AMD Ryzen 7 5800X3D Continues Showing Much Potential For 3D V-Cache In Technical Computing

[brucethemoose]

In any case, triple or quad channel is unlikely to happen for AM5. Even if you ignore the CPU, the iGPU could really use the bandwidth.

Bingo. CPU doesn't really need it, GPU does.

That being said, consumer desktops dont really need strong IGPs, as the advantages (lower power, vram size, faster transfer, more compact) don't matter much there.


What *does* need it is consumer + professional laptops. AMD/Intel should absolutely make a 4+ channel laptop platform.

[piotrj3]

If it includes synthetic benchmarks, I suppose one could create a fine-tuned benchmark that chases multiple pointers concurrently in a single thread. A CPU capable of executing 3+ loads per cycle would be required (I do not own such a CPU yet) to show a measurable difference with a 4-channel RAM. With AMD Zen 3, there is a small performance advantage when the AM4 motherboard has 4 memory modules installed instead of 2, although both of these configurations are still dual-channel DDR4 - I am not sure whether this applies to just single-threaded code, to just multi-threaded code, or to both.

Measuring such diffrence won't be hard in workloads (I did it myself with AVX2) with low compute on very large data sets, you can very easly saturate dual channel 3600MHz memory with 1 core only on Ryzen 3600. If 1 core from zen2 can do that, then for sure 16 cores from zen 3 can do that as well.

Also there are real benchmarks on intel 7820X working with 1, 2 and 4 sticks of ram (it supports up to quad channel, but can work in single channel as well)

(polish website, so you might want to autotranslate it: https://www.purepc.pl/test-pamieci-r...nnel?page=0,14 )

[piotrj3]

I've considered this issue, but it depends on your workload. I was thinking that maybe for command rates configured to T2, the pairs of channels could maybe even work asynchronously to reduce latency. I imagine that is very complicated, and could potentially interfere with threads that need more RAM than what a pair of channels has to offer.
In any case, more channels can improve performance for a minimal increase in cost. Bigger caches in a lot of cases cost a lot and sometimes yield no benefit.


That's assuming all boards include all 4 channels. I'm sure most ITX boards would either stick with 2 slots, or go with SO-DIMMs. Budget boards won't need 4 channels. I think paying 10 extra is well worth the performance gains, when you consider the cache costs a hell of a lot more than that.

Latency you are chasing here are very small gains that cannot be overdone.

https://www.techpowerup.com/forums/t...aida64.263929/

Literally smallest latency (on Ryzens) you can practically gain on daily drive with quite strong XMP profile is around 60ns, and if you want absolute stability, more like 80ns. Meanwhile L3 cache has around 7-10 times lower latency. And you can't do anything about it really, as you can see on leaderboards, latency didn't change much since DDR2! times. Everytime CPU fails to predict what needs to be in cache, it needs to wait until it gets information from RAM.

Let's imagine you make simple function call that is in pretty far away land. Functions does something very simple (let's say 8ns). now if CPU fails to predict what is supposed to be come, but CPU has that in L3 cache, you will wait additional 8ns for that cache, so everytime L3 cache call happens performance on such function drops by half.

Now imagine thing wasn't in L3 cache, and we need to go... to RAM. now things take 64ns, so now we need to wait 8 times longer. Performance drops by 9 times. This is primary advantage of 3d cache, because cache is larger, there is much higher chance what you need is in cache, and if it is in cache you most of time don't pay such big costs, This is why in general performance increase by itself isn't that great, like most games show in cpu bound scenarios maybe 10% performance improvement to 5800X. But if you look at worst case scanarios (1% and 0.1% lows) 5800X3D isn't 10% ahead, it is often more like 30% ahead. This is why it is often called gamer cpu, because gamers more care about consistent gameplay then few higher average FPS. Meanwhile from polish benchmarking website i shown on 7820X in most games quad channel doesn't provide big benefits over dual channel neither in average neither in lows. In nutshell cache does something quad channel can only wish to achieve.

If you want to truly reduce latency CPU <-> RAM we would have to move towards many smaller channels and soldered RAM very close to CPU and RAM being optimized in latency not speed.

[brucethemoose]

But if you look at worst case scanarios (1% and 0.1% lows) 5800X3D isn't 10% ahead, it is often more like 30% ahead. This is why it is often called gamer cpu, because gamers more care about consistent gameplay then few higher average FPS.

Isn't this a false equivalency? Thousands of functions are being called every frame, hence a single branch prediction fail to memory isn't going to cause a stutter. Its about the aggregate... and I don't understand why the slowest frames would have proportionally more "misses." Are you saying the game hits more of those unpredictable functions during the bad frames?


I would think its about the cache holding more code/data, so when the engine does something atypical, whatever its churning through is more likely to already be in the cache.

[geearf]

Power limitations of the socket.

Thank you!

[skeevy420]

It is the last CPU for the AM4 platform. Define "the best" please. It's faster in some tasks but lots of people don't even need that level of performance in the first place and would be happy with something like Ryzen 5500 which costs just $160. 5800X3D on average won't be three times faster.

