Research library · updated 2026-07-10 · public

Board — Accelerator Silicon (GPU / TPU / ASIC / Wafer-Scale)

Status: active Owner: Finance / Charlie AGT-002 Board ID: BOARD-AI-SILICON Visibility: PUBLIC Last updated: 2026-07-10

Purpose

Track the technical trajectory of AI accelerator silicon — architectures, roadmaps, measured performance, and cost curves — across the merchant GPU incumbents, hyperscaler in-house ASICs, the China domestic stack, and wafer-scale challengers.

Methodology (SemiAnalysis-inspired, public-primitives version): follow the physical primitives — process node, memory type/bandwidth, packaging, scale-up/scale-out interconnect, rack power — from PUBLIC primary sources only (vendor spec pages, architecture whitepapers, MLCommons results, listed-company filings). Spec-sheet numbers are commitments (A2); measured benchmark results and shipment/revenue disclosures are throughput (A3); street pricing and rental rates are price signals (A4).

This board's pages are approved PUBLIC (Hugo, 2026-07-10): technical facts and source-graded tables only. Investment implications, share forecasts, and portfolio linkage stay MEMBERS/INTERNAL elsewhere.

Coverage

Entity pageScope
../entities/nvidia.mdMerchant GPU incumbent — architecture cadence, HBM/interconnect roadmap
../entities/amd.mdMerchant GPU challenger — Instinct line, ROCm maturity signals
../entities/google-tpu.mdHyperscaler in-house ASIC — TPU generations, internal + external availability
../entities/huawei-ascend.mdChina stack lead — Ascend series, SMIC node constraint, cluster-scale workaround
../entities/cambricon.mdChina merchant accelerator — listed (688256.SH), filings-visible revenue
../entities/cerebras.mdWafer-scale challenger — WSE generations, inference-as-a-service pivot
../entities/custom-asic.mdBroadcom/Marvell co-designed hyperscaler ASICs (Trainium, Maia, MTIA, etc.)

Tracked Series

SeriesUnitSource IDCadenceSeries file
Accelerator spec matrixnode / GB / TB/s / FLOPs / WSRC-AI-VENDOR-SPECSEvent (launches) + quarterly sweep../../series/accelerator-specs.md
Measured benchmarksMLPerf results, tokens/s/chipSRC-AI-MLCOMMONSPer MLPerf round (~2/yr) + event../../series/accelerator-benchmarks.md
Roadmap cadencemonths between generations per vendorSRC-AI-VENDOR-SPECSEvent(derived in this board page)
China stack shipments/revenueCNY revenue, units where disclosedSRC-AI-CNINFO-FILINGSQuarterly filings../../series/accelerator-specs.md (rows) + china-ai-stack board

Primary Sources

  • Vendor spec pages / architecture whitepapers (NVIDIA, AMD, Google Cloud, Huawei, Cambricon IR, Cerebras) — Primary
  • MLCommons (MLPerf Training/Inference) results tables — Primary
  • Listed-company filings: Cambricon 688256.SH (cninfo), TSMC/SK Hynix calls for node/HBM context — Primary
  • SemiAnalysis FREE posts — Secondary (never paywalled content; client-conflict caveat)
  • Hot Chips / ISSCC papers — Primary for architecture detail

Current Claims

  • CLAIM-AI-SILICON-001 — custom-ASIC share of accelerator compute rising vs merchant GPU (watch)
  • CLAIM-AI-SILICON-002 — China domestic stack node gap vs frontier, and the cluster-scale/chiplet workaround path (watch)
  • Related: CLAIM-AI-BOTTLENECK-001 (pricing power sits at the current bottleneck)

Noise Rules

  • Ignore un-dated "next-gen chip will be Nx faster" claims without a spec sheet or paper (A1 narrative — log nothing).
  • Peak-FLOPs marketing without precision/sparsity qualifiers is not comparable data; record only with precision noted.
  • Do not infer China-stack parity from single benchmark demos; require reproducible results or filings-visible revenue.
  • Vendor "orders/backlog" leaks are not shipments; only filings and disclosed shipments count as A3.