Thursday, March 26th 2026

AMD Announces Ryzen 9 9950X3D2 Dual Edition Desktop Processor with 192 MB L3 Cache

AMD today launched the Ryzen 9 9950X3D2 Dual Edition Socket AM5 desktop processor. This processor is positioned above the Ryzen 9 9950X3D, and is the much awaited implementation of 3D V-Cache memory on both CCDs (CPU complex dies) of the processor. The 16-core/32-thread processor is based on the Zen 5 microarchitecture, and features a total of 192 MB of shared L3 cache—that's 32 MB of on-die L3 cache plus 64 MB of 3D V-Cache that's contiguous with it, across both CCDs. This enables the maximum possible gaming performance, as worker threads of the game can be located on either of the two CCDs and benefit from large last-level cache. The base clock is 4.30 GHz, with a boost clock of 5.60 GHz—100 MHz lower boost than the 9950X3D, and the same clocks as the 9850X3D—no word if these are the same for each CCD.

The AMD Ryzen 9 9950X3D2 Dual Edition is positioned to be a 16-core Zen 5 Flagship part, and to ensure the chip has not just the most cache, but also the highest possible clock speeds in the series, and retain its overclocking capabilities, AMD expanded the TDP of the processor to 200 W—the highest ever for an AMD Ryzen part. AMD is offering gaming performance rivaling its latest Ryzen 7 9850X3D part, but with significantly improved productivity performance in applications with large cached data-sets, such as software development, AI training and inferencing, and video production. The company's first-party productivity benchmarks show the 9950X3D2 post significant single-digit percentage gains over the 9950X3D. AMD did not announce price, but said that the 9950X3D2 Dual Edition will be available from April 22, 2026.
Known specifications of the Ryzen 9 9950X3D2 Dual Edition follow.

Add your own comment

149 Comments on AMD Announces Ryzen 9 9950X3D2 Dual Edition Desktop Processor with 192 MB L3 Cache

#101
AVATARAT
igormpI don't think this will happen. Scheduling should still attempt to group threads belonging to the same process into the same, higher-clocking CCD, and it doesn't really matter if both have the extra cache now. Even on the regular 9950x the best CCD clocks ~300MHz higher than the 2nd CCD by default, I don't think this would change with this new version. The 9950x3D has a 200MHz delta, so at best I could see the gap being a bit smaller compared to the non-3D version.
The scheduling module simply follows certain rules.
CCD2 operates with higher latency, and the additional frequency sometimes helps maintain synchronization with CCD1. It remains to be seen whether the cache and the lower frequency will work well.
We’re looking forward to seeing how the additional secondary cache will help when moving low-priority threads from one CCD core to the next CCD. For now, we just have to wait for the data to be copied.
Posted on Reply
#102
efikkan
HBSoundI am very serious, and I have no reason I want to pay for somethig unless needed. But I also realize a lot of people know a lot more than I do, so someone could offer some information to confirm why wait? Or a great ready why? I do a lot of CAD/3D/Revit work, so I am seeking anything that could make a real-world difference and anything that offers real speed in what I do.
For any upgrade to be worthwhile, it needs to be a significant upgrade, that rarely happens even jumping one generation, let alone within the same generation. There would be no reason to upgrade unless you had a lower tier CPU as a "placeholder". With the two models you mentioned specifically, the differences will in most cases be unnoticeable, only a few select workloads will benefit from the extra cache, and others will likely lose a little performance. Save your precious money and buy a worthy upgrade when it's time.

