As a note, we're just finishing up this review at the very last minute due to us getting our hands on the reference laptop only in the last 48h. I'll be completing the missing page texts in the next few hours as we're tidying up the article.
Did you have a description/specs of the test systems? If it was there I missed it, even after going back to look. Differences in RAM / storage etc. can affect some tests.
I'm guessing the size based on the name of the Asus... Looks like you're comparing a 16" workstation vs a 13" thin/light?
Would the AMD CPU perform better in a larger/cooler chassis?
"Did you have a description/specs of the test systems?" A brief description of the Intel reference system is in this review, more detail of the AMD system is available in the review these test results came from.
"Would the AMD CPU perform better in a larger/cooler chassis?" A 45W variant of the AMD CPU in a larger chassis would see higher sustained multi-core performance, but single-core is probably quite similar.
Strange article Andrei. 5980HS is rated 35-54 W or 45W+. How can you judge that 45W Intel is less efficient?? Have you data about TDP settings of Asus X13 ? Likely the AMD SKU run at the highest TDP for more performance on Asus device, for several minutes or continuously. Bet you neeed to be more informed in your articles, OEMs can go at the max TDP of a cpu since the Tskin of the laptop allow this. Bet Intel Tiger Lake H will be faster than in your article on the right chassis ? Bet direct power measures are better than generic comments ?
Strange comment Gondalf. The graph of the 5980HS on page 2 shows that the Asus X13 runs at 42W for about 300s and then drops to 35W for the rest of the time. Bet you didn't read the article and just came down instantly to try and feel smug? Bet you need to be more informed when making hate posts?
He measured the power consumption, you pillock. It's right there in the review. Nice work getting your FUD on the front page though, round of applause for gondaft.
If Tiger Lake H will be better in "the right chassis", Intel really should have thought of that when they supplied this one. As things stand, it's clear that this chassis wasn't causing the CPU to throttle at 45W, so the only way it would perform better is in a chassis that allows for 65W - at which point you'd find AMD's CPUs performing better, too...
This is definitely what Rocket Lake should've been. If they just put this chip in a desktop package, so it could be run with a desktop power budget and cooling, it'd sure be a lot more interesting than it is inside a laptop.
it's probably more that they've tweaked their 10nm to hit high boost at the cost of efficiency. I think they increased their gate pitch with "superfin" so you end up with more performance scaling but also more power use. considering how far behind their desktop chips are compared to 7nm chips from AMD they may just be crippling efficiency across the board to get performance parity while their fabs lag behind. they don't seem to have high hopes for 10nm considering their target for market leadership is 2024 with 7nm.
laptop users generally stick with bursty operations or video games and in both cases raw throughput isn't as much of a concern. average user would probably not notice or even benefit from the high ST burst performance, but anyone planning on using it professionally would probably be better off with cezanne.
It would certainly be able to stretch its legs better there. It would be interesting to see whether it could handle running those higher boost clocks across more cores with a higher TDP. Guess we'll find out with Alder Lake.
I thought the same. This chip in a mini-STX case with a desktop cooler would make a great portable system. However, if it is having thermal issues with a full-size workstation laptop, it'll likely struggle in the smallest of SFF cases like the NUC.
the laptop doesn't look that that big. A nuc would have more vertical space for the cooling for example. It would also be easier to throw that heat out.
Uh, the mini-STX NUCs don't really have much space. Everything is packed in pretty tightly. Furthermore, they usually top out at 28 W.
For Coffee Lake, Intel made a larger system they called a "NUC", but I think they had actual Nvidia graphics cards in them and were bigger than a lot of mini-PCs.
no, that's not right, Tiger Lake is mainly clock speed improvements, not IPC, running Tiger Lake or Comet Lake in a desktop at the same 4.8GHZ all core would get you almost exactly the same performance
> Tiger Lake is mainly clock speed improvements, not IPC, running Tiger Lake or Comet Lake > in a desktop at the same 4.8GHZ all core would get you almost exactly the same performance
You're confusing Comet Lake with Ice Lake. IPC of Tiger Lake isn't much improved above that of Ice Lake.
I didn't mean that in a pointed way. If anything, I thought it would partially validate the statement.
And yes, I wish Intel would've left the Lakes behind with 14 nm, but I guess there are just too many "lake" names for them to part with it for the mere sake of naming consistency. More annoyingly, they're even using "lake" names for some things that aren't CPUs.
it seems they are staying with lake and cove names so unless you are using a slide ruler and a decoder ring, you have no idea which cpu is what :-) i gave up trying to keep track of their names are which cpu line a while ago.
> it seems they are staying with lake and cove names
Sapphire Rapids is the next server CPU. Also, the little cores seem to be Monts, while the big cores are Coves.
