About Neurophos

Neurophos develops a photonic computing architecture that utilizes ultra-dense optical modulators to achieve 160,000 TOPS at 300 TOPS per watt, significantly outperforming traditional GPUs. This technology addresses the escalating demand for AI compute power by providing a solution that replaces 100 GPUs with a single processor while consuming only 1% of the energy.

```xml <problem> The escalating demands of AI, particularly for large language models, require significant increases in compute power, leading to high costs and unsustainable energy consumption for companies relying on traditional GPUs and TPUs. Scaling these systems faces limitations due to real estate constraints and diminishing returns in energy efficiency. </problem> <solution> Neurophos is developing an optical processing unit (OPU) that leverages photonic computing to achieve substantial performance gains with significantly reduced power consumption. By miniaturizing optical modulators by a factor of 10,000, Neurophos enables a 3D photonic computing architecture that overcomes the limitations of traditional electronic systems. The OPU utilizes optical systolic arrays, where light replaces electrons, eliminating latency issues and enabling clock speeds of 100 GHz or higher. This approach allows a single Neurophos processor to deliver the performance of 100 GPUs while consuming only 1% of the power. </solution> <features> - Ultra-dense optical modulators based on metasurface technology, 8,000 times smaller than standard silicon photonics modulators - Optical systolic arrays that use light for computation, eliminating signal propagation latency - Goodman Engine architecture for purely optical vector-matrix multiplications - Folded design for compact and efficient layout, reducing latency and enhancing scalability - 3D stacking on a standard CMOS chip with dense through-silicon via (TSV) array for high-bandwidth communication - Model-agnostic design that supports multiple numerical formats without retraining </features> <target_audience> The primary target audience includes organizations involved in AI model training and inference, particularly those working with large language models and requiring high compute performance with stringent power constraints. </target_audience> ```

What does Neurophos do?

Where is Neurophos located?

Neurophos is based in Durham, United States.

When was Neurophos founded?

Neurophos was founded in 2020.

How much funding has Neurophos raised?

Neurophos has raised 16800000.

Location

Durham, United States

Founded

2020

Funding

16800000

Employees

16 employees

Major Investors

Gates Frontier Fund

Find Investable Startups and Competitors

Search thousands of startups using natural language

AI voice (2021+)underground pipe robots energy flexibility software

Start Searching

Neurophos

⚠️ AI-generated overview based on web search data – may contain errors, please verify information yourself! You can claim this account with your email domain to make edits.

Executive Summary

neurophos.com 2K+

Crunchbase

Founded 2020 – Durham, United States

Funding

Estimated Funding

$10M+

Major Investors

Gates Frontier Fund

Team (15+)

No team information available.

Company Description

Problem

The escalating demands of AI, particularly for large language models, require significant increases in compute power, leading to high costs and unsustainable energy consumption for companies relying on traditional GPUs and TPUs. Scaling these systems faces limitations due to real estate constraints and diminishing returns in energy efficiency.

Solution

Neurophos is developing an optical processing unit (OPU) that leverages photonic computing to achieve substantial performance gains with significantly reduced power consumption. By miniaturizing optical modulators by a factor of 10,000, Neurophos enables a 3D photonic computing architecture that overcomes the limitations of traditional electronic systems. The OPU utilizes optical systolic arrays, where light replaces electrons, eliminating latency issues and enabling clock speeds of 100 GHz or higher. This approach allows a single Neurophos processor to deliver the performance of 100 GPUs while consuming only 1% of the power.

Features

Ultra-dense optical modulators based on metasurface technology, 8,000 times smaller than standard silicon photonics modulators

Optical systolic arrays that use light for computation, eliminating signal propagation latency

Goodman Engine architecture for purely optical vector-matrix multiplications

Folded design for compact and efficient layout, reducing latency and enhancing scalability

3D stacking on a standard CMOS chip with dense through-silicon via (TSV) array for high-bandwidth communication

Model-agnostic design that supports multiple numerical formats without retraining

Target Audience

The primary target audience includes organizations involved in AI model training and inference, particularly those working with large language models and requiring high compute performance with stringent power constraints.