Skip navigation

AMD Business

2 Posts authored by: suresh.gopalakrishnan Employee

Today I am excited to let you know that the AMD EPYC Cloud footprint is increasing globally with Tencent Cloud announcing its 2nd Gen AMD EPYC processor-based “Star Lake” Server Platform at the Tencent Global Digital Ecosystem Conference.

 

Let’s take a closer look at the latest Tencent Cloud announcement and how the 2nd Gen AMD EPYC processor-powered “Star Lake” platform enables Tencent Cloud to achieve their business goals and extend performance & TCO advantages to their customers.

 

Enhanced efficiency and scalable performance for exponentially growing cloud service

Tencent recently became the first Chinese company with more than 1.1 million servers in their network and is one of the fastest growing cloud computing companies in the global IaaS market. This rapid business growth brings new challenges including efficiency improvement and operational cost reduction for the infrastructure. To address these challenges Tencent Cloud developed a technology system from the infrastructure layer to the application layer to enable the next stage of cloud computing growth.

 

Server design, energy efficiency, security features, and reliability have a direct impact on the performance and cost efficiency of Cloud Service Provider offerings. The 2nd Gen AMD EPYC processor based “Star Lake” server platform is Tencent’s first self-designed server developed for the Tencent Cloud environment. Tencent employed many advanced capabilities to improve energy efficiency. For example, according to Tencent, the advanced thermosyphon heat dissipation technology used in “Star Lake” improves maximum load energy efficiency by 50%. The “Star Lake” platform is designed to optimize cloud computing, storage and network requirements to effectively meet 98% of Tencent cloud application scenarios.

 

Liu YuXun, General Manager of Tencent's server supply chain Announcing the AMD EPYC<img src='https://community.amd.com/images/emojis/2122.png' class='jive_emoji'/> Powered Star Lake Server Platform at the Tencent Global Digital Ecosystem Conference, 2019.

Liu YuXun, General Manager of Tencent's server supply chain Announcing the AMD EPYC Powered Star Lake Server Platform at the Tencent Global Digital Ecosystem Conference, 2019.

 

Industry's best single core performance and significant single core TCO savings with 2nd Gen AMD EPYC Processor Powered “Star Lake” server

According to test results presented by Tencent Cloud at the Tencent Global Digital Ecosystem Conference, the “Star Lake” Server with Tencent’s SA 2 instance powered by 2nd Gen AMD EPYC processors achieved the industry’s best single core performance and provides a significant TCO advantage. Tencent Cloud’s results in the image above show that the 2nd Gen AMD EPYC processor-based “Star Lake” server platform improves the overall performance of Tencent’s SA 2 cloud service instances by 35%, including 40% improvement in video processing, 35% improvement in graphics transcoding and 150% improvement in page QPS. This enables Tencent Cloud to provide performance enhancements and cost efficiencies to end customers.

 

You can read more about this at the Tencent Cloud Star Lake Announcement here. It's in Mandarin but can be translated easily!

 

I greatly appreciate the close collaboration and efforts of the Tencent Cloud and AMD teams to bring these innovations to our customers.

We at AMD are proud to be at the forefront of innovation through our collaboration with Microsoft Azure to offer our latest innovations to cloud-based enterprises with the general availability of the new Azure D-series and E-series virtual machines powered by AMD EPYC 7452 Processors. AMD and Microsoft Azure will continue our collaboration to provide guidance on optimization & migration to Azure virtual machines powered by AMD EPYC Processors. AMD and Microsoft are also expanding their partnership with Azure Data Explorer, a leading managed data analytics service for near real-time ingestion and ultra-fast queries.

 

Operational cost efficiency, space optimization, and faster application response times are critical for today’s modern data centers. Architectural innovations in AMD EPYC 7002 Series processors are designed to deliver exceptional performance and scalability to help drive TCO savings for users of a variety of cloud environments including traditional bare metal, software defined, converged and hyper-converged infrastructures in private, public, and hybrid cloud environments.

 

Let’s take a quick look at how Azure and AMD EPYC continue to give customers leadership performance for cloud workloads.

 

Enhanced Performance with Azure D-series virtual machines powered by AMD EPYC

Microsoft considers the Azure Da_v4 and Das_v4-Series the fastest Azure VMs in their class, with a balanced core-to-memory ratio, providing enhanced performance for a wide variety of production workloads. Example use cases include most enterprise-grade applications, relational databases, in-memory caching, and analytics. Microsoft Azure D-series virtual machines are powered by AMD EPYC 7452 Processors and provide up to 96 vCPUs, 384GB DDR4 RAM, and 2.4TB of SSD-based temporary storage per virtual machine.

 

Optimize large in-memory business critical workloads with Microsoft Azure E-Series virtual machines powered by AMD EPYC

Azure Ea_v4 and Eas_v4 VMs offer class-leading performance for memory-intensive applications such as relational databases, caching servers, and in-memory analytics. Powered by AMD EPYC 7452 Processors, the E-Series offer up to 96 vCPUs, up to 672GB DDR4 memory, and 2.4TB SSD-based temporary storage per VM. For database workloads, the Ea-series VMs offers a 22% better performance/dollar than competitive VMs. [i]

 

Power a lightning fast data exploration engine

AMD and Microsoft are expanding their partnership with Azure Data Explorer, a leading managed data analytics service for near real-time ingestion and ultra-fast queries. Azure Data Explorer is using commercially available Azure compute powered by AMD EPYC to deliver groundbreaking and cost-effective interactive analytics.

 

Microsoft Ignite offers a great opportunity to explore innovative ways to build solutions, migrate and manage your infrastructure, using the new Azure D-series and E-series virtual machines powered by AMD EPYC processors.

 

In addition, there are plenty of chances to learning the latest skills from technology leaders and industry users shaping the future of cloud. AMD is hosting a technical breakout session (BRK1114: “Turbocharge your infrastructure with AMD EPYC”) on Thursday, November 7 at 11:30AM-12:15PM in OCCC W208. You can also come by meeting room MR-32, Sponsor Rooms B in the Partner Solution Zone for a deeper dive into our innovative technologies or join us at Booth # 249 to experience solution demos and interact with AMD experts.

 

You can also read more about the new Azure VMs on the Microsoft blog, here.

 

I would like to thank the Microsoft and AMD teams who partnered to bring these innovations to our customers.

 

[i] "Results as of 10-28-2019 using MS SQL Server 2019. Comparison based on internal testing of HammerDB TPCC/OLTP workload. Azure E16asv4 virtual machine generated a result of 600K transactions/minute and costs $0.5301/hour based on three year reserve pricing in US East with RHEL operating system. Pricing found at https://azure.microsoft.com/en-us/pricing/details/virtual-machines/red-hat/. AWS r5.4xlarge virtual machine generated a result of 545K transactions/minute and costs $0.587/hour based on effective hourly 3-year reserve pricing in US East region with RHEL operating system. Pricing found at https://aws.amazon.com/ec2/pricing/reserved-instances/pricing/ ROM-340