I think the biggest groaner is "Lakefield", which is that mobile CPU with one big core, 4 little cores, and a chunk of eDRAM. MS used it in a Surface model.
Indeed it is a big and crucial step as it is the first new arch and node on H45+ all predecessors where Skylake and 14nm iterations.
However a make or break will be AlderLake as bigLITTLE either is a game changer or an issue. Golden cove will be good but it really depends on the sheduling and Gracemont.
Especially on possible benefits on mobile run time and consumption!
It has platform advantages (i.e. PCIE 4, Thunderbolt) and if anticipated, great gaming performance. As a consumer, it is much better to have a choice with competitive processors. And there will be reasons to buy a Tiger Lake system when it comes up for review.
While it is nice that it supports gen 4, realistically you're just getting SSDs that put out more heat, with more power draw, while gaining performance benefits that are only measurable in benchmarks or very specific situations.
I'm sure file copy performance is much higher, but how fast do you need that to be? Assuming you're copying to the drive itself or maybe to a Thunderbolt 4 external drive, it is the difference between copying 1TB of data in 2 minutes versus 6 minutes. You can (theoretically) completely fill a $400 2TB SSD in 4 minutes with gen4 vs maybe 12 minutes with Gen 3. If someone needs to do that all the time, then sure there's a difference... but that has to be pretty uncommon.
For smaller amounts of data, any decent nvme drive is fast enough to make the difference between models almost unnoticeable. For the vast majority of users, even a SATA drive is plenty fast enough to provide a smooth and nearly wait-free experience.
> realistically you're just getting SSDs that put out more heat, with more power draw, > while gaining performance benefits that are only measurable in benchmarks > or very specific situations.
Well, you could copy full blast to an external drive and have plenty of remaining performance to do other storage intensive things - that's assuming your external drives is fast enough to suffocate PCIe 3.0 x4, and your internal drive is faster still.
Sequential read and write speeds are basically just flexing. Very few people actually ever make significant use of such speeds in a way that saves more than a second or two here or there. Most laptop users are not sitting there copying a terabyte of sequential data over and over again.
You're not getting those kind of speeds sustained in a laptop without RIDICULOUS thermal throttling. PCIe 4.0 in mobile atm is just a marketing checkmark & nothing more.
It allows faster "races to sleep" for the processor. And, since the Core2 architecture, the winning move was "fast and power hungry processor that does what it must and then goes to a very low power state". This gives you very good burst speed and low average power - as soon as you finish, you can throttle everything down (CPU, caches, SSDs, ...)
> It allows faster "races to sleep" for the processor.
Are we still talking about PCIe 4? I don't think it works like that.
> since the Core2 architecture, the winning move was "fast and power hungry processor that does what it must and then goes to a very low power state".
No, it's more energy-efficient to run at a slower clock speed. There's a huge difference between the amount of energy used in turbo and non-turbo modes. As it's far bigger than the performance difference, there's no way that going to idle a little sooner is going to make up for it.
It is from an M.2 gen 4 drive in a gaming laptop - ASUS ROG Zephyrus S17 GX703 (GX703HS model – Core i9 11900H + RTX 3080 140W, 4K 120Hz screen) but I get your point - at the moment, not many will need such speeds. Gen 3 will serve them fine. Please do not question the benchmark itself. Personally I got an AMD Ryzen 7 5800H-based machine myself, without waiting for Tiger Lake H45.
xpclient> It is from an M.2 gen 4 drive in a gaming laptop - ASUS ROG Zephyrus S17 GX703 xpclient> (GX703HS model – Core i9 11900H + RTX 3080 140W, 4K 120Hz screen)
BS. Look at the numbers: you cannot do 10.5 GB/s read or 9.8 GB/s write over PCIe 4.0 x4.
I don't know what it's from, but it's no mere x4 drive. Maybe a 4-drive RAID-0 or something like that.
@mode_13 Those scores are from a laptop that comes with a 3-drive RAID-0 config, which is - quite frankly - an absurd setup to have by default for a gaming system.
@mode_13h and @Spunjji, my apologies. I didn't notice the 3 drive RAID config in that review article of an ASUS laptop and missed that completely. My bad.
> let's not forget that Intel was 2 years late to PCIe4 on DESKTOP
It's there now. If you weren't in the market for a new PC in the past 2 years, what does it matter?
> and Intel fans didn't seem to mind.
Not even just Intel fans. AMD was early with their PCIe 4, on the desktop. That's why they caught Intel by surprise. Because, at the time, PCIe 3 was good enough. We're only just starting to see some minor advantages for PCIe 4, on the desktop. It's no game changer.
Honestly, of all the criticisms you could make of Intel, this is one of the weaker ones.
