The announcements around high-performance computing and data center upgrades were made Wednesday during the Tech World conference.
Lenovo announced two partnerships at its Tech World conference Wednesday. The first is a high-performance computing cluster in film studio DreamWorks Animation's data center. The second is a collaboration with SAP HANA Enterprise Cloud customer edition.
The business of animation
DreamWorks found itself needing to update its legacy data center earlier this year. Producing a computer-generated animated feature typically takes four years, with hundreds of artists and engineers working in tandem to create half a billion digital files that require 200 million compute hours to render—which is more than 22,000 compute years, Lenovo said. "It's a scale of heavy computational loading and processing not unlike the supercomputing needs of researchers,'' the company said.
SEE: Kubernetes security guide (free PDF) (TechRepublic)
Designing and installing a high-performance computing cluster at the height of a global pandemic is a considerable challenge. Lenovo navigated the supply chain and collaborated closely with the studio.
Today, DreamWorks Animation's data center is equipped with the Lenovo Neptune liquid cooling technology to support the studio's passion for producing bigger, bolder films.
"I was joking that I couldn't buy a roll of toilet paper during the pandemic, but I could buy and install a supercomputer," said Skottie Miller, fellow, systems architecture, DreamWorks Animation, in a statement.
The Lenovo Neptune liquid cooling system harnesses water from existing sources to cut power consumption by a third, while allowing more computing power to be packed into the walls of the legacy data center, according to the computer company.
Additionally, the studio's logistics team leveraged Lenovo's global supply chain reach to pre-order components with long lead times, staged them in Europe until they could be shipped, and worked with suppliers worldwide to provide the systems and synchronize their arrival, according to DreamWorks Animation.
"It was a beautifully orchestrated logistical masterpiece," Miller added.
SEE: MSP best practices: Server deployment checklist (TechRepublic Premium)
Lenovo said partnering with DreamWorks Animation offers a stage to showcase what high-performance computing can achieve for industries outside scientific research, especially when paired with the right expertise and support.
"The data center really is the heart of our environment," said Jeff Wike, chief technology officer at DreamWorks Animation, in a statement. "As it beats and as it grows, it has to support all these different creative and operational ambitions."
SAP HANA Enterprise Cloud customer edition will now be delivered on-premises in the customer's data center, according to Wednesday's announcement. It will leverage Lenovo TruScale Infrastructure Services and Lenovo ThinkSystem and ThinkAgile servers and storage, which are SAP HANA-certified and supported, Lenovo said.
"It is a low-risk, turn-key offering that enables customers to keep their SAP software landscape and data on-premises while gaining the benefits of a private-cloud experience," Lenovo said.
SEE: Pro tips: Ubuntu 20.04 (free PDF) (TechRepublic)
Lenovo's TruScale Infrastructure Services is an example of a consumption model that can help mitigate financial challenges when scaling up computing footprint, Lenovo said. It also plays a role in enabling flexible consumption models for enterprise customers so that SAP can bring the cloud to the customer, Lenovo said.
This is one way organizations can accelerate and optimize data management capabilities to enable actionable enterprise intelligence, deliver faster insights leveraging real-time analytics, and democratize the power of artificial intelligence (AI) to make better decisions and gain competitive advantage with insights, Lenovo said.
Data is no longer just being processed within a traditional data center, the company said. Data is being created at multiple access points, and the latest technology innovations are now allowing users to do more with their data, and both process and analyze it at the edge and even within the cloud.
"This trend shows that the industry is going to continue to need to evolve and find a smart way forward when it comes to leveraging [customer] data to deliver improved results,'' Lenovo said.
One proven technique uses high performance data analytics (HPDA) to achieve real-time results. HPDA is the convergence of big data and high-performance computing. Traditional big data analytics engines, such as Apache Hadoop and Apache Spark, store and manage large amounts of unstructured data that can be mined for trends and insights, Lenovo said.
However, the speed and latency requirements of real-time analytics creates significant challenges for traditional big data systems.
The challenge for customers running these workloads, is that traditional scale-out computing is not cost-effective, nor does it provide the performance needed to analyze data in real time, according to the company.
"Customers with common data center platforms typically must make trade-offs between storage, memory, and compute performance—and then decide which combination best suits their specific workload needs,'' Lenovo said. "Running these compute-intensive workloads often not only requires the performance of HPC, but also demands the level of storage and memory capacity suited for big data."
Lenovo said the mission-critical systems it is designing will combine processing capacity, storage, and memory into a single machine. The goal is to enable users to run and analyze massive data sets across the system memory while minimizing latency challenges, the company said.
- How to become a database administrator: A cheat sheet (TechRepublic)
- Hybrid cloud: A guide for IT pros (free PDF) (TechRepublic)
- IT Data Center Green Energy Policy (TechRepublic Premium)
- How hyperscale data centers are reshaping all of IT (ZDNet)
- Best cloud services for small businesses (CNET)
- DevOps: More must-read coverage (TechRepublic on Flipboard)