All i'm seeing is the confirmation that independently parallalizable tasks finish twice as fast on a cpu with twice the cores. cool, amdahl's law is proven.
The handbrake one, all the times seems similar indicating similar single core perf.
This matters for me since single core perf is pretty important for visual studio/other software with alot going on feeling "snappy" even tho the actual compiling/rendering might be faster and scale with moree cores.
Single threaded tasks should never run at the base clock. The base clock can pretty much be thought of as the minimum clock speed you should see when all cores are maxed out and the thermal solution is only just meeting the spec.
I doubt 2.5ghz vs 4.2ghz is going to make any real difference to "responsiveness". The more pressing concern would be making sure the kernel actually schedules foreground workloads promptly.
Maybe i'm missing why it doesn't matter. Ryzen runs at 4.5 base clock, TR Pro runs at 2.5 base clock, upon booting up nothing is happening so each cpu runs at their base clock. I open something like visual studio that isn't too intensive so each cpu doesn't realize it needs to boost. Won't the ryzen with 4.5 base clock feel snappier than the 2.5 one when vs loads?
When a pretty big task (compiling, rendering) activates the scheduler and causes the cpu to boost to their respective 5 ghz or w/e, then yeah the numbers would be the same, but they don't be at the beginning when i'm dragging windows around and right clicking on stuff in visual studio. I don't believe this feeling is reflected in the scores.
No. None of what you're writing is accurate. No processor made in the last decade will ever idle at the base clock. Any modern processor idles far, far lower than that, approximately 1Ghz, maybe even lower. Idling at multiple gigahertz would be a huge waste of energy. The minimum clock speed is not correlated to the "base clock" at all.
The base clock is entirely irrelevant to everything you are talking about. Please reference my earlier comment for the meaning of "base clock": https://news.ycombinator.com/item?id=37980293
While technically correct for longer time frames, setting a performance governor on both windows and linux basically means that it comes out of idle at the max allowable frequency. In order to achieve this it basically means that idle isn't adjusting the clock rates (to avoid the transition latencies) for idle times less than 2x those latencies. Depending on the core/firmware/etc it may be gating the clock, or clock skipping, which can save some power
And yes it can waste energy you can measure with the your battery monitor (or UPS/PDU) but its also possible to measure the interrupt handling latency/etc, and for some cores it can make a very noticeable difference to desktop latency if you happen to be sensitive to such things.
While I've posted elsewhere about clamping the clock rate to save power, I also do the converse when plugged in by cutting off the bottom 2/3rds of the frequency range. This results in a far more responsive desktop in linux and even windows to a lesser extent.
>> and the thermal solution is only just meeting the spec.
Ok, so, as I alluded to earlier... make sure to have better-than-minimum-spec cooling to let the processor indefinitely run all cores at the boost clock (or very close to it).
It's been a long time since I've seen a desktop/workstation processor limit itself to the base clock for any reason.
Also, I agree with dralley. Clock speeds are unlikely to be the issue there anyways.
That's more of a software thing than hardware. You could do that in the 80's with the right software, but most modern operating systems suck at realtime stuff (and ui is realtime).
+1. it's great that it compiles code faster, but i would also like when i'm writing code and hit enter, a newline is added and all lines under it goes down by 1 without any "lag".
That's why i decided to go with a 5950x + 3090 rtx + gamer ram for my current "workstation" instead of a 5995wx + rtx 6000 + ecc ram for my current machine. even tho its not workstation rated, it seemed like the better way to go for quality of life feel.
When the next generation of cpu/gpu/ram drops in the next couple eyars, i can re-evaluate the gamer vs professional offering to see if it matters.
Having run a 3945WX machine side by side with same era intel and AMD desktops the Threadripper Pro was the more “responsive” machine, but it was minor enough you would have had to have them side by side to really notice.
Once there were a lot of programs in flight it started making a larger and larger difference. Now half my family and friends have TR Pro systems bought refurbished (they watched eBay) because they loved mine so much.
Its usually the ones with more cores than the max ryzen cpus that have to make tradeoffs and seeing how it affects day to day use. (the 32, 64, and in this case the 96 core ones).
since a few generations ago boosts have become so good that for many use-cases base clock don't matter that much
AFIK it's basically tweaked AMD EPYC™ 9654 with much higher boost and some other changes, so that's probably where the base clock comes from
some situations where the base clock might still matter:
- you perfectly max out CPU utilization (no I/O, hardly cache misses, etc.) and at the same time have exactly only the thermal headroom from the spec and run it for a "long" time
- you want to max optimize for watter/perf the best power efficiency is likely around the base clock (for this one because of my assumption of it being more or less a tweaked server processor, on a typical consumer desktop PC I would say likely quite a bit below the base clock)
Threadripper is as the name implies, purely MT focused.