> it's almost one could skip PCIe4 if early 2022 PCIe5 is stable ... on mainboards?
Uh, I'm still eager to see exactly how Intel is going to use PCIe 5, in Alder Lake. I suspect it'll be used only for the DMI link to the chipset, in fact.
Since graphics cards and M.2 SSDs aren't even close to maxing PCIe 4, I struggle to see why they would bother with the added cost and potential issues of supporting 5.
"and if anticipated, great gaming performance"... Inside this notebook case he had a hard time controlling the temperature, if you add a 100W GPU, where is the rest for this cpu? mmm .... it's going to be interesting.
Most OEMs still prefer Intel as it has capacity that AMD can't offer and even more it has better features and integration such as AV1 coding, USB / TB 4.0, Intel WIFI etc.
Also Intels provides better support for OEMs in design and issues.
AMD systems can provide TB support, there's no technical limitation preventing it. Intel WiFi chips are standalone cards, which also work fine in AMD systems (my AMD board has Intel WiFi). There's no reason to use an Intel CPU for either of those features.
The fact that not a single AMD laptop has thunderbolt, points to an issue with cost of implementation/PCI lanes limitations etc. which apparently doesn't exist on Intel CPUs, given how many Intel laptops come with TB as default. This is a fact, and talking about what's possible theoretically doesn't change the facts that AMD systems lack TB
> The fact that not a single AMD laptop has thunderbolt, points to an issue with cost of implementation/PCI lanes limitations etc.
Perhaps. Or it's simply a reflection of the fact that there is only niche demand for TB.
It's on Intel based laptops because it's supported by the chipset so pretty much a no-brainer (or alternatively, Intel mandates it is included, in order to try and make it more relevant?)
However the vast majority of laptop consumers don't need, want or care about TB, so the extra cost to include it in AMD laptops doesn't appear justified. I'm sure a vendor could include TB on an AMD laptop if they ever thought they'd get a reasonable return on the extra cost.
And maybe now that Intel have been kicked in to touch by Apple, Intel might lose interest in TB in future.
TB has its fans, but it also has the distinct whiff of being the next FireWire.
power draw on a laptop is always going to be paired with battery capacity. It's about battery life right? Or maybe its about the heat on the bottom of the laptop. End of the day its mostly down to laptop design. The power consumption is likely to be transparent to the end user.
Not exactly. Between availability and incidentals like Thunderbolt, there are now reasons to opt for Intel where before they were nowhere near as compelling.
I'd still err on the side of AMD as I prefer efficiency, but I'm sure others would go the other way.
LOL. No, it is not competitive. >90W boosts is NOT competitive. In long gaming sessions, its UNcompetitive power hungry soul is going to hamstring the GPU that shares thermals in a notebook chassis.
And even with its increased power envelope, 8-core Tiger Lake H's multicore performance falls short of the best 8-core Ryzen 4000 series CPU (Ryzen 9 4900HS).
No, not really. This is Intel's REFERENCE SYSTEM and it only trades blows with an AMD system that is a product. How is this competitive? You have to realize that the fans on this system aren't tuned for a consumer, they are tuned to make Intel's processor look better. If you read Andrei's conclusions, it is a processor for a laptop no one is selling anymore. It is a 65W processor battling a 35W processor.
Their are two reasons this may sell well. AMD's systems are still hard to find and the fact that many consumers still believe that the Intel Inside label is important.
> You have to realize that the fans on this system aren't tuned for a consumer, > they are tuned to make Intel's processor look better.
Not to argue with your main point, but it's worth noting that even when Intel gets to design their own thermal solution, it still fell on its face @ the stock 65W settings. That's pretty bad.
Maybe they should've had the team design it who rigged up that Cascade Lake workstation demo to run all cores at like 5 GHz. Sure, it'd have been the size of a briefcase and sounded like a leaf blower, but at least the it'd clock well!
Just to make it clear and visible: The i9-11980HK is advertised as a default 45W CPU. The fact that the system came in 65W mode shouldn't be seen as a "stock" behaviour of that SKU.
@mode_13h - they did that with their previous Ice and Tiger Lake reference platforms (100% fan speed constantly, yes please) so it makes sense they did the same again here. 😬
Another thing to consider is that Intel platforms have been much more stable, for me, than AMD. My ASUS G14 with the Ryzen 4900HS, for example, *can* deliver both outstanding battery life and amazing performance. However, there are often times when the system draws extra power for seemingly no reason. There are whole forums dedicated to tweaking the G14's power settings to fix high idle draw. I've also experienced some weird freezes, lockups, etc. It's a great laptop, but I wouldn't use it in a professional setting where I need it to work all the time.