Since you are targeting "workstation" use, generic or synthetic performance is pretty irrelevant, you should seek benchmarks as close to your workflow as possible. If your current performance is unsatisfiable, you should try to find out what's bottlenecking you. If it happens to be either core count or memory bandwidth then the solution is something like Threadripper. If on the other hand it's very sensitive to peak core speed, then perhaps the other team is faster, which will be especially interesting once Nova Lake and Zen 6 arrives. Or it may not be the CPU at all.
A Computer GuyOr in the case if you have X3D wait for Zen6 X3D.
Only if the cache makes a meaningful difference for his particular workload, which is generally rare for "workstation" tasks. If not, then even regular Zen 6 should be on the table.
Posted on Reply
#103
evernessince
usinameI literally said this "in the best case scenario will match the single CCD X3D parts"
Its not the miracle the people expected, it was obvious that adding cache to the second CCD, won't make it faster than the single CCD, just like 9700X and 9950X are within 1-2% difference. Now will be the same with 3D cache on the both CCDs vs single one.
Preceded by this:
usinameAs expected no gaming improvement, in the best case scenario will match the single CCD X3D parts
So how can something have no gaming improvement, as you claimed, while simultaneously being 7.1% faster? You cannot have "literary said this" when referencing my 7.1% performance increase because you clearly said there was no gaming improvement.

The article isn't stating it matches regular X3D parts but the newer OC'd X3D parts.

It is EXACTLY what people who were pushing for 2 X3D cache dies wanted. It completely erases the disadvantage of having that second CCD.
Posted on Reply
#104
HCT3000
OnasiThat’s cool, I suppose, as a “no compromise” CPU. Won’t suffer from the “use GamBar” nonsense as well, I would assume. But I don’t think it’s of much use for the general audience or even enthusiasts. At least it isn’t a total waste of sand like the 9850X3D.
That's been fixed for a good while now, no need for the Game bar any longer.
Panther_SeraphinPeople are stating it will need the game bar.

I don't think it will. Game bar was there to make sure that the gaming threads prioritised the X3D equipped CCD and not the non X3D ccd.

Normal scheduler should make sure that relevant data stays within the same ccd as that is the default behaviour for all of Zen since Zen 2 IIRC.
Correct, the game bar is not needed any longer, Microsoft and AMD worked together to fix this quite some time ago.
Posted on Reply
#105
harm9963
Can't wait for reviews, only interested in 4K with a Rtx4090 or 5090 !
Posted on Reply
#106
A Computer Guy
harm9963Can't wait for reviews, only interested in 4K with a Rtx4090 or 5090 !
Aren't those GPU's already bottlenecked at 4K?
Posted on Reply
#107
Tyler-98-W68
harm9963Can't wait for reviews, only interested in 4K with a Rtx4090 or 5090 !
Prepare to be disappointed. You don't need a 9950 anything to run 4k with a 5090
Posted on Reply
#108
Rulumi
evernessinceSo how can something have no gaming improvement, as you claimed, while simultaneously being 7.1% faster? You cannot have "literary said this" when referencing my 7.1% performance increase because you clearly said there was no gaming improvement.

The article isn't stating it matches regular X3D parts but the newer OC'd X3D parts.

It is EXACTLY what people who were pushing for 2 X3D cache dies wanted. It completely erases the disadvantage of having that second CCD.
It eases scheduling a bit because cache has parity now, but most games still will be kept to only one CCD as most still lose more from the cross CCD latency. The benefit of this kind of product is mostly for other use cases, not for games.
Posted on Reply
#109
Panther_Seraphin
SOME games may benefit from it but far less than what takes advantage of the extra memory on the single X3D ccds
  • First things first, How many games currently out there take advantage of more than 8 cores/16 threads in the first place.
  • How many games perform better on a 9950x than a 9700x currently and for that advantage to NOT be due to the increased clock speed of the CCD.
  • Are developers going to spend the extra time to specifically optimise for the 1% of the 1% who will be using these processrors most likely? I suspect it will be a lot of extra work for very little benefit beyond this small base of users in the short/mid term.
  • How is the extra cache going to be treated by developers?
    Individual cache setups that take full advantage of the extra capcity but may introduce cross CCD communication latency due to poor implementation/cache optimisation.
    Exact copies across the two CCDs to prevent cross CCD transactions? May help those gmaes that utlise more than 8 cores but your limiting the cache effectiveness overall.
Here is a good going over Zen 5 and how gaming works. He even goes through a simulated scenario where he forces cross CCD communication by forcing different threads across the CPU and there was a ~7% drop in performance in doing so.
chipsandcheese.com/p/running-gaming-workloads-through

