We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies, revised Privacy Policy and Terms of Service.
You are being directed to ZacksTrade, a division of LBMZ Securities and licensed broker-dealer. ZacksTrade and Zacks.com are separate companies. The web link between the two companies is not a solicitation or offer to invest in a particular security or type of security. ZacksTrade does not endorse or adopt any particular investment strategy, any analyst opinion/rating/report or any approach to evaluating individual securities.
If you wish to go to ZacksTrade, click OK. If you do not, click Cancel.
AMD Expands Portfolio With Latest FPGA-Based Adaptive SoC
Read MoreHide Full Article
Advanced Micro Devices (AMD - Free Report) recently introduced the Versal Premium VP1902 adaptive system-on-chip (SoC), which claims the title of the world’s largest adaptive SoC. This cutting-edge chiplet-based device offers twice the capacity of its predecessor, empowering designers to streamline the verification process of complex semiconductor designs and accelerate the introduction of next-generation technologies to the market.
Growing artificial intelligence (AI) workloads have increased chipmaking complexity. FPGA-based emulation and prototyping have emerged as the gold standard for achieving high-performance silicon verification, enabling developers to begin software development earlier in the design cycle and expedite time-to-market.
Acquisition of Xilinx has helped AMD to consistently push the boundaries of capacity in emulation devices, with each generation nearly doubling its capabilities. The latest VP1902 adaptive SoC offers an impressive 18.5 million logic cells, doubling the programmable logic density of the previous generation Virtex UltraScale+ VU19P FPGA. Furthermore, it boasts twice the aggregate I/O bandwidth, delivering enhanced performance for demanding designs.
Debugging plays a crucial role in pre-silicon verification and concurrent software development, and the VP1902 SoC excels in this aspect as well. Leveraging the Versal architecture, including the programmable network-on-chip, the VP1902 offers up to eight times faster debugging compared to its predecessor, the VU19P FPGA. This remarkable improvement empowers designers to iterate designs quickly and efficiently, keeping programs on schedule and within budget.
Moreover, to further facilitate development on the VP1902 adaptive SoC, AMD provides the Vivado ML design suite. New features like automated design closure assistance, interactive design tuning, remote multi-user real-time debugging, and enhanced back-end compilation features enable faster iteration of IC designs.
The sampling of the AMD Versal Premium VP1902 adaptive SoC will begin in the third quarter of 2023, with production expected in the first half of 2024.
Strong Product Portfolio to Aid AMD’s Prospects
AMD benefits from a strong product portfolio that has helped its shares jump 70.4% year to date, outperforming the Zacks Computer & Technology sector’s return of 33%.
The accelerator is based on AMD CDNA 3 accelerator architecture and supports up to 192 GB of HBM3 memory. NVIDIA’s H100 NVL dual-GPU card offers 188GB of HBM3 memory. Thanks to these features, AMD MI300X can efficiently run large language model training (up 80 billion parameters) and inference for generative AI workloads.
AMD also launched the Instinct platform, which combines eight MI300X accelerators into an industry-standard design to address AI inference and training needs.
AMD is adding two new workload-optimized processors to the fourth Gen EPYC CPU portfolio. The new AMD EPYC 97X4 cloud native-optimized data center CPUs are based on the new Zen 4c core architecture. The company also announced its fourth Gen EPYC processors, with AMD 3D V-Cache technology.
Microsoft (MSFT - Free Report) and Meta Platforms (META - Free Report) announced support for AMD’s fourth Gen EPYC CPU portfolio. AMD also announced the continuation of its relationship with Amazon Web Services.
Microsoft announced the general availability of Azure HBv4 and HX instances, powered by fourth Gen AMD EPYC processors with AMD 3D V-Cache. Meta also stated impressive performance gains with the fourth Gen AMD EPYC 97X4 processors compared with the third Gen AMD EPYC across various workloads.
Moreover, AMD recently expanded its collaboration with Hewlett Packard to support the new modular and multi-protocol storage solution, HPE Alletra Storage MP, with AMD EPYC Embedded Series processors.
Strong adoption of the EPYC processor is expected to boost top-line growth. AMD expects second-quarter 2023 revenues to be $5.3 billion (+/-$300 million), approximately flat sequentially, thanks to higher Client and Data Center segment revenues.
Disclaimer: This article has been written with the assistance of Generative AI. However, the author has reviewed, revised, supplemented, and rewritten parts of this content to ensure its originality and the precision of the incorporated information.