My i7-10810U powered Dell Latitude 9510, while quite slow in comparison, gets 12 hours of battery life every time and can run days at a time without any hiccups.
> "Intel platforms have been much more stable, for me, than AMD"
LOL. Even with Xe, I still see major graphical issues with 3D games which in some cases even refuse to render. It has gotten way better than five years ago, but AMD's graphic drivers are still far and away better. Stop reaching...
This reply doesn't really contradict morello159's main point, though.
I've had similar experiences - my 8th gen Intel Dell work system is rock solid, if unspectacular. My 4800H + 5600M Dell gaming system has... issues. A lot of them appear to be Dell's fault, TBH, but not all of them are.
You are comparing a gaming laptop against a high end professional laptop. First the 4900HS is a 35W CPU and the 10810U is a 15W CPU. If both laptops have equally size batteries, the one with the lower TDP "should" have longer battery life. On top of the the G14 has a 120Hz display and a dGPU. Both of those will pull extra power and the screen was specifically talked about in reviews of the laptop. Setting the screen to a 60Hz refresh rate instead of 120Hz significantly increased battery life. Finally the weird freezes is most likely due to the dual GPU design and switching between the iGPU and dGPU. Unless you are using so much RAM that you are page swapping.
@schujj07 I have the same zephyrus laptop as morello159. I haven't experienced weird freezes when switching between gpus on mine, or my old laptop with an intel processor and nvidia gpu, so optimus working isn't likely to be causing the freezing. The random high power draw is a valid complaint though. I think the randomness is caused by Asus's turbo settings, which was mostly fixed by me modifying power limits and disabling turbo. But, the default experience is the processor randomly boosting ridiculously high when it should be in a near idle state and not clocking anywhere near as high. Like the chip randomly pushes all 8 cores to 3.8Ghz, when it should be running in the 1.4-1.7Ghz range.
They are trading blows in performance, but AMD is doing that on 35W instead of 45W for Intel. For manufacturers that use the same chassis with Intel AND AMD processors, the Intel one will run hotter, be noisier and/or have lower battery life when working hard (I don't seem to find anything related to idle/low power consumption).
I'm sorry, but your SPECFP2017 results are just wrong. There is no possible way that the 1185G7 is faster than the 11980HK by 2x in 503.bwaves
That's just absurd, especially when every other test bar 3 shows the exact opposite results, and even of those that show similar results it isn't nearly to the same degree baring 549.fotonik, and that one has the 4900HS somehow being faster than the 5980HS.
The 1185G7 being twice as fast is a little questionable, and possibly the results for the Tiger Lake processors were switched accidentally.
As to the 4900HS being faster than the 5980HS in one very specific subtest, I suppose companies have never released a new CPU architecture slower than the old one. That's why Bulldozer was well received for its incredible performance over Thuban. Rocket Lake was well loved for consistently beating Comet Lake and Zen 3 in gaming, with the 11900K always at the top of the chart. Broadwell-S of course isn't better than Skylake or competitive with Coffee Lake in gaming.
Keyword "almost" Zen 3 does not win every benchmark over Zen 2, just the vast majority of them due to superior clock speeds and IPC. In 1 very specific subtest, out of all the test conducted, is it really unreasonable to see the older architecture get a win. The last time I can think of a new architecture winning every single benchmark was Conroe. Sandybridge might also get this title with workloads that didn't need more than 4 cores, but I don't exactly recall. Remember IPC is an average of performance at a given frequency, so if a few benchmarks have negative improvements in IPC, but most have large positive improvements, you can easily see a 20% IPC uplift.
Vermeer was consistently faster than Matisse, but Milan was not consistently faster than Rome. Cezanne is faster than Renoir in all but 1 subtest. All 3 comparisons are Zen 3 vs Zen 2. Also SPEC isn't an actual workload by the standards of it's something people run for work or entertainment. It's just a series of industry-standard benchmarks to evaluate the performance of processors. In all of the real workloads Cezanne wins.
Rocket Lake was well loved.... by who? it was universally panned by reviewers. the lower end sub-$300 i5 may be good value, but that's about it. the high end parts not only lose to Zen 3 but loses even to CML in some cases.
I find that his Spec testing has gotten worse and worse over the years. Andrei honestly just don't know how to use the suite and it almost always makes some parts look better than others when they really shouldn't be. Just look at the M1 tests for that, where the single thread perf in SPEC vastly exceeds that scene in any other test.
You're welcome to demonstrate what is flawed with actual technical arguments.
The M1 exceeds because it's that good, we're missing it in many other benchmarks simply because they aren't ported to macOS or currently don't have data on them.
Single thread performance seems to align quite well with other tasks! Look at Cinebench single thread performance. Look at compiling performance. Look at javascript performance, etc, etc!