I run simulations that are inherently completely single-threaded and I lean on Geekbench which tend to be a good predictor for me. As far as I can tell, Intel still holds the crown in absolute ST perf, granted at horrific efficiencies: https://browser.geekbench.com/processor-benchmarks/
(be sure to ignore the "Top Single-Core Results" which AFAICT is full of BS numbers). Intel's latest 14900K isn't there yet, but should be a smidgen faster: https://www.techspot.com/news/100034-intel-core-i9-14900k-to...
> All i'm seeing is the confirmation that independently parallalizable tasks finish twice as fast on a cpu with twice the cores. cool, amdahl's law is proven.
Yes, but if you can squeeze more cores in the same space (and/or power) envelope, and not suffer a performance per core penalty, you're winning.
LOL Both are correct. Threadripper Pro has 8 Channel, and Threadripper only has 4 ( damn ). And op was correct in saying EPYC, which really do have 12 memory channel, but obviously he is wrong when it is Threadripper and not EPYC.
With smaller sticks, they could populate all the channels while keeping total memory capacity the same as other setups. I don't see why they had to splurge all the way up to 512GB.
> I don't see why they had to splurge all the way up to 512GB.
Quoting the article:
"To celebrate the much-hyped launch, our sister site PCMag put the flagship CPU through its paces (remotely) in several popular benchmarks."
The people who did the benchmarks didn't splurge... they had no physical access to the remote machine at all. Certainly, it would have been ideal to talk to their remote contact and see if there were any 16GB sticks sitting around to test with instead, but I agree with the other comments that the memory capacity is unlikely to make a significant difference in these benchmarks.
There will certainly be plenty of other benchmarks soon enough, once people get hands on with these processors.
It just seems so incredibly sloppy to not have that be consistent. Do they expect all of their readers to then audit the code of the benchmarking that they are doing to ensure that it cannot possibly be bound by this?
They used Cinebench. You can download this and verify that it uses less than 4GB of RAM. It is a CPU bound benchmark. Adding 384GB of RAM makes no difference whatsoever.
There is no need to start out every article with remedial lessons. It is reasonable for an enthusiast magazine to assume familiarity with how computers work. The average ExtremeTech reader should already know what memory is and how increasing the amount of memory changes (or doesn't change) performance.
It is not possible to give all the systems the same memory configuration. They don't support the same memory and don't have the same number of channels. And I expect giving all the systems 512 GiB of memory would only widen the lead because larger DIMMs are usually slower.
>Do they expect all of their readers to then audit the code of the benchmarking that they are doing to ensure that it cannot possibly be bound by this?
Cinebench is hardly obscure. The average ExtremeTech reader will already know what it is and what it measures.
you want to max out memory channels on all devices to test max performance
but you also want to use RAM DIMs which are equally good, if possible the same
as AMD has more memory channels this means it will get more "equally good"(1) RAM DIMs and in turn have more memory
and as long as you make sure that no of your benchmarks perform pressure wrt. RAM capacity (e.g. max RAM usage 64GiB) you now have a fair benchmark wrt. max performance
naturally if you don't plan to max out your RAM channels on AMD you do need a different benchmark for non-max performance
(1): "equally good" is also a bit tricky as different vendors have slightly subtle differences in access patterns and DDR5 ram training also can make the same RAM run with different settings on different systems which can make the same ram dim not equally good, but there probably is some RAM which doesn't have such issues
If the benchmark has any cache misses at all then you also want to make sure everything about the memory configuration is the same, too, for a fair CPU benchmark, right? Number of channels, latency, etc.
No, the actual amount of RAM isn't directly relevant, but it seems like a possible brown m&m to me.
> for a fair CPU benchmark, right? Number of channels,
That's exactly where the differences comes from you want to max out the available memory channels on each device not have the same number. Same for latency etc.
I mean your also not fixing the clock speed to 2GHz no boost or when comparing cars limit things just to the first 3 gears or similar.
Because if you would add such artificial limits you won't compare fairly how fast the _max performance_ can be, it would be a very different comparison and wrt. evaluating max performance very unfair.