According to his reporting currently there is very few "natural" scenarios in gaming where cross CCD communication will happen with current Zen 5 parts and here is a really big thing people need to take into consideration

"Cross-CCX transfers account for a negligible portion of L3 miss traffic: sampled latency events at the L3 indicate cross-CCX latency is similar to or slightly better than DRAM latency"

So as it has been suggested in previous posts/articles the main bottleneck for Zens architecture in terms of gaming performance beyond the single CCD is mainly the Infinity fabric bandwidth and latency. X3D minimises this limitation by lowering the need to go out on the IF to Memory etc leading to higher framerates. The ONLY situation currently where a Dual X3D part will benefit vs a single one now is when you have a need for >8 core/16 threads OR and this is a REALLY big OR your game has multiple threads that could take advantage of a larger cache without the need for large interactions between the two, I am thinking of things like world generation and AI NPC logic etc.

This is the reason why in EPYC there are specific parts that utilise 2 IF links between each CCD and the IO Die to maximise the throughput for the CCD in certain use cases.
Posted on Reply
#110
evernessince
RulumiIt eases scheduling a bit because cache has parity now, but most games still will be kept to only one CCD as most still lose more from the cross CCD latency. The benefit of this kind of product is mostly for other use cases, not for games.
Gaming performance being equal to the fastest gaming CPU are the market while also having the fastest multi-threading is the draw. It's not one or the other as you are trying to make it out to be.
Posted on Reply
#111
harm9963
Tyler-98-W68Prepare to be disappointed. You don't need a 9950 anything to run 4k with a 5090
I known that for years ,my RTX 4090 does the heavy lifting at 4K, my 5950X is just fine .
Posted on Reply
#112
damric
Probably going to be expensive as hell, but I want one.
Posted on Reply
#113
AusWolf
evernessinceSo how can something have no gaming improvement, as you claimed, while simultaneously being 7.1% faster? You cannot have "literary said this" when referencing my 7.1% performance increase because you clearly said there was no gaming improvement.

The article isn't stating it matches regular X3D parts but the newer OC'd X3D parts.

It is EXACTLY what people who were pushing for 2 X3D cache dies wanted. It completely erases the disadvantage of having that second CCD.
Keep in mind, this chip has a higher TDP, so presumably, it clocks higher as well.
Posted on Reply
#114
efikkan
Panther_SeraphinAre developers going to spend the extra time to specifically optimise for the 1% of the 1% who will be using these processrors most likely?(1) I suspect it will be a lot of extra work for very little benefit beyond this small base of users in the short/mid term.

How is the extra cache going to be treated by developers?(2)
Individual cache setups that take full advantage of the extra capcity but may introduce cross CCD communication latency due to poor implementation/cache optimisation.
Since there are a lot of misconceptions here, I'll have to explain (2) first;
Developers generally speaking don't "optimize" to use more cache, at least not in the way you expect. There are mainly two types of cache, instruction(code) and data, and the way we optimize for them is a bit different. One key difference between L2 and L3 is that L2 is the cache the CPU front-end is interfacing with, while L3 is just discarded L2 (from all the cores). And while we don't have direct control of any of the caches**, cache optimizing have a primary effect on L2, while the only real way L3 is positively affected is by having L2 fetch less unnecessary data.

Cache optimization for code is primarily in making the code computationally denser and therefore the same code takes up fewer cache lines, this includes avoiding/removing unnecessary function calls results in cache misses. Meanwhile data optimization is mostly about making the data "denser", meaning it's either more compact or you traverse the data in the optimal way, so you need fewer cache lines to read the same amount of data. So in layman's terms, both types of optimization can be viewed as trying to use as little as possible to do a set amount of work. It's not like most people think that the programmer controls what is cached and what is not.

One thing of note is that the chances of a cache hit in L3 is significantly higher for instruction cache vs. data cache, because a instruction cache hit in L3 usually means the code is a little too large and the code is the same when churning through lots of data, while most of the data is switched out. So when we see some games and a few applications very sensitive to L3 cache size, that's actually a sign of the application being badly coded, not a sign of quality. This is the opposite of what those who are not experienced low-level programmers expect.

