amd-details-zen-4-epyc-cpu-and-cdna-3-gpu-roadmaps-for-ai-and-data-center-dominance
If you thought AMD would solely discuss {dollars} and cents at its Financial Analyst Day occasion, assume once more. Sure, AMD CEO Dr. Lisa Su shared loads of information on TAM development alternatives and ongoing investments, nevertheless it’s all predicated on a wide-ranging portfolio of compute and graphics merchandise for each shopper and information heart shoppers. We already lined the buyer aspect yesterday with particulars on RDNA 3 chiplets, 3D V-cache for Zen 4, and Phoenix Point laptop computer chips. In this text, we’ll go over AMDs’ information heart bulletins and claims. Let’s get began.

AMD 4th Gen EPYC Server CPU Roadmap And Performance Claims

Starting with its CPU silicon roadmap, AMD talked about what’s within the pipeline to succeed its third technology EPYC Milan (common objective) and Milan-X (technical) processors. As you possibly can see within the above roadmap, AMD’s 4th gen EPYC household will probably be comprised of Genoa (common objective), Bergamo (cloud native), Genoa-X (technical), and Siena (telecommunications), adopted by its fifth gen EPYC Turin launch in 2024.
Not all of that is new data, as AMD has talked about its Genoa and Bergamo platforms earlier than. Genoa is meant to increase AMD’s lead on the socket stage and per-performance stage. It will characteristic as much as 96 Zen 4 cores in 5nm, help for 12-channel DDR5 reminiscence and PCI Express 5.0, and a brand new CXL interface for intelligent reminiscence expansions.
According to AMD, Genoa is poised to be the highest-performance general-purpose server processor in the marketplace—the corporate claims its top-of-the-stack silicon will ship a larger than 75 % uplift in enterprise Java efficiency in comparison with its prime third gen EPYC processor.
Genoa is on observe to launch within the fourth quarter. Then within the first half of 2023, AMD will launch its Bergamo stack powered by what the corporate is dubbing Zen 4c. Likewise, AMD is pitching Bergamo because the highest-performance server processors for cloud native computing.

Bergamo relies on the Zen 4 ISA, however will throw extra cores and threads at cloud functions. Specifically, Bergamo will max out at 128 cores and 256 threads.
AMD beforehand mentioned Bergamo will stay absolutely software program suitable and make the most of the identical socket platform as Genoa, and help the identical applied sciences (like DDR5 and PCIe 5). However, it’s going to additionally embody a set of cloud enhancements, similar to a density-optimized cache hierarchy and higher energy effectivity for cloud-native workloads.
Looking just a little additional down the road, AMD revealed it’s going to have two different 4th gen EPYC iterations in 2023, these being Genoa-X and Siena. Genoa-X include as much as 96 cores and 192 threads identical to Genoa, and make the most of the identical SP5 socket (LGA 6096), however will characteristic 1GB or extra of L3 cache per socket. Like Milan-X, AMD is focusing on prospects who have to energy by workloads that thrive on L3 cache.
As for Siena, it’s going to wield as much as 64 Zen 4 cores, although past that we don’t have a ton of particulars to share. All we actually know is what’s said within the slide, which is that it’s optimized for performance-per-watt and will probably be pitched as a lower-cost platform for clever edge and telecommunications markets.
Look for extra particulars on Genoa-X and Siena as their respective launches come nearer into view.

AMD Instinct MI300 Fuses Zen 4 CPU Cores With CDNA 3 Graphics

One of the messages AMD delivered robust and clear through the occasion that it is graphics IP is strongly positioned throughout virtually each market section, together with cellular, embedded, consoles, PC, and naturally the info heart. Not solely does this give AMD a broad market to deal with, it additionally permits merchandise that faucet into each its CPU and GPU architectures, as is the case with its upcoming Instinct MI300 based mostly partially on its upcoming 5nm CDNA 3 structure.
The Instinct MI300 is being billed because the world’s first information heart APU. Leveraging what AMD describes as a “groundbreaking 3D chiplet design,” the info heart APU combines CDNA 3 graphics cores with Zen 4 CPU cores on the identical bundle, together with each cache reminiscence and HBM chiplets to spherical issues out.
According to AMD, the web acquire of this mixture is a large eight-fold improve in AI coaching efficiency in comparison with its Instinct MI200 accelerator. Make no mistake, AMD sees itself making a significant splash within the excessive efficiency computing (HPC) market and it is going to be attention-grabbing to see the way it fares towards NVIDIA’s Grace Hopper and Intel’s Falcon Shores produces.
Just as RDNA 3 is coming to ship a brand new technology of desktop and laptop computer graphics options for gaming, CDNA 3 will observe swimsuit within the information heart someday subsequent yr, with AMD promising a five-fold soar in performance-per-watt on AI workloads in comparison with CDNA 2.
CDNA 3 will probably be manufactured on a 5nm course of and make the most of 3D chiplet packaging. It may even mark a shift away from a coherent reminiscence structure to a unified reminiscence APU structure, which guarantees to make it extra environment friendly. Going this route eliminates redundant reminiscence copies by taking away the necessity to copy information from one pool to the opposite.
Finally, AMD talked just a little about XDNA, the foundational structure IP it possesses after buying Xilinix earlier this yr. It consists of key applied sciences, together with the FPGA material 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,” AMD says.
Looking on the sum of all these components, it is clear AMD doesn’t intend to let it is foot off the gasoline pedal. Broadly talking, it has robust roadmaps in place for each shopper and information heart markets, and it is going to be attention-grabbing to see the way it all unfolds.