And God forbid we remember that Intel still exists and offers excellent CPUs like Core i3 12100 which costs just $122 and has a built-in GPU which can only be found on much more expensive AMD APUs like 5600G and 5700G.

God forbid I have to buy another motherboard versus upgrading my current AM4 to something better. I could care less that Intel exists -- not for fanboy reasons, but because I'd have to spend an extra $130 (to get an equivalent motherboard to what I own on AM4) to use an Intel CPU. I could buy high-end AMD for the price I'd have to spend to buy mid-range Intel. I'm just trying to decide what I'll eventually toss into my AM4 box before I retire it from upgrades.

Also, the Core i3 12100 is mostly a downgrade from my current APU, a Ryzen R5 4650G. I'm not even considering the 5600G because of that.

Ignoring not having an iGPU, for me on a general purpose desktop the "best" has the best balance in regards to number of cores, processing speed, and available features. 5800X3D seems to have that balance with the 5000 series. While neither the highest core count or the fastest clocked 5000, the stacked cache gives it an edge that makes it arguably the "best" 8c/16t AM4.

I'm tied between the 5700G and the 5800X3D as the best general purpose desktop AM4. To me the base 5800 model is rather moot -- compared to the 5700G it just has some more cache but it loses the iGPU. I'd rather have the iGPU. It's basically GPU redundancy and VM options versus 1-3% faster Zstd.

I'll be honest with you, fastest clocked AM4 5000 is kind of moot, too. Precision Boost Overdrive is friggin simple to use and lets anyone willing to watch a YouTube video the ability to OC their Ryzen to its safe limits.

[skeevy420]

I don't think AMD is going to release more products for the AM4 lineup given that AM5 is almost here, though we don't how much time is AM4 going to be around once AM5 gets released.

I think AMD will stop producing the 5800X3D as soon as they release any 3D V-Cache CPU, but they might continue making CPUs and APUs to fill the entry-level market. I don't think they will release cheap AM5 products at launch, knowing that it's going to be a DDR5 only platform and though DDR5 prices are quickly improving, they are not very good. So it wouldn't make sense to release cheap SKUs if the end user has to pay a premium for the RAM.

So, I guess the 5800X3D will remain as the best AM4 gaming CPU and the 5700G will remain as the best AM4 APU.

That's what I'm thinking, but I'd love to be wrong.

[birdie]

God forbid I have to buy another motherboard versus upgrading my current AM4 to something better. I could care less that Intel exists -- not for fanboy reasons, but because I'd have to spend an extra $130 (to get an equivalent motherboard to what I own on AM4) to use an Intel CPU. I could buy high-end AMD for the price I'd have to spend to buy mid-range Intel. I'm just trying to decide what I'll eventually toss into my AM4 box before I retire it from upgrades.

Also, the Core i3 12100 is mostly a downgrade from my current APU, a Ryzen R5 4650G. I'm not even considering the 5600G because of that.

Ignoring not having an iGPU, for me on a general purpose desktop the "best" has the best balance in regards to number of cores, processing speed, and available features. 5800X3D seems to have that balance with the 5000 series. While neither the highest core count or the fastest clocked 5000, the stacked cache gives it an edge that makes it arguably the "best" 8c/16t AM4.

I'm tied between the 5700G and the 5800X3D as the best general purpose desktop AM4. To me the base 5800 model is rather moot -- compared to the 5700G it just has some more cache but it loses the iGPU. I'd rather have the iGPU. It's basically GPU redundancy and VM options versus 1-3% faster Zstd.

I'll be honest with you, fastest clocked AM4 5000 is kind of moot, too. Precision Boost Overdrive is friggin simple to use and lets anyone willing to watch a YouTube video the ability to OC their Ryzen to its safe limits.

5900X overall is a much better CPU than 5800X3D. More real cores, costs now even less than 5800X3D.

[skeevy420]

5900X overall is a much better CPU than 5800X3D. More real cores, costs now even less than 5800X3D.

I'm aware I'm about to contradict myself from my statement above, but I use enough inline compression that I'd rather have the V-Cache over the 4 extra cores. V-Cache really isn't much of a gaming feature as much as it is just great overall -- it doesn't hurt performance and may dramatically increase it.

In my experiences for gaming and generalized use those 4 extra cores will be moot and next to useless. My 6c/12t 4650G is already a perfectly adequate as a gaming CPU and doubling my current core count won't make my 4K upscaled from 1080p60 games magically run at native 4K60...I wish it worked like that.

[agd5f]

Threadripper (LGA 4096) cost isn't a good indicator of the cost of a hypothetical AM4 with 4-channel DDR4, because Threadripper supports 4 PCIe-x16 slots while AM4 supports 1 PCIe-x16 slot.

You could just reuse the socket and not populate the extra lanes. The same physical socket is shared with Epyc as well. The original argument was that it would have been "cheaper" to do a 4 channel Ryzen compared to adding the additional cache stack. I would argue that it would be "cheaper" to do a cut down Threadripper that uses the same socket that designing a new socket and die for 4 channel Ryzen.