**) There are prefetch and flush instructions as hints to the CPU frontend, but this is very low-level stuff you'll probably never see in a game engine.

--

So addressing your first question(1), are developers going to "address" this? No, not in the way you think, it's the opposite, meaning they will see less of a need to actually optimize it, since all the "hard core" gamers will be having lots of L3 and will be "suffering" less from unoptimized code. This is actually sometimes the downside of some unbalanced "improvements", especially the ones which "favors" bad design. Don't get me wrong, more L3 is a good thing, but there's a "sweet spot" where going beyond that only helps "bad code", and therefore incentivizes developers to write more bad code.

Let me take a similar situation, this time in software, but it's an underlying API so it affects games. Some years back, there was all this hype about DirectX 12 and Vulkan (and Mantle) lowering overhead, which is a good thing by itself. But then we even got benchmarks to measure draw calls, and developers realized that the reduced cost of bloat means we don't have to prioritize optimizations as much. And we see the results now; many games in the last ~5-8 years are incredibly demanding for both CPU and GPU, while only offering a small step above the previous generation of games in terms of visual fidelity.
Panther_SeraphinExact copies across the two CCDs to prevent cross CCD transactions? May help those gmaes that utlise more than 8 cores but your limiting the cache effectiveness overall.
The cache doesn't really work that way, it's transparent to the code.
So I assume in your scenario you're expecting one or more threads in each CCD to access the same cache line, and that one or more of them will at some point write data to it, then any mechanism (in software or hardware) will have too do some kind of synchronization to keep those up to date. The CPU already have a mechanism to synchronize L1, L2 and L3 on various cores, but I don't see how hardware can duplicate those automatically and still keep them in sync, at least not without creating a penalty for everything.

But if the data isn't changing, or only changing at very specific times (and probably only by one thread), then you can easily do this in software by letting each thread have their own copy of the data.

And while a lot of people are very focused on this problem, I don't think it's that much of a deal as people make it out to be. I believe the proper solution is not to solve this problem, but to avoid it. Any software where you need this level of fine-grained synchronization between cores is never going to scale well. This basically comes down to Amdahl's law; the more synchronization you have, the less scaling you'll have. So if you can't scale it's either you're doing it wrong, or the problem can't scale further.
Panther_SeraphinAccording to his reporting currently there is very few "natural" scenarios in gaming where cross CCD communication will happen with current Zen 5 parts and here is a really big thing people need to take into consideration
I agree.
And if there is a game which is an edge case, then customers should petition that developer to fix their game.
Panther_SeraphinThe ONLY situation currently where a Dual X3D part will benefit vs a single one now is when you have a need for >8 core/16 threads OR and this is a REALLY big OR your game has multiple threads that could take advantage of a larger cache without the need for large interactions between the two, I am thinking of things like world generation and AI NPC logic etc.

This is the reason why in EPYC there are specific parts that utilise 2 IF links between each CCD and the IO Die to maximise the throughput for the CCD in certain use cases.
Probably more like games which are incredibly bloated. And contrary to some, I think there will be a few games where the addition of the L3 offsets the disadvantage of the dual X3D dies, but that doesn't make it sensible.

It's very relevant for some server loads, especially heavy enterprise Java code, which is in nature incredibly bloated.
Posted on Reply
#115
AusWolf
Panther_SeraphinFirst things first, How many games currently out there take advantage of more than 8 cores/16 threads in the first place.
During loading screens or shader pre-caching, quite many. During the game running, probably not one.
Panther_SeraphinAre developers going to spend the extra time to specifically optimise for the 1% of the 1% who will be using these processrors most likely? I suspect it will be a lot of extra work for very little benefit beyond this small base of users in the short/mid term.
I've always thought optimisations are necessary for weaker hardware, not stronger.
Panther_SeraphinHow is the extra cache going to be treated by developers?
Individual cache setups that take full advantage of the extra capcity but may introduce cross CCD communication latency due to poor implementation/cache optimisation.
Exact copies across the two CCDs to prevent cross CCD transactions? May help those gmaes that utlise more than 8 cores but your limiting the cache effectiveness overall.
Inter-CCD communication is an issue regardless of cache size. I'm curious how two X3D CCDs help this situation, if at all.
Posted on Reply
#116
_roman_
you can always optimise code, regardless of the architecture.