Now you still need to e.g. have a fair choice of RAM, so preferably if possible use the same RAM sticks (and also use RAM which works equally well with both Intel and AMD). But what that means is that you _have to_ give the AMD system more RAM because it has more channels. Now you also _have to_ make sure that you benchmarks don't have any RAM pressure wrt. capacity.
Also I'm not sure why you mention cache misses? Because number of cache misses is quite independent of RAM amount? Do you mean disk cache or swap misses instead, but I don't think the benchmark does disk I/O and shouldn't have swap either?
But even if the benchmark only uses let's say 32GiB of memory for getting a proper GPU
> If the benchmark has any cache misses at all then you also want to make sure everything about the memory configuration is the same, too, for a fair CPU benchmark, right? Number of channels, latency, etc.
No. Adding that memory bottleneck would make it an unfair and worthless comparison. If you are testing the maximum CPU performance then you need to eliminate those bottlenecks, not create them.
Larger sticks (or more sticks) of RAM are generally slower than smaller sticks. It might not be possible to duplicate same speed ram and capacity on the Intel board. I would hope they duplicated the test with the same speed of RAM before matching capacity. The results are so one sided, I doubt either capacity or speed matters.
Pardon my ignorance, I hear about "fun with avx512" so often yet still have 0 intuition about why its fun? What do people do with that instruction that's so different to all the other stuff?
I’m looking at one for research purposes. Agent based simulation, non-GPU-implementable Ml modeling, large scale data processing. There are a lot of tasks in my work that are greatly sped up by having tons of threads.
Developers will love it. With limited resources nobody tests their code for compatibility: good testing requires an order of magnitude more cores. Test against multiple competing libraries? Compiled with multiple competitive alternative dependencies? Maybe it is also important to test dependencies with various flags? Maybe test in multiple Linux distributions? And then cross-product multiply all possible combinations and get the best result.
I know video cards have sepcialized hardware for video encoding, but those are tuned for realtime streaming and not meximum quality. If you want to use a different algorithm than the one baked into the hardware, can you use a GPU for that?
> I know video cards have sepcialized hardware for video encoding, but those are tuned for realtime streaming and not meximum quality. If you want to use a different algorithm than the one baked into the hardware, can you use a GPU for that?
If you're doing something that follows the same general design as most existing video codecs, absolutely; these days "hardware" encoding is less "fixed function chip" and more "the driver/firmware knows how to stitch together these components so as to comply with the xyz standard" - hence you see support for new encoding standards getting added in driver updates. If you're doing some completely radical out-of-left-field video compression algorithm, maybe not, although even then GPU hardware is pretty general these days and video encoding tends to be well suited to running on it.
Tell that to my flight simulators. DCS has gotten better with the recent MT release, but the determinative requirements of that coupled with multiplayer servers in the 50+ population and all the AI brings most systems to their knees. Especially in VR…
AI systems are the new hungry monster. They're still pretty slow on expensive hardware and not everything is GPU based for reasons I don't fully understand. (I've got GTX/4090s and TR/3990x with 256GB of pretty fast ram and an NVME array for storage and have done a bunch of things related to AI/ML where I walk away for a few hours or even a day - both CPU and GPU get pretty taxed.)
CPUbenchmark is giving the new chip about a 100% improvement over the 3990x which is fairly tempting even at the 6-10k price tag I've seen floating around.
>CPU performance has been well beyond acceptable since a long time ago.
Our antenna design folks sends simulation runs to a group of R7525s with 2x EPYC 75F3 CPUs and 2x A100 80GB GPUs.
A small problem might have tens of millions of elements and billions of unknowns to solve and run on one server. Larger problems might be spread across all of the servers, after coordination with everyone else.
Simulations take 8-12 hours to run.
This is not acceptable.
Anything slower than "an amount of time imperceptible to even the most responsive human" is unacceptable.
Everything is too slow.
Networks are too slow, memory is too slow, storage is too slow, GPUs are too slow, and CPUs are definitely too slow.
Has anyone done a perf / watt scatterplot of the current AMD and Apple offerings?
I'd guess this wins in absolute performance (due to the TDP), but I've heard AMD is pretty competitive on energy efficiency too these days. I'm typing this on an M2, which is simultaneously cooler and faster than my old Intel laptop.
Wondering if it's time to upgrade my decade-old Intel Linux desktop to an AMD yet.
