We’re excited to bring Transform 2022 back in person on July 19 and pretty much July 20-28. Join AI and data leaders for insightful conversations and exciting networking opportunities. Register today†
IBM is looking to grow its enterprise server business with the expansion of its Power10 portfolio announced today.
IBM Power is a RISC (Reduced Instructions Set Computer) based chip architecture that can compete with other chip architectures, including x86 from Intel and AMD. IBM’s Power hardware has been used for decades to run IBM’s AIX Unix operating system, as well as the IBM i operating system once known as the AS/400. In recent years, Power has increasingly been used for Linux and specifically to support Red Hat and the OpenShift Kubernetes platform that enables organizations to run containers and microservices.
The IBM Power10 processor was announced in August 2020, with the first server platform, the E1080 servera year later, in September 2021. Now IBM is expanding its Power10 family with four new systems, including the Power S1014, S1024, S1022 and E1050, which are being positioned by IBM to solve business use cases, including the growing need at machine learning (ML) and artificial intelligence (AI).
What runs on IBM Power servers?
The use of IBM’s Power servers may well shift into an area that Intel still dominates today.
Steve Sibley, vp, IBM Power Product Management, told VentureBeat that approximately 60% of Power workloads currently run on AIX Unix. The IBM i operating system is used for approximately 20% of workloads. Linux makes up the remaining 20% and is on a growth trajectory.
IBM owns Red Hat, whose eponymous Linux operating system is supported on Power, in addition to the OpenShift platform. Sibley noted that IBM has optimized its new Power10 system for Red Hat OpenShift.
“We’ve been able to demonstrate that you can deploy OpenShift on Power for less than half the cost of an Intel stack with OpenShift because of the container density and IBM throughput we have within the system,” Sibley said.
An Inside Look at IBM’s Four New Power Servers
A key feature of the new servers is the ability to access more memory at a higher speed than previous generations of Power servers. The enhanced memory is made possible through support for the Open Memory Interface (OMI) specification that IBM helped develop and is part of the OpenCAPI consortium.
“We have Open Memory Interface technology that provides more bandwidth, but also reliability for the memory,” says Sibley. “Memory is one of the most common areas of failure in a system, especially if you have a lot of it.”
The new servers announced by IBM all use open-source technology OpenBMC project that helps IBM lead. OpenBMC provides secure code to manage the server plinth in an optimized approach for scalability and performance.
E1050
One of the new servers IBM announced today is the E1050, a 4RU sized (4 rack unit) server with 4 CPU sockets, which can be scaled up to 16 TB of memory, enabling large data and memory-intensive operations. workloads can be run.
S1014 and S1024
The S1014 and the S1024 are also both 4RU systems, with the S1014 offering a single CPU socket and the S1024 integrating a two-socket design. The S1014 can scale up to 2TB of memory, while the S1024 supports up to 8TB.
S1022
Rounding out the new services is the S1022, a 1RU server that IBM positions as an ideal platform for OpenShift container-based workloads.
More power for AI and ML
AI and ML workloads are a particularly good use case for all Power10 systems, thanks to optimizations IBM has built into the chip architecture.
Sibley explained that all Power10 chips take advantage of IBM’s Matrix Match Acceleration (MMA) capability. The business use cases that Power10-based servers can help support include organizations looking to build out risk analytics, fraud detection, and AI models for supply chain forecasting.
IBM’s Power10 systems support and are optimized for multiple popular open-source machine learning frameworks, including PyTorch and TensorFlow.
“The way we see AI emerging is that a vast majority of AI in the future will be done on the CPU from an inference standpoint,” Sibley said.
The mission of VentureBeat is a digital city square for technical decision makers to gain knowledge about transformative business technology and transactions. Learn more about membership.