Review: Ryzen 7 5800X3D is an interesting technical demo that is hard to recommend

AMD’s AM4 socket has had a long and successful run on the desktop, heralding the Ryzen processor series and helping AMD compete with and outperform Intel’s chips for the first time since the mid-2000s.

The age of the aging socket is coming to an end later this year when the Ryzen 7000 series chips are launched, but AMD is sending it off with one last high-performance processor: the Ryzen 7 5800X3D, which launches on April 20 for $ 449.

AMD uses a unique packaging technology called “3D V-Cache” to triple the amount of L3 cache on the processor, from 32 MB for the standard Ryzen 5800X to a full 96 MB. This new technology feels in some ways like an experiment. Unlike other Ryzen CPUs, the 5800X3D does not offer overclocking or power consumption control, and its clock speeds are a bit bottom than standard 5800X. But AMD says the extra cache allows the 5800X3D to surpass Intel’s fastest CPUs when it comes to gaming.

We have run some tests on the 5800X3D to find its strengths and weaknesses and to get a sense of when you will notice the effect of the extra cache. This is without a doubt one interesting processor, but its pricing and extremely specific performance benefits will limit it to a niche of a niche.

3D V-Cache, in short

Architecturally, nothing about the Zen 3 cores that power the 5800X3D has changed compared to the vanilla 5800X. We’re still talking about an 8-core, 16-thread core complex die (CCD) built on TSMC’s 7 nm process, with its 32 MB L3 cache intact. Just like Apple bulit interconnect support for the M1 Max to support the M1 Ultra, AMD created the Zen 3 to support 3D V-Cache technology when it was ready to ship.

The main change is that AMD and TSMC have reduced the physical height of the CCD array so that a CPU package with 3D V-Cache does not have to be physically higher than a CPU package without. This adjustment maintains compatibility with existing CPU coolers.

The 64 MB extra L3 cache, also built on TSMC’s 7 nm process, is physically stacked on the Zen 3 CCD and connected by direct copper-to-copper bonding. The result is something that the system sees as one large pool of L3 cache, all of which can be treated the same – the 64 MB stacked cache is not an L4 cache, and the 32 MB L3 cache built into the CCD has no performance advantage over the cache stacked on top.

A side effect of this packaging technology is that the 5800X3D runs at a noticeably slower clock speed than the 5800X, and AMD officially allows no overclocking or power adjustments when using the 5800X3D. AMD is pushing the 5800X3D primarily as a gaming processor, and that’s because games take more consistent advantage of having a larger pool of cache to play with. For workloads that care less about cache and more about clock speed – as we will see when we start benchmarking – the 5800X3D can be more slowly than the regular 5800X, which AMD freely admits.

AMD was sorry if we could expect future Zen 3 CPUs with 3D V-Cache enabled, but reading between the lines seems unlikely. 3D V-Cache will be one of the tools in AMD’s toolbox when it comes to enhancing performance for Zen 4 and the first Socket AM5 platforms – along with a 5nm TSMC process, DDR5 support and other architectural enhancements – but I understand it does not feel like the 5800X3D will be followed up with an expanded range of Zen 3-based X3D chips.

AMD says motherboards need a BIOS update to see and use the extra 64 MB cache – look for AGESA version 1.2.0.6b or later in the release notes. Motherboards that support other Ryzen 5000 CPUs will work with the 5800X3D, but they will not be able to access the extra cache, which defeats the purpose of spending more money on the CPU in the first place.