A translation widget is provided for your convenience to facilitate translation of the English language version of this blog into several languages. If you choose to utilize this automated translation facility, please understand there may be deviations between the automated translation and the original English version. IBM is not responsible for any such automated translation deviations and offers the translated version "AS IS" without warranties of any kind.
IBM POWER9 is here! Announcing the best server for enterprise AI
This is an exciting time for IBM Business Partners and their customers, as IBM unveils its next-generation Power Systems servers incorporating its newly designed POWER9 processor. Built specifically for compute-intensive AI workloads, the new POWER9 systems are capable of improving the training times of deep learning frameworks by nearly 4x,[i] allowing enterprises to build more accurate AI applications, faster.
Say hello to the new POWER9 processor-based server
This is game-changing technology. The new POWER9-based AC922 Power Systems are the first to embed PCI-Express 4.0, next-generation NVIDIA NVLink and OpenCAPI, which combined can accelerate data movement, calculated at 9.5x[ii] faster than PCI-E 3.0-based x86 systems.
The system was designed to drive demonstrable performance improvements across popular AI frameworks such as Chainer, TensorFlow and Caffe, as well as accelerated databases such as Kinetica. As a result, data scientists can build applications faster, ranging from deep learning insights in scientific research to real-time fraud detection and credit risk analysis.
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 the dependability IT requires. IBM Power Systems AC922 offers the fastest way to deploy accelerated databases and deep learning frameworks—with enterprise-class support.
Educate yourself and take this offering to your customers and prospects today
Help your customers access hidden data that will enable them to leap ahead of their competition. Get started by understanding this new trailblazing technology and become that trusted advisor that can help your customers fully exploit artificial intelligence to unleash business insights.
In addition to a rich set of sales enablement assets in IBM SmartSeller, we have two education modules in IBM PartnerWorld University. The first is an introduction to the new IBM Power Systems AC922 with POWER9 processor-based technology. The second takes the discussion to a more technical level. Take the time to familiarize yourself with the next big step forward for enterprise AI, and take this offering out to your customers and prospects.
- Read the press release
- Learn more about the new POWER9 server
- Leverage a rich set of sales resources
Get started today!
2018 will be an exciting year as IBM rolls out the rest of the POWER9 family of Power System servers. Get started today with this first POWER9 offering:
IBM is always looking for new and existing Business Partners interested in helping their customers accelerate their digital transformation. If you have any questions or would like additional information, please do not hesitate to reach out to your IBM representative or to me at [email protected]. You can also let me know what you think by using the comments feature below.
Bob Friske (@bobfriske)
Global Channel Marketing Manager, IBM Power Systems
[i] Results of 3.8x are based on IBM internal measurements running 1,000 iterations of Enlarged GoogleNet model (mini-batch size=5) on Enlarged Imagenet Dataset (2240×2240). Power AC922; 40 cores (2 x 20c chips), POWER9 with NVLink 2.0; 2.25 GHz, 1024 GB memory, 4xTesla V100 GPU; Red Hat Enterprise Linux 7.4 for Power Little Endian (POWER9) with CUDA 9.1/ CUDNN 7. Competitive stack: 2x Xeon E5-2640 v4; 20 cores (2 x 10c chips)/40 threads; Intel Xeon E5-2640 v4; 2.4 GHz; 1024 GB memory, 4xTesla V100 GPU, Ubuntu 16.04 with CUDA .9.0/ CUDNN 7. Software: IBM Caffe with LMS Source code https://github.com/ibmsoe/caffe/tree/master-lms
[ii] POWER9 and next-generation NVIDIA NVLink peak transfer rate is 150 GB/sec = 48 lanes x 3.2265625 GB/sec x 64 bit/66 bit encoding. x86 PCI Express 3.0 (x16) peak transfer rate is 15.75 GB/sec = 16 lanes x 1GB/sec/lane x 128 bit/130 bit encoding.