has this chanced since 1996? a cpu can fetch faster it needed "data" for computation when the cache is bigger. l1 is faster than l2 than l3 and so on. than DRAM than storage. what is done in the cpu itself does not matter. i doubt it has changed. when it is not in l1, it is searched in slower l2 cache, if not than it is searched in slower l3 cache and so on.

note: data is up to discussion, feel free to provide an example with assembler with full explanation whatever. it does not change how the other caches are slower and how the chain of "data" handling is.
efikkanThe cache doesn't really work that way, it's transparent to the code.
that is the point. one is hardware, the other is the compiler generated "machine" code.

i appreciate your efforts in explaining things to the public
efikkanThe CPU already have a mechanism to synchronize L1, L2 and L3 on various cores, but I don't see how hardware can duplicate those automatically and still keep them in sync
maybe i am wrong. what i learnt in 1996, yes 1996, the cpu itself has various mechanics.

that is the reason i mentioned assembler. that is a nice topic to waste time on. at the end of the day i hope those gcc developers or windows equvialent, freebsd equivalent, apple hardware equivalent, ucontroller equivlanent and so on bother with those task and provide a decent compiler and decent programming language. those pdfs were for the 8 bit and one 16 bit ucontroller i bothered with usually sometimes up to 600 pages and it were multiple pdf files for a single controller.
Posted on Reply
#117
A&P211
jesdalsLooking forward to Wizzards review and Stephen Burkes rant about waste of sand... :D

200Watt TDP - one can fry eggs on that cpu :D
Brings back memories of the Nvidia 480.
Posted on Reply
#118
A Computer Guy
Panther_SeraphinAccording to his reporting currently there is very few "natural" scenarios in gaming where cross CCD communication will happen with current Zen 5 parts and here is a really big thing people need to take into consideration
I see this as well gaming on my 5950x and to a similar note with my VM's on 5950x/7950x (when running a single VM whos thread count fits onto a CCD). Windows appears to run the games on the first CCD or the VM activity on the first CCD. Just casual observation in Task Manager.
Posted on Reply
#119
efikkan
_roman_has this chanced since 1996? a cpu can fetch faster it needed "data" for computation when the cache is bigger. l1 is faster than l2 than l3 and so on. than DRAM than storage. what is done in the cpu itself does not matter. i doubt it has changed.
What is often taught in CS studies is that it's all one "memory hierarchy", ranging from faster and more expensive to slower and cheaper, and the more important stuff are stored towards the top, which is not exactly true. Speaking for modern x86 CPUs, slower storage aren't a part of the same address space, even when you have swapping. But more importantly how the caches actually work; the caches L2 and L3 are basically streaming buffers, L2 is the one the prefetcher works with, L1 is the feeding into the pipeline, and L3 the discarded stuff.

The more "important" stuff don't stay in cache, the CPU is constantly churning through lots of data every few thousand clock cycles, so if one particular piece of code or data isn't nearly constantly used, it will be pushed out of cache very quickly. We don't control this directly in code, but we can indirectly affect this by how we traverse data, how many jumps we do, and how dense our logic is. If we do this in patterns which the prefetcher can keep up with, then performance will generally be good, if not, performance will suffer, not just by a few percent, it can be like 50x. This also means we don't want the prefetcher to fetch data we don't need, because everything cached will discard something else which may be useful too.