" Name a single workload where the spec results line up with application performance" post a single link that shows you are right, and Andrei is wrong, as so far, it seems you are just typing FUD. personally, im going with Andrei.
I've added in the text to those pages now, and I explain why they would end up like that.
The TGL-H system has half the memory level parallelism with its 2x64 DDR4 channels versus the 4x16b LPDDR4 channels of the TGL system, and those two workloads are characterised by heavy parallelised memory bandwidth.
We've seen a 66% performance difference on a 5950X between 2x SR and 4x SR DIMM memory in the MT test, it all depends on the DRAM configuration and what kind of parallelism it allows.
Our testing is correct and we have the correct understanding of the microarchitectures and workloads.
The compiler settings are literally on the SPEC page and have been there the whole time, and have been set in stone on the Windows side for over a year now for every article.
Outlier results should be investigated and understood. They might be very informative of edge cases. Or, they might indeed expose procedural errors in the testing. Either way, your attitude of dismissing them as erroneous and abusing the testers is not helpful.
It's fine to call attention to anomalies and ask questions, but abuse is not called for and shouldn't be tolerated.
And every time I've demolished the unsubstantiated empty argument with data and facts. If you do not have any actual technical argument to make then don't make any.
I have to back up Andrei here. You've only given us hyperbole so far. Which compiler settings do you have a problem with exactly? As a former Gentoo Linux user, I don't see a problem with them. Of course, -Ofast shouldn't be used in a production system -- but he is benchmarking here.
Incidentally, I have a Phenom II motherboard that allows me to configure page-granularity interleaving. Not sure how common it is, but I don't think my Intel workstation board gives me that option!
So, you want a suite of benchmarks that all behave similarly and don't stress the platform in various and different ways?
Suit yourself, but I think a good benchmark suite should have enough diversity to hit different edge cases, as long as it's not doing anything unrealistic. And, as far as I can tell, the SPEC 17 tests are entirely comprised of real-world programs.
Interesting how much power Tiger Lake H needs to draw to be competitive with Cezanne. At this point it's clear that Intel's big cores are bloated when AMD has higher IPC and frequency at lower power draw with a comparable node. Little cores in Alder Lake may help with efficiency, but they are taking power budget away from the big cores which hurts their frequency. Intel probably needs to redesign their big cores from the ground up rather than continuing to refine and improve Pentium-M.
On a side note I'm conflicted on your decision to omit AVX-512 on NAMD. On one hand you are not testing AVX-512, but on the other hand you are omitting a possibly real world scenario for someone. Intel's marketing on AVX-512 and its inclusion in consumer processors are questionable choices, but that still is a valid, functional feature built into the chip. Perhaps a good compromise would be to add in the updated version for AVX-512 processors only.
Most workloads that can run avx256 can easily be extended to AVX-512. In some cases, you need just to recompile with AVX-512 optimization floag on. Even Skylake-X and cascadelake-X there is a noticeable improvement in performance in AVX-512
And that's why if there is an option to run AVX-512, I'd like to see it being run. Also with the massive efficiency deficit of Tiger Lake, and AVX-512 requiring even more power, it's plausible Cezanne might be competitive at the same power limits. Although with NAMD, I'd expect Tiger Lake to top the chart.
Depends on how well the compiler can vectorize your workload or if you're using something like OpenMP. However, if I really wanted max performance from AVX-512, I'd be using the intrinsics.
BTW, it's worth noting that you can't simply disable AVX-512 with build-time compiler flags, for software that performs runtime code-generation (usually via LLVM). Many popular deep learning frameworks fall in this category.
I actually ran that test myself in my university lab. we ran AI workloads and vectorized workloads on avx2 and avx512. Running avx512 on all threads would result in a significant clock drop, but despite this, I was testing 20% faster than AVX 256 (they were using the same power ~200 watts). When you mixing several workloads (AVX and non-AVX), you don't see the same drop unless more than 50% of the cores are running AVX. Granted this is anecdotal evidence, but I think the power budgeting across the chip was working well to maximize performance.
> I actually ran that test myself in my university lab. we ran AI workloads and vectorized > workloads on avx2 and avx512. Running avx512 on all threads would result in a > significant clock drop, but despite this, I was testing 20% faster than AVX 256 > (they were using the same power ~200 watts).
Depends on your network architecture. We saw the opposite, and this was confirmed by engineers at Intel. To resolve the problem, they sent us a patch to disable AVX-512.
> When you mixing several workloads (AVX and non-AVX), you don't see the same drop > unless more than 50% of the cores are running AVX.
I'm talking specifically about AVX-512. And when I had a lot of threads using it for maybe only 10% of the time (different scenario than above), I also saw clock drops big enough to decrease overall system throughput.
