Monday, January 6th 2025
AMD Launches Ryzen 9 9000X3D Series "Zen 5" Desktop Processors with 3D V-Cache
AMD today expanded its Ryzen 9000X3D line of Socket AM5 desktop processors that combine the "Zen 5" microarchitecture with 3D V-Cache technology, with the introduction of two high core-count models, the Ryzen 9 9950X3D and the Ryzen 9 9900X3D. The 9950X3D is a 16-core/32-thread chip, while the 9900X3D is 12-core/24-thread. These are dual-CCD processors, and much like the Ryzen 9 7000X3D, the 3D V-Cache is only present on one of the two CCDs, while the other is a regular CCD with just the 32 MB on-die L3 cache. There is one key difference, though. Since AMD has redesigned 3D V-Cache for "Zen 5" to be below the CCD and not above, the CCD with it has the same clock speed boosting characteristics as the CCD without 3D V-Cache; and AMD has worked to refine its software-based OS scheduler optimization such that productivity applications favor either of the CCDs, while games stick to the one with 3D V-Cache.
The Ryzen 9 9950X3D comes with a base frequency of 4.30 GHz, and boosts up to 5.70 GHz, with a 170 W TDP. This is much higher than the 5.20 GHz maximum boost frequency of the Ryzen 7 9800X3D, which makes the 9950X3D the company's fastest gaming desktop processor. The Ryzen 9 9900X3D is similarly interesting—you get a base frequency of 4.40 GHz, and 5.50 GHz maximum boost frequency, which is higher than that of the 9800X3D, although the CCD with the 3D V-Cache only has 6 cores. The 9950X3D should hence end up beating the 9800X3D in gaming workloads, while the 9900X3D should be either on par or slightly slower than the 9800X3D at gaming, although faster than any chip from the non-X3D Ryzen 9000 series.AMD claims that the Ryzen 9 9950X3D is on average 8% faster than the 7950X3D, and on average 20% faster than the Intel Core Ultra 9 285K in gaming workloads, tested across 40 games. It's also 13% faster than the 7950X3D at productivity, and 10% faster than the 285K across the same productivity tests. The company hence claims that the 9950X3D will be the "world's best processor" for both gaming and productivity, ceding no ground to Intel. The company made no first-party performance claims for the 9900X3D. AMD says that the Ryzen 9 9950X3D and 9900X3D will be available in Q1 2025.
The Ryzen 9 9950X3D comes with a base frequency of 4.30 GHz, and boosts up to 5.70 GHz, with a 170 W TDP. This is much higher than the 5.20 GHz maximum boost frequency of the Ryzen 7 9800X3D, which makes the 9950X3D the company's fastest gaming desktop processor. The Ryzen 9 9900X3D is similarly interesting—you get a base frequency of 4.40 GHz, and 5.50 GHz maximum boost frequency, which is higher than that of the 9800X3D, although the CCD with the 3D V-Cache only has 6 cores. The 9950X3D should hence end up beating the 9800X3D in gaming workloads, while the 9900X3D should be either on par or slightly slower than the 9800X3D at gaming, although faster than any chip from the non-X3D Ryzen 9000 series.AMD claims that the Ryzen 9 9950X3D is on average 8% faster than the 7950X3D, and on average 20% faster than the Intel Core Ultra 9 285K in gaming workloads, tested across 40 games. It's also 13% faster than the 7950X3D at productivity, and 10% faster than the 285K across the same productivity tests. The company hence claims that the 9950X3D will be the "world's best processor" for both gaming and productivity, ceding no ground to Intel. The company made no first-party performance claims for the 9900X3D. AMD says that the Ryzen 9 9950X3D and 9900X3D will be available in Q1 2025.
63 Comments on AMD Launches Ryzen 9 9000X3D Series "Zen 5" Desktop Processors with 3D V-Cache
I'm quoting myself here :" In gaming, the other ccd is disabled"
If a game for some reason requires more cores, even with this scheduler prioritization it could spill into the 2nd CCD given the x3D ones becomes too busy.
Regardless, even if both CCDs would have 3DCache added, migrating threads would need their data pulled again from RAM which I suspect negates the advantage of 3DVCache. Probably the numbers (which only AMD has) indicated you win more benchmarks if you put a bigger cache on one CCD than if you put a smaller cache on both CCDs.
I guess I was just caught up in the idea of more cache, more better.
In particular "the more cache, the better" was never true. Because the more cache, the higher the latency. Correctly sizing a cache for an architecture is so complicated that, as you can see, landed us with 4 levels of cache, each still able to put more performance on the table. Without the latency problem, we'd have one huge 1st level cache (kidding, that's not possible, for different reasons).
For a naive answer, look here (look past the first couple of paragraphs, they're not a good explanation): electronics.stackexchange.com/a/82883
For a less naive answer, look at the link at the end of the response.