cancel
Showing results for 
Search instead for 
Did you mean: 

AMD EPYC for Big Data Analytics Support Continues to Grow

raghu_nambiar
0 0 2,252

We just celebrated the one year anniversary of the introduction of the AMD EPYC processor. As exciting as it is to look back, in this industry we must continue to look forward.

The world is undergoing unprecedented change driven by technology advances that are connecting billions of people to the internet and to each other, creating enormous amounts of data in the process. These connections and data represent an opportunity for companies to improve their business, create new revenue streams, even invent whole new models to solve the world’s most challenging problems.

Whole industries are being transformed as state-of-the-art software running on innovative processors demonstrate both the collective and personalized power of analytics harnessing big data. Healthcare systems that leverage the totality of medical data for personalized diagnosis; recommendation systems for targeted marketing to better serve the customer; transportation systems that reduce traffic and improve routing are just a few examples. There are many more: education, smart cities, genomics, drug discovery, energy efficiency, safety, security, etc.

Many of these systems use services that are now easily accessible to anyone through cloud providers. These providers run huge storage and server farms all built on a foundation of massive compute power with the flexibility to handle a wide variety of workloads.

The revolutionary AMD EPYC processor has gained significant momentum in the industry this year. It is truly exciting to see it being adopted by major server vendors and cloud service providers. With its high core count, large memory capacity and memory bandwidth, and vast I/O density, AMD EPYC is helping customers meet their performance needs without breaking the bank. By offering a choice in x86 architecture, AMD EPYC provides the flexibility, performance and security for the evolving needs of modern data center applications translating directly to more performance per dollar.

Partnerships are critical to bringing the potential of EPYC to anyone who wants to leverage its unique blend of performance and features. Big Data Analytics (BDA) are now commonly used on-premise, in the cloud, and in hybrid environments. An integral part of BDA is the Hadoop ecosystem.  At AMD, we’ve been working diligently to expand our software ecosystem partnerships with the industry leaders in this space: Cloudera, Hortonworks, MapR and Transwarp. Today, we are focusing on partnerships and reference designs, both single-socket and dual-socket, with these partners providing the flexibility, performance and scalability needed to meet the requirements of modern data processing.

The “no compromise” single-socket design ensures you are only paying for the processing power the application needs. Single-socket servers support all of the I/O and memory bandwidth available to a dual-socket server without the extra cost. The versatile dual-socket design offers the highest available AMD EPYC core density and memory capacity, enabling our highest performance. Comprehensive offers based on these reference designs will soon be available from our server partners.

The advent of big data has revolutionized analytics and data science by allowing enterprises to store, access and analyze massive amounts of data of almost any type from any source. The AMD EPYC processor family has arrived at the perfect time as the underlying hardware solution to provide the perfect mix of flexibility and scalability of resources. I look forward to continuing to work with our ecosystem partners to bring the AMD EPYC processors to their customers.

About the Author
Raghu Nambiar is the Corporate Vice President of Datacenter Ecosystems and Solutions at AMD. In this role, he leads engineering teams and their collaboration with ecosystem partners. Raghu has more than 20 years of technology industry experience across a number of engineering organizations. He was previously the CTO of the Cisco UCS business and played an instrumental role in accelerating the growth of the Cisco UCS to a top data center compute platform. He has spent his entire career working on software and hardware ecosystems for data centers, both on in research and business use cases.