This was all on 14 nm CPUs, so I'm eager to try Intel's 10 nm chips.
> I'm conflicted on your decision to omit AVX-512 on NAMD.
Let's remember that this is a notebook processor. Sure, it's what most Intel-based mobile workstations will probably use, but most users of this processor aren't going to be recompiling their apps with -march=native.
In other words, I think the case for testing AVX-512 on this CPU is a lot weaker than on server CPUs or even desktop processors.
Frankly, while power consumption is a big problem and we know 10nm is not that great, the performance is good and actually intel providing a reference system for review is a good sign.
They've provided reference systems for launches twice before now - with Ice Lake and Tiger Lake (U) - and for both of those launches, the reference system outperformed comparable devices available at retail. Given that history it's not surprising they pushed this out with a 65W TDP, but it is very amusing that the cooling system couldn't handle it.
Thanks for the review guys! It beat a laptop half its weight by only 7-10% while using 25% more power...
The ROG X13 is awesome but its only 2.8 lbs and 16mm thick. That 16" inch Intel machine outclassed it thermal capabilities easily and likely weighed in at ~6lbs... Looking forward to reviews in comparable chassis.
Glad to see the performance is there, but too hot and power hungry for a laptop. 10nm Superfin, still cant catch TSMC 7nm, with 5nm coming soon...
Hopefully, Alder Lake rectifies the power efficiency gap between Ryzen 5000 and Tiger Lake because... yikes. Now, I can see why 8-core Tiger Lake was mysteriously held back for so long. These 90-95 degree temperature peaks are going to seriously hamper GPU performance in the shared thermals of a very compact notebook chassis. Never mind that 8-core Tiger Lake's peak power exceeds AMD's own Ryzen 5600X desktop part.
And even with its increased power envelope, 8-core Tiger Lake H's multicore performance falls short of the best 8-core Ryzen 4000 series CPU (Ryzen 9 4900HS).
quite surprising. considering the performance of quad core tiger lakes, i estimated the Intel eight cores to be on par or easily beat AMD. it also doesnt seem Intel will be selling the 6-8 cores at lower tdps soon
They had to hit high clocks to get that performance, at a disproportionately high power cost. With 8 cores going at once, they simply don't have the thermal headroom.
Intel's 8C "mobile" chip is not worth the money ...
Unless you have some badly optimized code, where the extra ST performance will out weigh the extra money spent for Intel, the increased heat generated, the lower battery life and the bulkier / heavier laptop.
The M1 Mac mini peak power makes no sense in that graph! You are comparing the Mac mini Total Power Draw on the Wall, with other devices’ CPU peak power - clearly completely different things.
I think that was a leftover from Ian or a misunderstanding, the M1 does have around 32W peak package power, but you're right, CPU only is only around 21W, I've edited that.
This is not surprising, and it is in line with the TL-U results. I think TL-U is a compelling option, but given the possibility, I'd go for an AMD-based laptop: 30 more minutes of battery life are well worth 7-10% single-core performance disadvantage, all the rest considered. IMHO.
Damn I still expect a little bit better (or much better) result from H45. Many Core i7 10870H can reach 1.600+ points on Cinebench R15 MT. We suppose to wait for final product. But still too disappointing :(
Fortunately intel will trading blow with AMD today and for the rest of 2021. Intel can't be strong enough to compete with AMD if they haven't TGL-H45 series
Ask people who run demanding games or run heavy workloads on their laptops (who are precisely the market for this thing) and you'll probably find they spend most of their time plugged in.
I myself have a desktop replacement laptop that I use almost exclusively plugged in. When it's plugged in I certainly care about noise, but I don't care about power usage. However I do sometimes use it on battery power, both on power hungry tasks (with which I try to have it plugged in when running) and less power-hungry tasks. That's when battery life, and hence power draw, becomes important to me for the laptop.
So, although I use my laptop mostly plugged in and I do care about power draw, the power draw I care about is almost entirely for when the laptop is unplugged. And of course I also care about the performance I get for that power draw in those situations. The noise factor must be considered exclusively laptop to laptop, so looking at power draw in plugged in situations isn't very useful. And frankly, I can't see a good reason that many consumers to be looking at the situation differently and would be concerned about the power draw of the laptop when plugged in.
Should read "And frankly, I can't see a good reason for many consumers to be looking at the situation differently such that they would be concerned about the power draw of the laptop when plugged in."
I'm not saying that plugged in power usage is useless to consider, just that it seems to me much less important, as far as power-usage is concerned (even for a desktop replacement) than battery-powered power usage and performance. Maybe others feel differently but I don't understand why. It's not like any laptop is a real power hog unlike some desktop systems can be. We're talking about, what, plus-or-minus 20 watts here? 30 watts? 30 watts plugged in means nothing to me. Does it mean a lot to most others, and if so why?
