AMD begins production ramp of 256-core EPYC Venice — first 2nm HPC chip claims 70% performance leap

Tom's Hardware· Luke James

3h ago

·~3 min·5/21/2026·en·0

Quick Take

AMD's 6th Gen EPYC Venice processor enters production, promising a 70% performance boost on TSMC's 2nm process.

Key Points

256-core architecture enhances computational capabilities.
Manufactured on TSMC's advanced 2nm technology.
Targets high-performance computing applications.

Reader Mode unavailable (could not extract clean content).

Read on tomshardware.com

Want this in your inbox every morning?

Daily brief at your local 8am — bilingual EN/中文, free.

Subscribe — it's free

More from Tom's Hardware

See more →

The custom AI ASIC state of play (May 2026) — Broadcom deals, Google TPUs, Meta MTIA & beyond

Tom's Hardware· Luke James

2h ago

FeaturedOriginal

The custom AI ASIC state of play (May 2026) — Broadcom deals, Google TPUs, Meta MTIA & beyond

AI Summary

ASIC-based AI server shipments are set to reach 27.8% market share by 2026.

#Inference #GPU #AI Startup #Enterprise AI

0

China bypasses US GPU bans with 1.54-exaflops 'LineShine' supercomputer — CPU-only monster packs 2.4 million Huawei-designed Armv9 cores

Tom's Hardware· Anton Shilov

4d ago

FeaturedOriginal

China bypasses US GPU bans with 1.54-exaflops 'LineShine' supercomputer — CPU-only monster packs 2.4 million Huawei-designed Armv9 cores

AI Summary

China's LineShine supercomputer achieves 1.54 exaflops using 2.4 million Armv9 cores, circumventing US GPU restrictions.

#Robotics #GPU #Policy

3

OpenClaw creator burned through $1.3 million in OpenAI API tokens in a single month — bill covered 603 billion tokens across 7.6 million requests and 100 coding agents

Tom's Hardware· Luke James

4d ago

FeaturedOriginal

OpenClaw creator burned through $1.3 million in OpenAI API tokens in a single month — bill covered 603 billion tokens across 7.6 million requests and 100 coding agents

AI Summary

OpenClaw's creator spent $1.3 million on 603 billion OpenAI tokens in one month.

#LLM #AI Coding #Funding

0

Related in this space

See more →

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

Hugging Face

2d ago

FeaturedOriginal

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

AI Summary

The article discusses fine-tuning NVIDIA Cosmos Predict 2.5 using LoRA/DoRA for enhanced robot video generation.

#Robotics #GPU #Open Source #AI Video

1

AMD to invest $10 billion in Taiwan's AI industry to advance top-end chips

CNBC Tech

7h ago

FeaturedOriginal

AMD to invest $10 billion in Taiwan's AI industry to advance top-end chips

AI Summary

AMD is investing $10 billion in Taiwan to enhance AI chip manufacturing and packaging.

#GPU #Funding #AI Startup

0

30%

33

Business impact20%0

Novelty (recency)10%97

≥75 high · 50–74 medium · <50 low

Why Featured

AMD's 256-core EPYC Venice chip's 70% performance leap on 2nm technology signals a new era for high-performance computing, crucial for developers and PMs optimizing resource-intensive applications.