I have an older threadripper - a 3970x. It's the most power hungry device in my house after my electric oven. In raw numbers it's hard to beat. But it is _not_ efficient
I have the same chip and it's amazing to see it idle at 75W after growing up on Intel chips that use like 5W at idle.
Of note is that Zen 2 (the 3970x's microarchitecture) is 7nm. The new Threadrippers are on a 5nm process. I would expect slightly lower power consumption, but note that the 7000 series of Threadrippers quote a TDP of 350W while the 3000 series quote 280W. So I'm guessing they're using the efficiency for more speed instead of more power savings.
To me, it's fine. I'd always prefer paying more for electricity than to wait longer for something to complete. (But I do respect the desktop chips that can blink my cursor with an efficiency core that uses a few tens of milliwatts.)
All of the AMD chiplet based designs do poorly at idle power.
These monsters will do better than the 39xx because of the 6mm IO die. But it's still going to have high idle power compared to a monolithic Intel design.
The monolithic AMD dies (laptop/mobile) are competitive in the idle power space.
I have a 16-core Ryzen 7950X that I run in "eco mode 105W". This delivers performance close to an Intel 13900K but at less than half the power. It's also much easier to cool and get a quiet PC without water cooling and enthusiast shenanigans (de-lidding, etc.)
I don't know if the Zen 4 Threadrippers can be similarly run with a power limit. If they can, I'd expect much better efficiency than whatever Intel offers.
There's some more nuance to efficiency than just max power at max load, of course. The Apple chips will likely have good efficiency compared to the lower core count (say, 32) TR because the watts per core gets high on those smaller TR chips. Yet if you compared their performance at a fixed 90w, I suspect the threadripper would come out ahead, since chips are much more efficient when at fractional loads that don't lead to boosted core clocks. Then again, at idle, the TR is probably guzzling power relative to the M2 Ultra. I'm only speculating to illustrate; a thorough comparison of their perf/watt characteristics would involve sampling many types of workloads of varying thread counts and levels of per-core saturation.
If you underclock the Threadripper to get a score of ~27k, then how much power will it use? I wouldn't be surprised if it was roughly equal to 90W, or even lower.
The stock configurations for a lot of desktop chips is to get the maximum performance at the expense of power, especially for things like these Threadripper series which are explicitly aimed at maximum performance. Often even drastically reducing power usage only gives modest performance penalties.
Yes, cutting power targets of a (Desktop) Ryzen to 65W or 90W reduces performance to around 50% or 80% in some benchmarks, iirc. Likely a good tradeoff in many scenarios.
I also run an RTX 3900 GPU at 60% power for 80-90% performance. It's a noticeable decrease in requisite cooling.
Yeah I am definitely not a fan of Intel/AMD/and even Nvidia who will completely push power to stupid levels just to get less than an extra 10% performance
Gamers Nexus did a video earlier this year comparing the 7950x at different eco modes and they found that putting the 7950x at a 105 watt eco made drop the performance around 5% but shaved almost 100 watts off of power. heres the link to the video https://www.youtube.com/watch?v=W6aKQ-eBFk0
I know why these companies do it and im lucky electricity isnt too expensive in my area but i rather shave 100 + watts of heat being dumped into my room (especially in the summer months)
>Has anyone done a perf / watt scatterplot of the current AMD and Apple offerings?
Tl;dr, if you want the absolute performance on Desktop, get the Threadripper Pro.
AMD Zen 4 7800X3D, 5nm 5.04Ghz, Single Core GB6 Score @ 2833
Apple A17 Pro, 3nm 3.80Ghz, Single Core GB6 Score @ 2914
Well you can find that with Geekbench but it is very likely worst to publish it as it leads to a wrong conclusion without the basic understanding of Hardware or CPU.
The node and design whether it was tuned for Clockspeed ( Desktop ) or SoC ( Apple ). There are measurable percentage difference in the same core for Risen on desktop and Ryzen SoC. And then you have to factor in Wattage difference in Clockspeed they are operating at. You are expected to know all these basics before the scatterplot would even make sense.
The Desktop 7800X3D will likely use 20W+ in the test, while the Smartphone A17 uses at best 5W.
You will then also have to factor it a lot of these performance test are not sustainable without adequate cooling. i.e You can sustain the above performance for a very long time on 7800X3D, dont expect that on A17 inside a phone.
Many of these are pointing out the obvious. But it seems on HN we are increasingly required to do so otherwise it leads to some sort of flamewar.
Anecdotally I find my m1 laptop and ryzen 5000-series laptop to have similar energy efficiency, but I don't have much hard data.
