Peter Hess

Mike Murphy

Kim Martineau

News

Research

Deep Dive

Explainer

The path to more powerful — and efficient — AI systems

Accelerating discoveries with new AI tools, powerful chips — and turkey

Co-packaged optics deliver high-speed connectivity to supercharge generative AI computing

How low-precision computing boosts efficiency — without hurting accuracy

Inside the lab testing some of the world’s most capable AI chips

How John Knickerbocker spent a career cultivating new technologies

How analog in-memory computing could power the AI models of tomorrow

We’re developing new devices and architectures to support the tremendous processing power AI requires to realize its full potential.

AI Hardware

Analog AI: A New Design Paradigm

AI Hardware Center

Semi­conductors

Neuro-inspired AI to optimize learning and computing efficiency of next generation AI.

Neuromorphic Computing

In-memory computing

NeurIPS 2024

IEDM 2024

Edge Computing

Exploratory Science

Hardware Technology

Semiconductors

Quantum

The world is generating reams of data each day, and the AI systems built to make sense of it all constantly need faster and more robust hardware. We’re developing new devices and architectures to support the tremendous processing power AI requires to realize its full potential.

AI has the potential to solve some of the biggest challenges facing myriad industries. At IBM Research, we’re working on semiconductor innovations for the hybrid cloud and AI — foundational hardware technology that we can use to build the next generation of chips to solve those challenges. 

Foundational Hardware Technology

The future of computing lies in the hybrid cloud. We're creating a hybrid data fabric that provides secure,  governed data access from anywhere, enables self-service discovery of the right data at the right time, and takes a holistic view at minimizing total cost of ownership for AI and analytics.

Data Management

We’re driving infrastructure innovations spanning physical infrastructure, operating systems, and software-defined compute, network, and storage. Our goal is to create technologies that improve performance, reliability, security, and ease of operation across hybrid and multi-cloud environments.

Hybrid Cloud Infrastructure

The hybrid cloud is creating new opportunities to transform the way scientific research is done. From access to high-performance infrastructure, to support for multi-cloud deployments and cloud-native technologies like containers and serverless computing, we're driving full-stack innovations to transform R&D.

Hybrid Cloud HPC

A conceptual illustration of in-memory computing. On the left half of the image, a set of line segments are connected by green, gray, black, and yellow points. On the right half, a green circle, divided into four equal sections, overlays a square grid.

AI Hardware

Our work

How analog in-memory computing could power the AI models of tomorrow

How John Knickerbocker spent a career cultivating new technologies

How low-precision computing boosts efficiency — without hurting accuracy

Inside the lab testing some of the world’s most capable AI chips

Co-packaged optics deliver high-speed connectivity to supercharge generative AI computing

Accelerating discoveries with new AI tools, powerful chips — and turkey

Projects

Neuromorphic Computing

In-memory computing

Analog AI: A New Design Paradigm

Publications

Towards Exact Gradient-based Training on Analog In-memory Computing

AIHWKIT-Lightning: A Scalable HW-Aware Training Toolkit for Analog In-Memory Computing

On the role of noise in factorizers for disentangling distributed representations

Cryogenic Analog 1T-ReRAM with Enhanced Dynamic Range and Suppressed Noise for Cold Neural Networks

D2W and W2W Hybrid bonding system with below 2.5 micron pitch for 3D chiplet AI applications

Heterogeneous Embedded Neural Processing Units Utilizing PCM-based Analog In-Memory Computing

AI Hardware Center

Related topics