But that varies widely from laptop to laptop. And it's not just a function of the heat output, it's a function of the cooling system, which is related to both cost and weight. So you don't really get helpful information for noise or throttling just by looking at plugged-in power usage.
Is there a reason why TGL-U is referred to (somewhat confusingly) in the article as just TGL? I know Intel (also somewhat confusingly) uses the TGL-U 4+2 LP die for three separate platforms (UP3, UP4, and H35), but they're all still considered TGL-U, aren't they? Whereas Tiger Lake is the codename for the whole range of processor families including UP3, UP4, H35, and H.
@Andrei Frumusanu : how is it that the amd 5800x (and others) spec2017fp_r results differ by as much as 7 points while the spec2017int_r values are basically on point? (there seem to be minor differences for the 49/4800U in spec2017int_r values too. plus large diff for the i9-10900K).
In that article we were using only the C/C++ sub-benchmarks due to not having a functioning Fortran compiler on the M1 at the time. So it's apples-and-oranges in terms of the scores between the articles. The integer suite only has 1 Fortran workload, the FP suite has much more.
Since, I've rerun the M1 ST scores on a vanilla LLVM and Gfortran toolchain to get all workloads, and anyhow all articles except for that initial M1 piece have the full subset of workloads. The M1 MT scores are missing from this piece as I never ran that (brainfart) and no longer have an M1 system at hand.
As far as I know the results in the Mac mini review aren’t the full SPEC 2017, because some tests require a Fortran compiler that didn’t exist for the M1.
I find it hilarious that a desktop CPU 5600x maybe even the 57/5800x would be about the same if not better power consumption with better performance LOL especially performance per watt lol.
I would assume because desktop cpus are typically tuned for performance at the cost of efficiency, and mobile processors are tuned for efficiency at the cost of performance. Power efficiency still does matter when plugged in for cooling purposes. Tiger lake needing a lot more power to deliver equal performance means higher temperatures, louder fans, or a more expensive cooling system.
> I would assume because desktop cpus are typically tuned for performance at the cost > of efficiency, and mobile processors are tuned for efficiency at the cost of performance.
I think we've established that the H-series processors are basically desktop chips in a BGA package.
> Tiger lake needing a lot more power to deliver equal performance means higher > temperatures, louder fans, or a more expensive cooling system.
Yup. Loud fans are why I disabled turbo on my H-series Dell Precision laptop that I use for work. The only thing I hate more than performance bogging down is screaming fans in my face. And yes, I have used pressurized air to blast any dust and debris from the cooling channels.
Also, a better cooling system tends to add bulk and weight.
One spelling comment, you have "GP Us" instead of "GPUs" on the first page, I use Text to speech, easy to catch it with that. Sorry to be the spelling guy. Thanks!
Also on the last page should be "Where things aren't" not "Where things are quite as straightforward, is the multi-threaded performance, as this is where we have to mention TDPs, power limits, and just the result of the Intel reference platform laptop we’ve tested today."
Thank you for the indepth review! Interesting stop gap to Alder lake, With apple in the market with a pending M2, going to be a very interesting space to watch.
Just wondering but could there be a comparison to an AMD 5800x or something like that just to put an idea on the power draw for the performance/ performance per watt? I was kinda curious after reading through the article a couple of times.
A key question is now if Intel can further improve its 10 nm superfin process in time for Alder Lake. This TL is at least getting somewhat close to AMD's monolithic Zen3, but Rembrandt is around the corner, and that'll be an even more capable competitor. Right now, Intel retains its market share mostly because AMD can't deliver as many CPUs as people would buy.
I'm looking forward to an i5 or i7 design with no dGPU and that sweet embedded TB4. Probably going to be a small subset of the offerings like the lower tier XPS 15/17. Interested to see what comes about later in summer.
I want to see a comparison of the 11980HK with the 5800X clocked down to 65W, apples to apples. Let's compare the thermals of the AMD 8-core desktop to this "desktop replacement" Intel 8-core.