I don't know how old you textbooks were back in 1996, but something which have changed are the performance characteristics of the CPUs when optimizing code. Like back in the early 90s (typically a 386, 486 or early Pentium) the relative cost of a cache miss was only a few clock cycles, today it's like 500+ clock cycles and our superscalar CPUs can execute ~8 calculations per clock, and math operations which used to be super costly are often very quick, so the relative cost of design choices changes over time. You'll see this if you watch videos of people optimizing their game for e.g. SNES, old DOS PCs or even N64, they do prioritization which wouldn't make sense today. Microcontrollers may be very different from a typical PC too. And this will likely change a lot in the coming years too. The current push from Intel is APX, primarily motivated by the fact that performance scaling is increasingly dominated by branch mispredictions and cache misses.
_roman_maybe i am wrong. what i learnt in 1996, yes 1996, the cpu itself has various mechanics.

that is the reason i mentioned assembler. that is a nice topic to waste time on. at the end of the day i hope those gcc developers or windows equvialent, freebsd equivalent, apple hardware equivalent, ucontroller equivlanent and so on bother with those task and provide a decent compiler and decent programming language.
Sorry, I didn't get your point. Can you elaborate how the compilers play into this in regards of caches? (other than gcc and llvm is much better at optimizing than msvc of course)
Posted on Reply
#120
PierreJG
It was just a matter of time before this happens. We will have to see how/if games can handle this. Then the price... I am guessing that thing is gonna be hella expensive. The best bang for your buck here are the 9800x3d. Anything over that just isn't worth it. Will you pay 2k more for a cpu with minimal performance gain? That is what happens here. This cpu will only make sense if it can match the price to performance of a 9800x3d otherwise not worth it for the average gamer.
Posted on Reply
#121
Thunderslat
PierreJGIt was just a matter of time before this happens. We will have to see how/if games can handle this. Then the price... I am guessing that thing is gonna be hella expensive. The best bang for your buck here are the 9800x3d. Anything over that just isn't worth it. Will you pay 2k more for a cpu with minimal performance gain? That is what happens here. This cpu will only make sense if it can match the price to performance of a 9800x3d otherwise not worth it for the average gamer.
I guess you missed AMD's marketing as well as many in this thread saying how these are not meant for gaming?
Posted on Reply
#122
Panther_Seraphin
I love this low level break down of points I dont have 100% knowledge in!!!
efikkanSince there are a lot of misconceptions here, I'll have to explain (2) first;
Developers generally speaking don't "optimize" to use more cache, at least not in the way you expect. There are mainly two types of cache, instruction(code) and data, and the way we optimize for them is a bit different. One key difference between L2 and L3 is that L2 is the cache the CPU front-end is interfacing with, while L3 is just discarded L2 (from all the cores). And while we don't have direct control of any of the caches**, cache optimizing have a primary effect on L2, while the only real way L3 is positively affected is by having L2 fetch less unnecessary data.
I thought L3 on Intel was different and it was front end facing similar to L1/L2 where as AMDs was purely discard based?
efikkanSo addressing your first question(1), are developers going to "address" this? No, not in the way you think, it's the opposite, meaning they will see less of a need to actually optimize it, since all the "hard core" gamers will be having lots of L3 and will be "suffering" less from unoptimized code. This is actually sometimes the downside of some unbalanced "improvements", especially the ones which "favors" bad design. Don't get me wrong, more L3 is a good thing, but there's a "sweet spot" where going beyond that only helps "bad code", and therefore incentivizes developers to write more bad code.
I was thinking this was probably going to be more game engine level vs game developer level so Epic Games, ID tech, Unity etc would have to do this optimistaion work but maybe I am completely missing on this, but as it has been from the 70s, the developers will try and code for the largest userbase and not for the highest end configurations.
efikkanLet me take a similar situation, this time in software, but it's an underlying API so it affects games. Some years back, there was all this hype about DirectX 12 and Vulkan (and Mantle) lowering overhead, which is a good thing by itself. But then we even got benchmarks to measure draw calls, and developers realized that the reduced cost of bloat means we don't have to prioritize optimizations as much. And we see the results now; many games in the last ~5-8 years are incredibly demanding for both CPU and GPU, while only offering a small step above the previous generation of games in terms of visual fidelity.
We have unfortuantely seen that with texture sizes as well requiring insane amounts of VRAM as well. I know how 4K is becoming the new standard for development but seeing how little has "improved" in visual fidelity over the last 5 years or so is sad.

