AMD outlines its strategy to drive its next phase of growth

AMD has outlined its strategy to deliver its next phase of growth driven by the company’s expanded portfolio of high-performance and adaptive computing products spanning the data center, embedded, client, and gaming markets.

“From the cloud and PCs to communications and intelligent endpoints, AMD’s high-performance and adaptive computing solutions play an increasingly larger role in shaping the capabilities of nearly every service and product defining the future of computing today,” said Dr. Lisa Su, AMD chair and CEO. “The close of our transformational acquisition of Xilinx and our expanded portfolio of leadership compute engines provide AMD with significant opportunities to deliver continued strong revenue growth with compelling shareholder returns as we capture a larger share of the diverse $300 billion market for our high-performance and adaptive products.”

Technology and Product Portfolio Updates

AMD announced expanded multi-generational CPU core, graphics, and adaptive computing architecture roadmaps including new details on the -

§ “Zen 4” CPU core expected to power the world’s first high-performance 5nm x86 CPUs later this year. “Zen 4” is expected to increase IPC 8%-10% and deliver more than a 25% increase in performance-per-watt and 35% overall performance increase compared to “Zen 3” when running desktop applications.

§ “Zen 5” CPU core planned for 2024, which is built from the ground up to deliver performance and efficiency leadership across a broad range of workloads and features and includes optimizations for AI and machine learning.

§ AMD RDNA 3 gaming architecture that combines a chiplet design, next generation AMD Infinity Cache technology, leading-edge 5nm manufacturing technology, and other enhancements to deliver more than 50% greater performance-per-watt compared to the prior generation.

§ 4th Gen Infinity Architecture that further extends AMD’s leadership modular SoC design approach with a high-speed interconnect, allowing seamless integration of both AMD IP and 3rd party chiplets to enable an entirely new class of high-performance and adaptive processors and providing a custom-ready heterogenous computing platform.

§ AMD CDNA 3 architecture, which combines 5nm chiplets, 3D die stacking, 4th generation Infinity Architecture, next-generation AMD Infinity Cache technology, and HBM memory in a single package with a unified memory programming model. The first AMD CDNA 3 architecture-based products are planned for 2023 and are expected to deliver more than 5X greater performance-per-watt compared to AMD CDNA 2 architecture on AI training workloads.

§ AMD XDNA, the foundational architecture IP from Xilinx that consists of key technologies including the FPGA fabric and AI Engine (AIE). The FPGA fabric combines an adaptive interconnect with FPGA logic and local memory, while the AIE provides a dataflow architecture optimized for high performance and energy efficient AI and signal processing applications. AMD plans to integrate AMD XDNA IP across multiple products in the future, starting with AMD Ryzen processors planned for 2023.

Expanded Data Center Solutions Portfolio

AMD revealed an expanded portfolio of high-performance, next-generation CPUs, accelerators, data processing units (DPUs), and adaptive computing products optimized for multiple workloads, including -

· 4th Gen AMD EPYC processors powered by “Zen 4” and “Zen 4c” cores.

“Genoa” powered by “Zen 4”: On-track to launch in Q4 2022 as the highest performance general purpose server processor available, with the top-of-stack product delivering greater than 75% faster enterprise Java® performance compared to top-of-stack 3rd Gen EPYC processors.

“Bergamo” powered by “Zen 4c”: Expected to be the highest performance server processors for cloud native computing, offering more than double the container density of 3rd Gen EPYC processors at their launch planned for the first half of 2023[i].

“Genoa-X” powered by “Zen 4”: An optimized version of 4th Gen EPYC processors with AMD 3D V-Cache™ technology to enable leadership performance in relational database and technical computing workloads.

"Siena” powered by “Zen 4”: The first AMD EPYC processor optimized for intelligent edge and communications deployments that require higher compute densities in a cost and power optimized platform.

· AMD Instinct MI300 accelerators, the world’s first data center APUs, expected to deliver a greater than 8x increase in AI training performance compared to the AMD Instinct MI200 accelerator. MI300 accelerators leverage a groundbreaking 3D chiplet design combining AMD CDNA 3 GPU, “Zen 4” CPU, cache memory, and HBM chiplets that are designed to provide leadership memory bandwidth and application latency for AI training and HPC workloads.

· AMD Pensando DPUs that combine a robust software stack with “zero trust security” throughout and an industry-leading packet processor to create the world’s most intelligent and performant DPU, which is already deployed at scale across cloud and enterprise customers

· Alveo SmartNICs deployed by hyperscale customers to accelerate custom workloads and extend confidential computing to the networking interface

Accelerating Leadership in Pervasive AI

AMD is uniquely positioned with its broad product portfolio and experience serving diverse embedded markets to help customers develop and deploy applications with multiple forms of AI. The transformative acquisition of Xilinx provides AMD with an unmatched set of hardware and software capabilities, integrating the leadership Xilinx AI Engine (AIE) across AMD Ryzen, AMD EPYC and Xilinx Versal products for small and mid-size AI models to complement next-generation AMD Instinct accelerators and adaptive SoCs, enabling leadership performance on scale-out training and inference workloads.

To unify AI programming tools, AMD also announced a multi-generation Unified AI Software roadmap that will allow AI developers to program across its CPU, GPU, and Adaptive SoC product portfolio from machine learning (ML) frameworks with the same set of tools and pre-optimized models.

Expanding PC Leadership

AMD showcased its leadership in the global PC market, detailing how it continues to deepen OEM partnerships and drive continued growth across premium, gaming, and commercial markets, and provided a preview of its client roadmap over the next several years, including -

· The “Phoenix Point” mobile processor planned for 2023 will bring together the AMD “Zen 4” core architecture with AMD RDNA 3 graphics architecture and AIE, followed by the “Strix Point” processor planned for 2024. “Phoenix Point” innovations include the AIE inference accelerator, image signal processor, advanced display for refresh and response, AMD chiplet architecture, and extreme power management.

· The “Zen 4”-based Ryzen 7000 Series desktop processors, which are expected to deliver faster clock speeds and greater single and multi-threaded performance compared to Ryzen 6000 processors[ii], will be followed by “Zen 5”-based “Granite Ridge” processors.

Driving Graphics Momentum

AMD announced the latest developments designed to continue bringing world-class graphics solutions to customers worldwide, including -

· “Navi 3x” products are expected to launch later this year, built on the next-generation AMD RDNA 3 gaming architecture.

· More than 50 new gaming PC platforms are expected to launch in 2022, elevating gaming to new levels of performance and visual fidelity by combining AMD Radeon RX Series graphics with AMD Ryzen processors.

· AMD expanded its leadership position in the gaming console space with the addition of Valve’s Steam Deck gaming handheld, powered by AMD “Zen 2” architecture- based processors and AMD RDNA 2 architecture-based graphics.

· New growth opportunities in 2022 and beyond, including providing a range of graphics technologies to accelerate next-generation metaverse applications, ranging from 3D content creation beyond games and movies, to cloud gaming and interactivity within metaverse environments.