Summary

• New AMD Ryzen processors offer significant gains over Intel, especially in terms of performance and efficiency.
• Utilizing Zen 5 architecture on advanced process nodes, AMD's Ryzen 9000 series impresses with powerful specifications.
• AMD introduces new 800-series chipsets with DDR5-8000 support and real-time memory overclocking for enhanced performance.

AMD held an event called Zen 5 Tech Day, which allowed the company to showcase in-depth details about the brand’s upcoming silicon. Zen 5 will be powering the next generation of AMD processors and banchmarks have been released by the company that puts the new chips against Apple, Intel, and Qualcomm processors. The new Zen 5 details were joined by the upcoming motherboard chipsets, an all-new RDNA 3.5 GPU, and XDNA 2 NPUs.

Showing off the new AMD Ryzen 9000 CPUs

The AMD Ryzen 9000 series of processors, codenamed Granite Ridge, rock a new microarchitecture with a reported 16% increase in instructions-per-cycle (IPC). This is important for generational releases since it provides an idea as to how much of an improvement the new processors are compared to existing chips. The new Zen 5 architecture will power processors on 4nm and 3nm process nodes. We’ve already covered the new processors, but here’s a quick refresher on what AMD will be launching.

All four processors support DDR5-5600 RAM as standard, though you can be sure these chips will happily run with EXPO profiles enabled. AMD shared official benchmark data for the new processors, though we’d hold off on reading too much into the numbers before our own testing. To put it into perspective, however, AMD is looking at considerable gains with the 9000 series over Intel. Another area AMD is expected to do well with is efficiency. Intel continues to struggle to keep power and heat down without sacrificing performance. Its latest 14th-gen chips have encountered stability issues and things are only set to worsen if Intel is unable to step up its game and keep up with AMD.

The flagship Ryzen 9 9950X draws a maximum of 230W, compared to the 14900K which can easily surpass 300W. It wasn’t just Intel that AMD compared its new processors against. Gaming was high on the list and the Ryzen 7 9700X was put up against one of the best Zen 3 chips for gaming, the mighty Ryzen 7 5800X3D. Incredibly, the 9700X was shown to be around 12% faster than the 5800X3D for 1080p gaming, which is simply not possible with the AMD Ryzen 7000 series, unless buying a dedicated X3D chip.

Diving into the Zen 5 architecture

So, what’s powering all these new processors and how has AMD managed to squeeze out around 16% improvement over the previous generation? It all boils down to the Zen 5 architecture and TSMC’s N4P node, an upgrade to the manufacturer’s standard 4nm node, which was essentially an offshoot of its 5nm line-up. (Don’t worry, it’s not quite as confusing as Intel’s node generations and naming.) As reported by Tom’s Hardware, this N4P node is where the bulk of the improvements can be found with an 11% performance boost, 22% better power efficiency, and a 6% higher transistor density, compared to N5.

The process node improvements allowed AMD to dial back the TDP slightly yet showed the Ryzen 9000 series processors running at lower temperatures when set to the same TDP. Using resource-intensive apps and games is when the CPU produces the most heat. It's inevitable when drawing more power through the motherboard socket. AMD and its partner TSMC can only do so much to battle against physics and efficiency is key when attempting to get as much performance out of a component without increasing operating temperatures. That's where TSMC's N4P node and AMD's Zen 5 architecture come into play.

Speaking of temperatures, AMD engineers went into some detail about improvements made to the chip design to combat hotspots, and the temperature sensors were moved to more optimal locations to work better with a smarter firmware control algorithm. All this results in tighter control for clock speeds and temperature readings for better overall performance. And if you're not into overclocking or pushing the chips to their limits, you can expect to experience a cooler and quieter system.

As mentioned above, Zen 5 is set to be the foundation of more than one generation of microarchitectures and be used for processors on TSMC's 4nm and 3nm process nodes. A similar core compute die (CCD) and input/output die (IOD) configuration is used with basic graphics support and connectivity. Interestingly, AMD is moving to a slight hybrid approach with its core design. Intel has "normal" P-cores and slower E-cores that are completely different and are designed for separate tasks, although they can be used together.

AMD is using full-size Zen 5 cores and slightly smaller Zen 5c cores. Unlike Intel, AMD uses the same microarchitecture for both the Zen 5 and Zen 5c cores, so you can expect to see the same feature set for all cores on the chip. These Zen 5c cores will operate at slower clock speeds, however, and provide weaker performance at peak power draw, but they do allow AMD to make use of the free space for GPU and NPU computing, making the Zen 5 processors more versatile.

Each core on the chip will have its own L1 and L2 cache with the 16MB of L3 cache split into two 8MB slices, one for Zen 5 cores and the other for Zen 5c cores. This does introduce some minor latency due to the caches having to communicate without one another but AMD states this won't have any impact on performance. Scheduling mechanisms will be used to handle workloads across the different core types, ensuring background tasks are sent to 5c cores and high-latency transfers occur as infrequently as possible.

The front-end design has been tweaked to improve fetch, decode, and dispatch elements for feeding a wider execution engine. AMD states this will lead to generational gaming performance improvements, thanks to the doubling of the data bandwidth between L2 and L1 caches and the L1 cache to the floating point unit. This is the first time AMD has widened the Zen execution engine to support up to eight instructions per cycle, which helps with the overall IPC gains the company showcased at this event.

AI was also present

AMD couldn’t have held an event without at least mentioning AI in today’s climate and the company failed to disappoint those obsessed with the terminology. Benchmarks were shared highlighting processor support for the AI-optimized instruction set VNNI. The Ryzen 9 9900X beat the Intel Core i9-14900K but this doesn’t mean much for the average PC user. What was interesting was the better performance running an AI model on multiple GPUs.

We've already covered the Ryzen AI 300 series, so be sure to check our extensive coverage on AMD's AI chips.

New 800-series chipsets for new CPUs

AMD won the hearts and minds of PC owners with its AM4 platform, which launched with the original Ryzen 1000 series in 2017. For AM5, which launched with the AMD Ryzen 7000 series, the company plans to offer support through 2027 at the earliest and the new X870 and X870E chipsets have already been showcased at Computex. Although the new 9000 series chips will work with older motherboards, the new 800-series motherboards will have USB 4.0 and PCIe 5.0 for GPUs and storage as standard.

Overclocking is thrown around almost as much as AI these days and the X800 series will not disappoint. AMD states they will be able to support up to DDR5-8000, which is rapid for system memory. The new chips will introduce real-time memory overclocking too, making the Ryzne Master app even more useful for those with DIY PC builds. PBO will also be able to take advantage of the lower TDP range for better gains when paired with adequate CPU cooling. This is something Intel has had to scale back, especially with its Intel Core i9 range due to power and temperature constraints.

Not everyone has the money to cover the cost of an X800 motherboard, which is where the newly announced B840 chipset comes into play, sitting just below the B850. Interestingly, this B840 chipset offers memory overclocking (both manual and using profiles) but not CPU overclocking. You can think of it as a slightly beefed chipset to offer more than the budget-friendly A800 series, which I fully expect to see announced at some point. As well as the CPU overclocking restriction, the B840 chipset will only have a single PCIe 3.0 x16 connection.

The new motherboards will not likely launch with the Ryzen 9000 series, set to arrive at the end of July. Pricing is yet to be confirmed with AMD for the new chips, though we expect them to be roughly in line with previous generation SKUs.