Just to add some further insight on these two charts, here is some breakdown. What ultimately happens is under sustained heavy loads, Ryzen 5000 series can maintain 8 cores at higher sustained clock speeds (~3.7 GHz) with lower power draw (35W). Bear in mind also that Zen 3 has a slight IPC advantage over Tiger Lake, meaning at a lower clock speed, it performs the same or does the same amount of work as Tiger Lake at a higher clock speed. Yet here we are where Ryzen 5000 can clock higher, do even MORE work, and draw less power. Meanwhile, Intel is struggling to reach similar sustained clock speeds (~3.2 GHz) at 45W sustained and it has slightly lower IPC. That is, Ryzen 5000 is ~10% faster clock-for-clock (or in IPC) than Intel's Willow Cove (Tiger Lake 11th Gen), Cypress Cove (Rocket Lake 11th Gen) or Sunny Cove (Ice Lake 10th Gen) which all three share roughly the same IPC amongst the whole trio (link: https://www.guru3d.com/articles_pages/intel_core_i... ). Ryzen 5000's synergy (higher clocks, lower power, higher IPC) sounds like a recipe for disaster for Intel, no? Alder Lake needs to come sooner rather than later if you ask me. Let's just hope Intel is throwing the full weight of their massive workforce of software developers at the problem of Alder Lake's heterogenous architecture because they will certainly need it working smoothly for it to shine.
It's a very odd choice. But then, didn't they use MSI for the original TGL reference platform too? That one actually outperformed most shipping devices, although IIRC it did so by running the fans at 100% 🤷♂️
I put it on twitter also but my opinion is that the Tiger Lake MSI design is actually about the cooling and size that MSI would use for an H series processor normally, such as the MSI Creator.
This implies that the MSI's thermal overhead is pure luck on Intel's part in that MSI didn't have time to reduce the thermal performance accordingly.
FWIW, I think there *is* a distinction and that the laptop is really a reference design. If Intel were selling their own laptops, then you could call a pre-release laptop an "engineering sample". If it's just a demonstration vehicle for their chips, then it's a "reference design".
Where the waters could get muddy is if Intel's lawyers have a lot of scary contracts threatening to sue you into oblivion if you sell on an engineering sample, as sometimes happens. And maybe they just chose to call the laptop an "engineering sample", so they could reuse those same legal agreements, rather than having to edit them so they instead apply to its reference boards/laptops.
How confident are you with that Compile test result? You have the i9-11980HK at 86.9 compiles per day which is a huge jump higher than the best desktop CPUs listed on your benchmark page (the best of which is the i9-11900K at 77).
Intel is about 1.5 years behind the competition. Once their 5nm fab starts puking out some silicon, we might see them return in the fold. But that's like 2023 or even 2024. Until then, accept the fact that Intel HAS competition.
LOL. I used to work with a guy who used another bodily function as an analogy for the operation of a systolic pipeline. You wouldn't have to think very hard to guess it.
Ice lake having a lower density isn't demonstrative of differences in process density. When designing Sunny Cove, the engineers may not have cared about density, and instead focused on performance and efficiency, resulting in Sunny Cove being less dense than Palm Cove (Cannon Lake). Intel's 10nm being slightly denser than TSMC's 7nm also doesn't mean that it is more efficient. When moving from TSMC's less-dense 7nm to Samsung's more-dense 5nm, mobile SOCs appeared to suffer from a regression in efficiency. Intel needs a node that is both performant and efficient and better engineering because their architectures are clearly less efficient than the competition. Golden Cove might fix Willow Cove's poor density and performance per watt, or we might be waiting till 2023-4 when Intel expects to be properly competitive again.
Intel's 10nm is indeed competitive with TSMC 7nm in terms of density, but AMD will be moving to 5nm with Zen 4 next year, what can Intel's response be? They can increase outsourcing to TSMC but that means less utilization of their own fabs which is bad. They absolutely won't be able to get 7nm ready in time to compete with AMD on TSMC 5nm. It will be back to the status quo of Intel lagging behind AMD by one full node, and likely foregoing power efficiency for performance parity.
no actual semiconductor professional expected Intel 10nm to surpass TSMC 7nm in any tangible way. the only people who expected otherwise are uniformed enthusiasts (usually gamers, who the to be partial to Intel)
I feel this review concludes that Intel have effectively lost their competitive edge when their fab started to lag behind. In fact, its also conclusive that the SuperFin is really nothing super at all even when compared to TSMC's 7nm. Its just 10nm on steroids just like what they have been doing to their 14nm. From an architect standpoint, Willow Cove is decent, but the bulk of the performance is due to pushing for very high clock speed at the expense of very high power consumption. If this was released on a desktop, it will be a hit. But on mobile, I don't think one can easily find a laptop that have the cooling capability to tame the heat output and also maintain a decent battery life. Especially this processor will likely be paired with a high end GPU. To me, this is a worrying trend for Intel because they will likely have to stick around with 10nm for another couple of years at least. If their new CPU architect is unable to provide decent IPC gains without bursting the power limit, they will surely be in trouble, especially when AMD's 5nm chips may appear in the market first.
Ah the M1 fastest CPU ever, doesn't make it to SMT SPEC scores for some reason, like always. