Summary: AMD's upcoming Zen architectures, including Zen 5 , and Zen6, offer an exciting glimpse into the future with anticipated IPC improvements, supported features, and core counts.
- 10-15% increase in IPC with Zen5
- Potential for 16-core complex with Zen5c
- 10% increase in IPC with Zen6
In an unexpected turn of events, Moore’s Law is Dead channel has shared some intriguing information about AMD’s upcoming Zen architectures. These details were extracted from an internal presentation that was not meant for public consumption, shedding light on anticipated IPC improvements, supported features, and core counts.
It’s important to note that these microarchitectures encompass a wide range of products, including both data center and consumer-oriented series. Therefore, the release timelines may not align solely with AMD’s plans for Ryzen 8000 and beyond, but also take into account considerations for EPYC products.
Nirvana Zen 5 , (1H 2024)
The leaked slides reveal the existence of Nirvana (Zen5), a 4nm/3nm microarchitecture intended for the Ryzen 8000 series. According to the information provided, it is expected to offer a 10 to 15% increase in IPC. However, it’s worth noting that this figure is still subject to verification by retail silicon. The slides also mention a 48K data cache, 8 wide dispatches, 6 ALUs, FP-512 variants, and a new low power core option.
One particularly interesting aspect is the mention of a 16-core complex. This could potentially be an option exclusively using Zen5c variants. Additionally, the Strix Point APU is expected to utilize both sub-architectures within a single die. This means that gamers on the AM5 platform might see designs featuring up to 16-core Zen 5 , or 32-core Zen5c, or a combination of both.
Morpheus Zen 6 , (2H 2025)
Moving on to Zen6, codenamed Morpheus, it is anticipated to utilize 3nm and 2nm process technology. AMD aims to achieve a 10% increase in IPC over Nirvana with this microarchitecture. Notably, AMD plans to introduce FP16 instruction for AI/ML algorithms acceleration, as well as a new memory profiler. The core count is expected to be increased to 32, which likely refers to Zen6c rather than Zen6.
According to the leak, Zen 6 , might feature a chip layout redesign similar to Zen2, along with new packaging techniques. While not confirmed, there are speculations that AMD might stack CCDs on top of the IOD (input/output interface die) for Zen6. This would mark a significant departure from AMD’s traditional disaggregated chiplet design approach. However, it remains to be seen whether Zen 6 , will utilize the AM5 socket.
These leaked details offer an exciting glimpse into the future of AMD’s Zen architectures. As always, it’s important to approach such leaks with caution, as plans can change over time. Nonetheless, these insights provide tech enthusiasts with plenty to speculate and look forward to in the coming years.
Source: Moore’s Law Is Dead (VIA YouTube)
About AMD: AMD, a large player in the semiconductor industry is known for its powerful processors and graphic solutions, AMD has consistently pushed the boundaries of performance, efficiency, and user experience. With a customer-centric approach, the company has cultivated a reputation for delivering high-performance solutions that cater to the needs of gamers, professionals, and general users. AMD's Ryzen series of processors have redefined the landscape of desktop and laptop computing, offering impressive multi-core performance and competitive pricing that has challenged the dominance of its competitors. Complementing its processor expertise, AMD's Radeon graphics cards have also earned accolades for their efficiency and exceptional graphical capabilities, making them a favored choice among gamers and content creators. The company's commitment to innovation and technology continues to shape the client computing landscape, providing users with powerful tools to fuel their digital endeavors.AMD Website: https://www.amd.com/
AMD LinkedIn: https://www.linkedin.com/company/amd/
AM5: Socket AM5 (LGA 1718) is a zero insertion force flip-chip land grid array (LGA) CPU socket designed by Advanced Micro Devices, that is used for AMD Ryzen microprocessors starting with the Zen 4 microarchitecture. AM5 replaces the Socket AM4 and is AMD's first LGA socket designed for mainstream, non-enthusiast CPUs.
APU: An APU, or Accelerated Processing Unit, is a type of processor that combines a CPU and a GPU on a single chip. This type of processor is becoming increasingly popular in the computer industry due to its ability to provide both computing and graphics processing power in a single package. APUs are used in a variety of applications, from gaming PCs to high-end workstations. They are also used in embedded systems, such as those found in smartphones and tablets. The combination of CPU and GPU on a single chip allows for more efficient power consumption and better performance than traditional CPUs. Additionally, APUs are often used in conjunction with other components, such as RAM and storage, to create powerful and efficient systems.
chiplet: Chiplets are a new type of technology that is revolutionizing the computer industry. They are small, modular components that can be used to build powerful computing systems. Chiplets are designed to be used in combination with other components, such as processors, memory, and storage, to create a complete system. This allows for more efficient and cost-effective production of computers, as well as more powerful and versatile systems. Chiplets can be used to create powerful gaming PCs, high-end workstations, and even supercomputers. They are also being used in the development of artificial intelligence and machine learning applications. Chiplets are an exciting new technology that is changing the way we build and use computers.
EPYC: EPYC is a technology designed by computer chip manufacturer AMD for use in the server and data center industry. It was introduced in June 2017 and features an innovative design to improve performance and power efficiency. EPYC processor technology is based on an innovative 14nm processor architecture, allowing up to 32 high-performance cores in a single socket. This allows for more efficient processing power, increased memory bandwidth, and greater compute density. EPYC is now widely used in the data center and cloud computing industry and provides benefits such as greater scalability, increased resource efficiency, and advanced virtualization capabilities. Additionally, EPYC technology is used in data intensive servers like server farms, gaming, and virtualization platforms. EPYC ensures that even with large deployments in multi-processor environments, power consumption and performance levels are optimized to ensure maximum efficiency.
- CTL introduces Sleek Chromebook NL73 Series: A Perfect Blend of Style and Function
- Arctic’s Liquid Freezer III AIO CPU Coolers Receive Impressive Price Reductions
- Crucial introduces high-performance DDR5-6000 memory and T705 M.2 Gen 5 SSD
- ASUS introduces AI-Enabled Vivobook S Series Notebooks, Powered by Intel Core Ultra Processors
- ASUS introduces AI-Enhanced Vivobook S Series Featuring AMD Ryzen 8040 CPUs
- NZXT about to launch the H6 Flow RGB, a HYTE Y60’ish Mid tower case
- HYTE teases the “HYTE Y70 Touch” case with large touch screen
- Intel’s CPU Roadmap: 15th Gen Arrow Lake Arriving Q4 2024, Panther Lake and Nova Lake Follow
- NZXT set to launch a non RGB version of the H6 Flow case
- Tech giants collaborate to establish standardized narrow precision data formats for AI.