See More Zacks Research for These Tickers
Normally $25 each - click below to receive one report FREE:
Image: Bigstock
AMD Expands Portfolio With Latest FPGA-Based Adaptive SoC
Advanced Micro Devices (AMD - Free Report) recently introduced the Versal Premium VP1902 adaptive system-on-chip (SoC), which claims the title of the world’s largest adaptive SoC. This cutting-edge chiplet-based device offers twice the capacity of its predecessor, empowering designers to streamline the verification process of complex semiconductor designs and accelerate the introduction of next-generation technologies to the market.
Growing artificial intelligence (AI) workloads have increased chipmaking complexity. FPGA-based emulation and prototyping have emerged as the gold standard for achieving high-performance silicon verification, enabling developers to begin software development earlier in the design cycle and expedite time-to-market.
Acquisition of Xilinx has helped AMD to consistently push the boundaries of capacity in emulation devices, with each generation nearly doubling its capabilities. The latest VP1902 adaptive SoC offers an impressive 18.5 million logic cells, doubling the programmable logic density of the previous generation Virtex UltraScale+ VU19P FPGA. Furthermore, it boasts twice the aggregate I/O bandwidth, delivering enhanced performance for demanding designs.
Debugging plays a crucial role in pre-silicon verification and concurrent software development, and the VP1902 SoC excels in this aspect as well. Leveraging the Versal architecture, including the programmable network-on-chip, the VP1902 offers up to eight times faster debugging compared to its predecessor, the VU19P FPGA. This remarkable improvement empowers designers to iterate designs quickly and efficiently, keeping programs on schedule and within budget.
Moreover, to further facilitate development on the VP1902 adaptive SoC, AMD provides the Vivado ML design suite. New features like automated design closure assistance, interactive design tuning, remote multi-user real-time debugging, and enhanced back-end compilation features enable faster iteration of IC designs.
Advanced Micro Devices, Inc. Price and Consensus
Advanced Micro Devices, Inc. price-consensus-chart | Advanced Micro Devices, Inc. Quote
The sampling of the AMD Versal Premium VP1902 adaptive SoC will begin in the third quarter of 2023, with production expected in the first half of 2024.
Strong Product Portfolio to Aid AMD’s Prospects
AMD benefits from a strong product portfolio that has helped its shares jump 70.4% year to date, outperforming the Zacks Computer & Technology sector’s return of 33%.
This Zacks Rank #3 (Hold) company recently announced the launch of the Instinct MI300 Series accelerator family, strengthening its competitive position against NVIDIA (NVDA - Free Report) in the generative AI space. You can see the complete list of today’s Zacks #1 Rank (Strong Buy) stocks here.
The accelerator is based on AMD CDNA 3 accelerator architecture and supports up to 192 GB of HBM3 memory. NVIDIA’s H100 NVL dual-GPU card offers 188GB of HBM3 memory. Thanks to these features, AMD MI300X can efficiently run large language model training (up 80 billion parameters) and inference for generative AI workloads.
AMD also launched the Instinct platform, which combines eight MI300X accelerators into an industry-standard design to address AI inference and training needs.
AMD is adding two new workload-optimized processors to the fourth Gen EPYC CPU portfolio. The new AMD EPYC 97X4 cloud native-optimized data center CPUs are based on the new Zen 4c core architecture. The company also announced its fourth Gen EPYC processors, with AMD 3D V-Cache technology.
Microsoft (MSFT - Free Report) and Meta Platforms (META - Free Report) announced support for AMD’s fourth Gen EPYC CPU portfolio. AMD also announced the continuation of its relationship with Amazon Web Services.
Microsoft announced the general availability of Azure HBv4 and HX instances, powered by fourth Gen AMD EPYC processors with AMD 3D V-Cache. Meta also stated impressive performance gains with the fourth Gen AMD EPYC 97X4 processors compared with the third Gen AMD EPYC across various workloads.
Moreover, AMD recently expanded its collaboration with Hewlett Packard to support the new modular and multi-protocol storage solution, HPE Alletra Storage MP, with AMD EPYC Embedded Series processors.
Strong adoption of the EPYC processor is expected to boost top-line growth. AMD expects second-quarter 2023 revenues to be $5.3 billion (+/-$300 million), approximately flat sequentially, thanks to higher Client and Data Center segment revenues.
Disclaimer: This article has been written with the assistance of Generative AI. However, the author has reviewed, revised, supplemented, and rewritten parts of this content to ensure its originality and the precision of the incorporated information.