When it comes to laptops idle efficiency is king and this is where it gets hard to test the chips because the rest of the motherboard also has a role.
For my m1, opening a vm or just plugging in a wireless mouse dongle is all it takes to shave several hours off the lifespan, like from 20 hours to 10.
For the amd laptop, anything waking up the nvidia gpu will do the same, like 10 hours to 3.
When you're talking such low amounts of power, the networking card, sound card, display efficiency, ssd efficiency, and whether the system chooses to run the fan or let the cpu stay warm starts to matter a lot since just like the cpu these are things that are running at the same time.
So I guess a fair test would have to use the same ssd and have the monitor off, using an external monitor. Then you're just stuck with the efficiency of the parts of the motherboard you can't choose.
Actually, no - their thing for the past few years has been to build out the most comprehensive test bench across all PC hardware components. "LTT Labs." They are aiming to become the authority on hardware performance and reliability, and have invested heavily in the tools and industry experts required to do that. Linus doesn't do any testing himself; he is just bankrolling it with the proceeds from his main channel and other media properties.
I find this whole thing super fascinating, coming from the perspective of Silicon Valley startups.
I don't know when/if that change you talk about happened, as I banned LTT from my feeds years ago for their (subjectively) annoying style of presentation, but latest drama isn't even year old and highlighted so many technical issues with LTT I have no intention of trying them again:
[0]: The Problem with Linus Tech Tips: Accuracy, Ethics, & Responsibility
Lol, Steve is ok, but I remember when he attacked wrong company for making claims against his videos. He never apologised or acknowledged he was wrong. So, please.
Fair enough. I have a few gripes with the channel, particularly how they title videos and the thumbnails are usually cheesy. The content can be hit or miss, but the smart house series is especially relevant to me as I'm going through something similar a smaller scale.
The thing that I find so interesting is that they - for better or worse - essentially live stream their business decisions, challenges, and aspirations. Whether their endeavors are successful or not, I agree with their decision to try and move beyond Youtube and create their own video platform via Floatplane. They've also found success in alternative revenue streams via sponsorships from reputable brands and merchandising and are very open about their metrics.
Lastly, I really respect that they are 100% bootstrapped. I've only ever worked for companies that rely on investor funding for growth, and their influence often feels intrusive and counterproductive.
It's basically a AMD EPYC™ 9654 but with more clock boost speed and some differences wrt. IO (e.g. less but faster memory channels) and I think some differences wrt. enterprise features.
For me as a developer it does not bother so much that some tasks like compilation or rendering or AI-training can take a long time. What bothers me is that I am doing multiple things at the same time like say committing to git or rebasing and trying to read my code at the same time, taking backups simultaneously. So this would seem like an ideal, if not overkill processor for me.
I am just wondering if it would be better and cheaper to buy an Threadripper 7980X 64 Core for Server than EPYC. You get higher single core performance. Specifically for those workload where bandwidth isn't an issue.
Something like StackExchange [1] could fit all their 9 server into 1 ( or 2 with one for redundancy ) without any degraded performance.
I keep trying to make the point that one or two servers could now put out the traffic of many top 100 websites, assuming they apps are written reasonably efficiently (e.g.: with C# or Rust, not Ruby).
Nobody believes me, which says a lot about both the hardware and software industries.
Yes. And we will have 128Core / 256 Thread Zen 4c Server soon.
I would be happy if Ruby Rails could do it in 2x the rendering time i.e slower with 2x Resources / Server. That is combined 4x difference. Unfortunately even with JIT we are not there yet.
107 comments
[ 2.7 ms ] story [ 171 ms ] threadAll i'm seeing is the confirmation that independently parallalizable tasks finish twice as fast on a cpu with twice the cores. cool, amdahl's law is proven.
The handbrake one, all the times seems similar indicating similar single core perf.
This matters for me since single core perf is pretty important for visual studio/other software with alot going on feeling "snappy" even tho the actual compiling/rendering might be faster and scale with moree cores.
https://www.cpubenchmark.net/compare/5726vs5234vs3862/AMD-Ry...
When a pretty big task (compiling, rendering) activates the scheduler and causes the cpu to boost to their respective 5 ghz or w/e, then yeah the numbers would be the same, but they don't be at the beginning when i'm dragging windows around and right clicking on stuff in visual studio. I don't believe this feeling is reflected in the scores.
