FabDashboardSemi Intelligence
Demo Data — MVP
OVERVIEW
  • Dashboard
  • Executive Briefing
FOUNDRIES
  • All Companies
  • TSMC
  • Intel Foundry
  • Samsung Foundry
  • GlobalFoundries
  • SMIC
  • Terafab
OPERATIONS
  • Intel Operations
  • Intelligence Feed
  • Bottleneck Index
  • Dependencies
  • Change Tracker
  • Review Queue
  • Search
STRATEGIC
  • Risk Model
  • Scenarios
  • Power & Energy
INTELLIGENCE
  • AI Infrastructure
  • Node Tracker
  • AI Chips
  • Packaging
  • Datacenters
  • Timeline
  • Supply & Demand
  • Global Map
  • Supply Chain
PLATFORM
  • About
  • Methodology
  • Sources
  • Glossary

FabDashboard v0.1 MVP
Data is illustrative only.
Not for investment use.

FabDashboardAI Chip Tracker
⚠Demo Data
⚠DEMO DATA — All figures are illustrative estimates only. Not for investment, trading, or business decisions.

AI Chip Tracker

AI accelerators, training chips, and inference processors. Key supply chain intelligence for the AI infrastructure stack.

All compute figures (TFLOPS), memory bandwidth, TDP, and release timelines are illustrative estimates from public sources. Actual chip specifications may differ. Data labeled with confidence level. Not for investment decisions.

Chips Tracked
12
GA / Ramping
10
In Development
2
Speculative
1

AMD

2 chips tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

MI300X

CDNA3

AI Inference / Training

Generally Avail.TSMC N5 / N6 (chiplets) [est.]CoWoS (Advanced Chiplet Package)
HBM3192GB
5,300 GB/s1,307 FP8750W2023
HIGH[AMD Financial Analyst Day 2023]

MI400

CDNA4

AI Training / Inference

In DevelopmentTSMC N3P [est.]Advanced CoWoS / SoIC [est.]
HBM3e [est.]
———2026
LOW[AMD Roadmap Slides 2024]

Amazon

1 chip tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

Trainium2

Trainium

AI Training

RampingTSMC N4 (4nm-class) [est.]Custom AWS packaging [est.]
HBM396GB
3,200 GB/s1,700 FP8500W2024
MED[AWS re:Invent 2023]

Cerebras

1 chip tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

WSE-3

Wafer Scale Engine

AI Training / LLM

Generally Avail.TSMC N5 (5nm, full wafer) [est.]Full wafer — no packaging
SRAM (on-chip)44GB
21,000 GB/s125,000 FP1623000W2024
HIGH[Cerebras Product Launch 2024]

Google

2 chips tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

TPU v5e

Trillium

AI Training / Inference

Generally Avail.TSMC N5 (5nm-class) [est.]Proprietary Google packaging [est.]
HBM2e16GB
820 GB/s393 BF16197W2023
MED[Google I/O 2023 / GCP Product Page]

TPU v5p

Trillium

AI Training (Large Scale)

Generally Avail.TSMC N4 (4nm-class) [est.]Proprietary Google packaging [est.]
HBM396GB
2,765 GB/s918 BF16450W2023
MED[Google I/O 2023]

Groq

1 chip tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

GroqChip LPU

LPU

AI Inference (Ultra-low latency)

Generally Avail.TSMC N14 (14nm) [est.]Standard flip-chip [est.]
SRAM (on-chip)0
80,000 GB/s750 FP16300W2023
MED[Groq product page / Hot Chips 2023]

NVIDIA

4 chips tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

H100 SXM5

Hopper

AI Training / HPC

Generally Avail.TSMC N4 (4nm-class) [est.]CoWoS-L
HBM380GB
3,350 GB/s1,979 FP8700W2022
HIGH[NVIDIA GTC 2022 / Hot Chips 2022]

H200 SXM5

Hopper

AI Training / Inference

Generally Avail.TSMC N4P (4nm-class) [est.]CoWoS-L
HBM3e141GB
4,800 GB/s1,979 FP8700W2024
HIGH[NVIDIA SC23 Announcement]

B200 / GB200

Blackwell

AI Training / Inference

RampingTSMC N4P (4nm-class) [est.]CoWoS-L (NVLink-C2C bridge)
HBM3e192GB
8,000 GB/s9,000 FP41000W2025
MED[NVIDIA GTC 2024]

Rubin R100

Rubin

AI Training / Inference

In DevelopmentTSMC N3 (3nm-class) [est./spec.]SoIC + CoWoS-L [spec.]
HBM4 [spec.]
———2026
LOW[NVIDIA Investor Day 2024 roadmap]

Tesla

1 chip tracked
ChipStatusProcess NodePackagingMemoryBandwidthPeak ComputeTDPGA YearConfidence

Dojo D1

Dojo

AI Training (Computer Vision)

RampingTSMC N7 (7nm-class) [est.]Custom Tesla ExaPOD tile [est.]
SRAM (on-die)
10,000 GB/s362 FP32400W2023
MED[Tesla AI Day 2021 / Hot Chips 2022]

Dominant Foundry

TSMC

Manufactures virtually all leading AI accelerators. NVIDIA, AMD, Google, Amazon all on TSMC N4/N5. [est.]

[Analyst consensus]

HBM Bottleneck

SK Hynix

Primary HBM3e supplier. NVIDIA Blackwell allocation reported to be prioritized over other customers. [est.]

[SK Hynix Q3 2024 earnings]

Packaging Constraint

CoWoS-L

TSMC CoWoS advanced packaging has been a key supply constraint for H100/H200/Blackwell GPU production. [est.]

[TSMC earnings / analyst reports 2023–2024]

* All compute figures, memory specs, and release timelines are illustrative estimates from public announcements. Speculative chips () have low-confidence data. Not for investment use.