the Azure high performance computing (HPC) Solution empowers silicon design experts by providing them with the infrastructure and tools for chip design, IP design, silicon manufacturing, and silicon supply chain. Cutting-edge technology development requires extreme computing power, and as our customers face additional unique threats and challenges exacerbated by the pandemic, the Azure cloud can solve many of these problems by providing a secure, scalable platform that is designed for HPC was developed. Customers are increasingly using the Azure HPC platform to increase productivity, optimize resources, reduce time-to-market and increase resource allocation. For example, AMD is using the Azure platform in combination with the HBv3 virtual machines to achieve higher quality designs, reduce time to market, and increase capacity by offloading to the cloud.

We recently announced a preview for Azure HBv3 virtual machines, enhanced by 3rd generation AMD EPYCTM Processors with 3D V cache, code name “Milan-X”. These enhancements continue us on our way to becoming the world’s best silicon design platform by improving the performance, scaling efficiency, and cost-effectiveness of a wide variety of storage-performance-bound workloads such as RTL simulation workloads. Customers using Milan-X benefit from up to 60 percent higher performance for RTL simulation, and the upgrade is provided free of charge over the existing HBv3-series VMs and does not require any changes to customer workloads. In addition, all VMs of the HBv3 series worldwide will soon be upgraded with Milan-X processors. For more information, see the Notice and detailed performance content.

In June we have the General availability the FX series virtual machines powered by second generation Intel Xeon scalable processors. These are designed for workloads that require very high single-thread and light-thread performance and are ideal for Electronic Design Automation (EDA). The new virtual machines of the FX series offer up to 19 percent better performance compared to virtual machines of the FSv2 series with 1008 GB RAM (42 GB per physical core), 2 TB connected NVMe SSD, a single core frequency of 4 , 1 GHz, a base frequency of 3.4 GHz and an all-core turbo frequency of 4.0 GHz. In addition, customers who need additional performance per CPU core can turn off Hyper-Threading. Read additional information about the FX series virtual machines.

We’ll be at the Design Automation Conference (DAC) in person and can’t wait to see you there.

Meetings you don’t want to miss

SKYTalk

Monday, December 6th | 1:00 p.m. Pacific Time (PT)
William Chappel, Azure Global
Semiconductors are deeply embedded in every aspect of our lives, and recent security threats and global supply chain challenges have brought the industry into the spotlight. Significant investments are being made by both nation states and the commercial industry to manage supply chain dependencies, maintain integrity, and build safe, collaborative environments to fuel growth. These changes offer unique opportunities for our industry. This talk brings together insights and experiences from government initiatives and Azure’s Special Capabilities and Infrastructure programs to outline how cloud and AI technologies work with tool vendors, fabless semiconductor companies, IP vendors, foundries, device makers, and other stakeholders of the ecosystem can help build a robust, end-to-end, secure silicon supply chain for commercial and government applications that also creates value for their businesses.

Design / IP / Embedded Track (DIET)

Monday, December 6th | 10:30 a.m. Pacific Time (PT)
Moderator: Preeth Chengappa, Senior Director, Semi and EDA, Azure Global

Industry panel: Prashant Varshney, Head of Product, Silicon, Azure Global; Phillip Steinke, Fellow, CAD Infrastructure and Physical Design, AMD; Michael Hale, Senior Infrastructure Architecture, NVIDIA; Derek Magill, CEO and Co-Founder of License Foundry and HPC Solutions Architect at Flux7; Sridhar Panchapakesan, Program Management Director for Cloud Engagements, Synopsys.

Take part in a live panel as experts from Microsoft, NVIDIA, Synopsys, License Foundry, and Flux7 discuss the real benefits and challenges of chip design in the cloud.

Design on Cloud Theater – Azure

Tuesday, December 7th | 10:30 a.m. Pacific Time (PT)
Learn how Microsoft’s silicon organization uses Azure Azure to enable their semiconductor development. We’ll cover how the team uses Azure DevOps capabilities in conjunction with GIT to manage design information and leverage Azure HPC to run their EDA workloads.

At the booth

Visit us at our booth in Design Infrastructure Alley to meet experts from Microsoft, AMD and Pure Storage. Check out the latest Azure HBv3 and Pure Storage FlashBlade hardware in our hardware exhibit.

Visit us for some bite-sized sessions in our mini-theater with speakers from customers and industrial partners such as AMD, ANSYS, Cadence, Pure Storage, Rescale, Siemens EDA and Synopsys.

Time

Monday

Tuesday

10:15 am – 10:30 am

Rescale

11:15 am – 11:30 am

cadence

Table of contents

12:15 pm – 12:30 pm

Siemens

ANSYS

1:15 pm – 1:45 pm

AMD

PureStorage

2:00 pm – 2:30 pm

Pure

AMD

3:15 pm – 3:30 pm

ANSYS

Siemens

4:15 pm – 4:30 pm

Table of contents

cadence

How our customers use Azure

AMD IT satisfies an insatiable appetite for capacity, scalability and innovation with Azure HPC

As a leader in semiconductors, computer processors, and related technologies, AMD has a responsibility to serve our customers, keep pace with the industry, and help set the standard for how servers, computers, and embedded systems work. To maintain its track record, the AMD IT team leveraged Microsoft Azure High-Performance Computing (HPC), HBv3 virtual machines, and other Azure resources to build scalable capacity and streamline the company’s cloud capabilities, accelerating time to market and weeks and even months of delay.

Don’t miss the video that will play on the Microsoft Azure booth.

Learn more

.



Source link

Leave a Reply