It takes tens of milliseconds to reach the boost clock: https://stackoverflow.com/a/64254459
The base clock is entirely irrelevant to everything you are talking about. Please reference my earlier comment for the meaning of "base clock": https://news.ycombinator.com/item?id=37980293
And yes it can waste energy you can measure with the your battery monitor (or UPS/PDU) but its also possible to measure the interrupt handling latency/etc, and for some cores it can make a very noticeable difference to desktop latency if you happen to be sensitive to such things.
While I've posted elsewhere about clamping the clock rate to save power, I also do the converse when plugged in by cutting off the bottom 2/3rds of the frequency range. This results in a far more responsive desktop in linux and even windows to a lesser extent.
Ok, so, as I alluded to earlier... make sure to have better-than-minimum-spec cooling to let the processor indefinitely run all cores at the boost clock (or very close to it).
It's been a long time since I've seen a desktop/workstation processor limit itself to the base clock for any reason.
Also, I agree with dralley. Clock speeds are unlikely to be the issue there anyways.
That's why i decided to go with a 5950x + 3090 rtx + gamer ram for my current "workstation" instead of a 5995wx + rtx 6000 + ecc ram for my current machine. even tho its not workstation rated, it seemed like the better way to go for quality of life feel.
When the next generation of cpu/gpu/ram drops in the next couple eyars, i can re-evaluate the gamer vs professional offering to see if it matters.
Once there were a lot of programs in flight it started making a larger and larger difference. Now half my family and friends have TR Pro systems bought refurbished (they watched eBay) because they loved mine so much.
https://www.amd.com/en/products/cpu/amd-ryzen-threadripper-p... vs https://www.amd.com/en/products/cpu/amd-ryzen-9-7900x
Its usually the ones with more cores than the max ryzen cpus that have to make tradeoffs and seeing how it affects day to day use. (the 32, 64, and in this case the 96 core ones).
AFIK it's basically tweaked AMD EPYC™ 9654 with much higher boost and some other changes, so that's probably where the base clock comes from
some situations where the base clock might still matter:
- you perfectly max out CPU utilization (no I/O, hardly cache misses, etc.) and at the same time have exactly only the thermal headroom from the spec and run it for a "long" time
- you want to max optimize for watter/perf the best power efficiency is likely around the base clock (for this one because of my assumption of it being more or less a tweaked server processor, on a typical consumer desktop PC I would say likely quite a bit below the base clock)
I run simulations that are inherently completely single-threaded and I lean on Geekbench which tend to be a good predictor for me. As far as I can tell, Intel still holds the crown in absolute ST perf, granted at horrific efficiencies: https://browser.geekbench.com/processor-benchmarks/ (be sure to ignore the "Top Single-Core Results" which AFAICT is full of BS numbers). Intel's latest 14900K isn't there yet, but should be a smidgen faster: https://www.techspot.com/news/100034-intel-core-i9-14900k-to...
Yes, but if you can squeeze more cores in the same space (and/or power) envelope, and not suffer a performance per core penalty, you're winning.
This feels like cheating to me.
I've read it has 12 channels of DDR5.
With smaller sticks, they could populate all the channels while keeping total memory capacity the same as other setups. I don't see why they had to splurge all the way up to 512GB.
Quoting the article:
"To celebrate the much-hyped launch, our sister site PCMag put the flagship CPU through its paces (remotely) in several popular benchmarks."
The people who did the benchmarks didn't splurge... they had no physical access to the remote machine at all. Certainly, it would have been ideal to talk to their remote contact and see if there were any 16GB sticks sitting around to test with instead, but I agree with the other comments that the memory capacity is unlikely to make a significant difference in these benchmarks.
There will certainly be plenty of other benchmarks soon enough, once people get hands on with these processors.
It is not possible to give all the systems the same memory configuration. They don't support the same memory and don't have the same number of channels. And I expect giving all the systems 512 GiB of memory would only widen the lead because larger DIMMs are usually slower.
>Do they expect all of their readers to then audit the code of the benchmarking that they are doing to ensure that it cannot possibly be bound by this?
