① SA Source

Context Before

GPT-OSS 120B Single Node

MI300X, MI325X, H200, and H100 group in the lower-left of the throughput vs interactivity plot, indicating broadly similar tradeoffs, with Nvidia generally holding a modest lead. The next step up is MI355X, which delivers roughly more than 2x higher token throughput per GPU at a given interactivity level, relative to that first group. Within MI355X, ATOM shifts the curve toward higher throughput at low interactivity, suggesting it prioritizes peak throughput over per-user responsiveness.

Evidence

Above that tier sits NVIDIA’s B200 and GB200, which outperform MI355X across the frontier

Context After

image

Source: SemiAnalysis InferenceX

② Atomic Claim

更高一層則是 NVIDIAB200GB200,兩者在整條 frontier 上都優於 MI355X

  • Epistemic Mode: ASSERTED
  • Mapping Status: PARTIAL

③ Semantic Frame

{
  "comparison_expression": "更高一層則是 NVIDIA 的 B200 與 GB200,兩者在整條 frontier 上都優於 MI355X。",
  "entities": [
    {
      "id": "02_companies/NVDA",
      "label": "NVIDIA"
    },
    {
      "id": "04_knowledge_base/NVIDIA B200",
      "label": "B200"
    },
    {
      "id": "04_knowledge_base/GB200",
      "label": "GB200"
    },
    {
      "id": "04_knowledge_base/MI355X",
      "label": "MI355X"
    }
  ],
  "frame_type": "COMPARISON",
  "metric": "UNSPECIFIED_METRIC",
  "operator": "OUTPERFORMS",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [],
    "temporal_mentions": []
  }
}

④ Canonical Entity Mapping

RoleSurface LabelCanonical Target
comparison_entity_0NVIDIANVDA
comparison_entity_1B20004_knowledge_base/NVIDIA B200
comparison_entity_2GB200GB200
comparison_entity_3MI355XMI355X

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。