1. Home
  2. Companies
  3. Normal Computing
Normal Computing logoNC

Normal Computing

About

Normal Computing develops software and hardware designed to reinvent computing for artificial intelligence by aligning hardware design with the intrinsic properties of physical systems. The company's approach centres on two main offerings: Normal EDA, an AI-accelerated co-design platform for silicon engineering teams, and Normal ASICs, physics-based application-specific integrated circuits built using thermodynamic computing that the company claims deliver up to 1,000 times more intelligence per unit of energy.

The company was founded by former members of Google Brain and Google X, and its team draws from Google Brain, Google X, Meta, Palantir, IBM Research, UC Berkeley, NVIDIA, and Intel. Normal Computing maintains offices in New York City, San Francisco, London, and Copenhagen, and works in partnership with major semiconductor design and manufacturing institutions.

Normal Computing operates at the intersection of hardware design, semiconductor manufacturing, and AI infrastructure. Its technical focus spans AI-accelerated electronic design automation, thermodynamic computing, quantum AI, physics-based computing, and ASIC design. The company has developed machine learning frameworks for probabilistic and quantum AI applications.

Similar companies

Fractile logoFR

Fractile

Fractile is a UK-based semiconductor company building AI acceleration hardware to radically improve frontier model inference performance.

1 job
Eridu AI logoEA

Eridu AI

Silicon Valley hardware startup building infrastructure solutions to accelerate AI model training and inference in data centres.

1 job
Graphcore logoGR

Graphcore

Graphcore is a British semiconductor company that develops Intelligence Processing Units (IPUs) and complete AI compute systems to accelerate machine learning and AI applications.

1 job
Extropic logoEX

Extropic

Extropic builds energy-efficient thermodynamic computing hardware and software for probabilistic AI workloads, leveraging thermal noise for sampling-based computation.

Cerebras Systems logoCS

Cerebras Systems

Cerebras Systems designs wafer-scale AI chips and supercomputers for high-speed machine learning training and inference, serving enterprises, national labs, and healthcare systems.

Etched.ai, Inc. logoEI

Etched.ai, Inc.

Etched builds specialized AI inference chips, including Sohu, the world's first transformer-specific ASIC that delivers 10x faster performance than GPUs.