Cinebench is hardly obscure. The average ExtremeTech reader will already know what it is and what it measures.
you want to max out memory channels on all devices to test max performance
but you also want to use RAM DIMs which are equally good, if possible the same
as AMD has more memory channels this means it will get more "equally good"(1) RAM DIMs and in turn have more memory
and as long as you make sure that no of your benchmarks perform pressure wrt. RAM capacity (e.g. max RAM usage 64GiB) you now have a fair benchmark wrt. max performance
naturally if you don't plan to max out your RAM channels on AMD you do need a different benchmark for non-max performance
(1): "equally good" is also a bit tricky as different vendors have slightly subtle differences in access patterns and DDR5 ram training also can make the same RAM run with different settings on different systems which can make the same ram dim not equally good, but there probably is some RAM which doesn't have such issues
No, the actual amount of RAM isn't directly relevant, but it seems like a possible brown m&m to me.
(https://www.snopes.com/fact-check/brown-out/)
That's exactly where the differences comes from you want to max out the available memory channels on each device not have the same number. Same for latency etc.
I mean your also not fixing the clock speed to 2GHz no boost or when comparing cars limit things just to the first 3 gears or similar.
Because if you would add such artificial limits you won't compare fairly how fast the _max performance_ can be, it would be a very different comparison and wrt. evaluating max performance very unfair.
Now you still need to e.g. have a fair choice of RAM, so preferably if possible use the same RAM sticks (and also use RAM which works equally well with both Intel and AMD). But what that means is that you _have to_ give the AMD system more RAM because it has more channels. Now you also _have to_ make sure that you benchmarks don't have any RAM pressure wrt. capacity.
Also I'm not sure why you mention cache misses? Because number of cache misses is quite independent of RAM amount? Do you mean disk cache or swap misses instead, but I don't think the benchmark does disk I/O and shouldn't have swap either? But even if the benchmark only uses let's say 32GiB of memory for getting a proper GPU
No. Adding that memory bottleneck would make it an unfair and worthless comparison. If you are testing the maximum CPU performance then you need to eliminate those bottlenecks, not create them.
But the memory is required there to populate the memory channel which push the CPU performance to max.
> not a GPU
Well, 3970x is able to soft-render DotA in 4k with 8-11 fps...
Wouldn't a cheap GPU be better for transcoding tasks?
Thus, the real question is how buggy these new CPUs will be. https://news.ycombinator.com/item?id=37812556
They're hopefully not using a CPU for that - that's all been on the GPU for years.
If you're doing something that follows the same general design as most existing video codecs, absolutely; these days "hardware" encoding is less "fixed function chip" and more "the driver/firmware knows how to stitch together these components so as to comply with the xyz standard" - hence you see support for new encoding standards getting added in driver updates. If you're doing some completely radical out-of-left-field video compression algorithm, maybe not, although even then GPU hardware is pretty general these days and video encoding tends to be well suited to running on it.
For simulation applications there is no such concept as "acceptable", the utility of a CPU scales linearly with how fast it can do the calculations.
CPUbenchmark is giving the new chip about a 100% improvement over the 3990x which is fairly tempting even at the 6-10k price tag I've seen floating around.
Our antenna design folks sends simulation runs to a group of R7525s with 2x EPYC 75F3 CPUs and 2x A100 80GB GPUs.
A small problem might have tens of millions of elements and billions of unknowns to solve and run on one server. Larger problems might be spread across all of the servers, after coordination with everyone else.
Simulations take 8-12 hours to run.
This is not acceptable.
Anything slower than "an amount of time imperceptible to even the most responsive human" is unacceptable.
Everything is too slow.
Networks are too slow, memory is too slow, storage is too slow, GPUs are too slow, and CPUs are definitely too slow.
I'd guess this wins in absolute performance (due to the TDP), but I've heard AMD is pretty competitive on energy efficiency too these days. I'm typing this on an M2, which is simultaneously cooler and faster than my old Intel laptop.
Wondering if it's time to upgrade my decade-old Intel Linux desktop to an AMD yet.
Of note is that Zen 2 (the 3970x's microarchitecture) is 7nm. The new Threadrippers are on a 5nm process. I would expect slightly lower power consumption, but note that the 7000 series of Threadrippers quote a TDP of 350W while the 3000 series quote 280W. So I'm guessing they're using the efficiency for more speed instead of more power savings.
To me, it's fine. I'd always prefer paying more for electricity than to wait longer for something to complete. (But I do respect the desktop chips that can blink my cursor with an efficiency core that uses a few tens of milliwatts.)
These monsters will do better than the 39xx because of the 6mm IO die. But it's still going to have high idle power compared to a monolithic Intel design.
The monolithic AMD dies (laptop/mobile) are competitive in the idle power space.
I don't know if the Zen 4 Threadrippers can be similarly run with a power limit. If they can, I'd expect much better efficiency than whatever Intel offers.