Just thinking of how things from the BF3/4 days to now and how you used to be able to run them on 1-2Gb of VRAM cards with everything maxed with no issue.
Posted on Reply
#123
A Computer Guy
AusWolfinter-CCD communication is an issue regardless of cache size. I'm curious how two X3D CCDs help this situation, if at all.
Just something to add to the conversation. In this particular experimentI managed to increase the MT performance of Cinebench 2026 despite crossing CCD's. There could be non-CCD communication reasons for that such as utilizing the cache on each chip (effectively doubling the cache available to CB). (I think I did another run across 4CCD's with the near same result)

As much as people think inter-CCD communication is a "problem" I think it's not such a big deal outside of cases where it proves to be detrimental. In other words I wouldn't use potential inter-CCD communication chance as a factor in a general purchasing decision. There seems to be a lot of concern around inter-CCD communication when it's mostly a non-issue in my opinion.

The exceptional case is with gaming and hybrid dual CCD X3D CPU's but there is also a difference such as click speed between CCD's also working toward lower or inconsistent performance if you cross CCD's. My expectation is with 9950X3D2 is basically normalization of performance across the chip as a whole due to both CCD's having the X3D cache but also being closer to the same clock speed with each other as with normal dual CCD chips.
Posted on Reply
#124
Thunderslat
Panther_SeraphinI thought L3 on Intel was different and it was front end facing similar to L1/L2 where as AMDs was purely discard based?
This hasn't been true in at least a few generations. Maybe Rocket Lake was the last time it was true IIRC.
Posted on Reply
#125
efikkan
Panther_SeraphinI thought L3 on Intel was different and it was front end facing similar to L1/L2 where as AMDs was purely discard based?
Apparently in Intel's optimization manual, page 307, Nehalem-Skylake architectures did support it, but more recent ones with non-inclusive L3 doesn't. And the manual advises against prefetching to L3.
Panther_SeraphinI was thinking this was probably going to be more game engine level vs game developer level so Epic Games, ID tech, Unity etc would have to do this optimistaion work but maybe I am completely missing on this, but as it has been from the 70s, the developers will try and code for the largest userbase and not for the highest end configurations.
This problem has to do with how the renderer is structured (regardless of if it's tailored, semi-custom or generic), usually there's multiple layers of abstraction to render a single object on-screen, and this will unfortunately result in a massive amount of API calls, state changes and CPU instructions. A well designed game engine should be able to batch objects and render much more efficiently, at least the simple ones.

But this problem has very little, if anything, to do with your point about "optimizing" for one userbase. Efficiency is the key to allow scalability, whether the priority is "good enough" for most people or maximum fidelity for a high-end systems.

Some of these engines seem to be more "content creation platforms" rather than fine-tuned game engines, engines like Unreal and Unity are probably among the "worst", and all the escalating problems we see in current games are mostly symthoms of this underlying inefficiency. Problems like terrible resource management(VRAM management, resource streaming and "duplicated" resources), bad LoD scaling, endless game bugs, slow shader compilation and the aforementioned crappy performance. I'm not going to elaborate on shaders in this thread, but it's probably them generating bloated "duplicated" shaders instead of tailoring them, and it's baffling to me that this has even become an issue. And it's not like what I'm wanting is impossible today, but engineering needs to be a priority, not just mass-producing garbage.
Panther_SeraphinWe have unfortuantely seen that with texture sizes as well requiring insane amounts of VRAM as well. I know how 4K is becoming the new standard for development but seeing how little has "improved" in visual fidelity over the last 5 years or so is sad.

Just thinking of how things from the BF3/4 days to now and how you used to be able to run them on 1-2Gb of VRAM cards with everything maxed with no issue.
What you're describing are symptoms of what I'm referring to, it's not primarily because of 4K. We had high resolutions a decade ago, and back then we generally used more heavy MSAA or even super sampling, but today gamers with pretty high specced systems "needs" to resort to fake frames and/or fake resolutions because the games are so bad.
Posted on Reply
Add your own comment
Nov 22nd, 2026 11:01 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts