State-of-the-art I/O and acceleration options

NVIDIA® Next Generation NVLINK™ for 5.6x data throughput vs PCIe Gen3. PCIe Gen 4 delivering 2x PCIe Gen 3 bandwidth.

Unmatched compute performance

4x bandwidth improvement over POWER8 with OpenCAPI and NVLink 2.0 high bandwidth links (25GB/s) for GPU/OpenCAPI Acceleration.

Simplified execution for enterprise AI

AI large model support with 2 TB of coherent memory, GPU to GPU communications, and GPU to CPU communications.

Innovators. Trailblazers. Change makers. Your journey begins with “what if?”

What if you could access hidden data to leap ahead of the competition? What if you could break the barrier of experimentation and fully exploit Artificial Intelligence (AI) to unleash business insights?

From the processor architecture and server hardware to software and services support, we’ve reimagined infrastructure for the AI era.

9.5x

max I/O bandwidth vs x86

2x

high performance cores vs x86

2.6x

more RAM supported vs x86

1.8x

more memory bandwidth vs x86

Say hello to the POWER9 processor

Built from the ground-up for enterprise AI, POWER9 is the only processor with state-of-the-art I/O subsystem technology, including next generation NVIDIA NVLink, PCIe Gen4, and OpenCAPI. These interfaces give POWER9 a memory bandwidth superhighway that gives you more accurate insights, faster.

Meet the best server for enterprise AI

Enterprise AI requires a new breed of servers. Servers that enable the cutting-edge AI innovation data scientists’ desire, with dependability IT requires. IBM Power Systems AC922 offers the fastest way to deploy accelerated databases and deep learning frameworks – with enterprise-class support.

3.7x

Better performance with Chainer

3.8x

Better performance with Caffe

Build an AI foundation for speed and scale

Evolving from compute systems to AI infrastructure requires more than high-performance infrastructure. Co-optimized hardware and software must work for deep learning and AI.

That’s why IBM PowerAI is an enterprise-ready software distribution built on open source.

Experience the power of enterprise AI now

The compute performance behind CORAL Summit supercomputer is now available to the enterprise. Don’t believe us?

This is what 200+ petaflops of high-performance computing and 3 exaflops of AI-as-a-service looks like for the U.S. Department of Energy.

From here to AI – your journey starts now