This has eco mode benchmarks: https://youtu.be/W6aKQ-eBFk0?si=o8l1qGUhSQKxmY_c
https://www.notebookcheck.net/R7-7840U-vs-M2_15023_14521.247...
The last benchmark is interesting but unfair given that's an ancient application with Rosetta.
No need to guess: An M2 Ultra will get around 27,000 in Cinebench R23 while this Threadripper will get around 100,000.
The M2 Ultra has a TDP around 90 watts (~ish according to a couple reviews) and this Threadripper has a TDP of 350 watts.
The stock configurations for a lot of desktop chips is to get the maximum performance at the expense of power, especially for things like these Threadripper series which are explicitly aimed at maximum performance. Often even drastically reducing power usage only gives modest performance penalties.
I also run an RTX 3900 GPU at 60% power for 80-90% performance. It's a noticeable decrease in requisite cooling.
Gamers Nexus did a video earlier this year comparing the 7950x at different eco modes and they found that putting the 7950x at a 105 watt eco made drop the performance around 5% but shaved almost 100 watts off of power. heres the link to the video https://www.youtube.com/watch?v=W6aKQ-eBFk0
I know why these companies do it and im lucky electricity isnt too expensive in my area but i rather shave 100 + watts of heat being dumped into my room (especially in the summer months)
Tl;dr, if you want the absolute performance on Desktop, get the Threadripper Pro.
AMD Zen 4 7800X3D, 5nm 5.04Ghz, Single Core GB6 Score @ 2833
Apple A17 Pro, 3nm 3.80Ghz, Single Core GB6 Score @ 2914
Well you can find that with Geekbench but it is very likely worst to publish it as it leads to a wrong conclusion without the basic understanding of Hardware or CPU.
The node and design whether it was tuned for Clockspeed ( Desktop ) or SoC ( Apple ). There are measurable percentage difference in the same core for Risen on desktop and Ryzen SoC. And then you have to factor in Wattage difference in Clockspeed they are operating at. You are expected to know all these basics before the scatterplot would even make sense.
The Desktop 7800X3D will likely use 20W+ in the test, while the Smartphone A17 uses at best 5W.
You will then also have to factor it a lot of these performance test are not sustainable without adequate cooling. i.e You can sustain the above performance for a very long time on 7800X3D, dont expect that on A17 inside a phone.
Many of these are pointing out the obvious. But it seems on HN we are increasingly required to do so otherwise it leads to some sort of flamewar.
For my m1, opening a vm or just plugging in a wireless mouse dongle is all it takes to shave several hours off the lifespan, like from 20 hours to 10.
For the amd laptop, anything waking up the nvidia gpu will do the same, like 10 hours to 3.
When you're talking such low amounts of power, the networking card, sound card, display efficiency, ssd efficiency, and whether the system chooses to run the fan or let the cpu stay warm starts to matter a lot since just like the cpu these are things that are running at the same time. So I guess a fair test would have to use the same ssd and have the monitor off, using an external monitor. Then you're just stuck with the efficiency of the parts of the motherboard you can't choose.
I find this whole thing super fascinating, coming from the perspective of Silicon Valley startups.
[0]: The Problem with Linus Tech Tips: Accuracy, Ethics, & Responsibility
[0]: https://www.youtube.com/watch?v=FGW3TPytTjc
The thing that I find so interesting is that they - for better or worse - essentially live stream their business decisions, challenges, and aspirations. Whether their endeavors are successful or not, I agree with their decision to try and move beyond Youtube and create their own video platform via Floatplane. They've also found success in alternative revenue streams via sponsorships from reputable brands and merchandising and are very open about their metrics.
Lastly, I really respect that they are 100% bootstrapped. I've only ever worked for companies that rely on investor funding for growth, and their influence often feels intrusive and counterproductive.
It's basically a AMD EPYC™ 9654 but with more clock boost speed and some differences wrt. IO (e.g. less but faster memory channels) and I think some differences wrt. enterprise features.
Something like StackExchange [1] could fit all their 9 server into 1 ( or 2 with one for redundancy ) without any degraded performance.
[1] https://stackexchange.com/performance
Nobody believes me, which says a lot about both the hardware and software industries.
I would be happy if Ruby Rails could do it in 2x the rendering time i.e slower with 2x Resources / Server. That is combined 4x difference. Unfortunately even with JIT we are not there yet.
That never gets old.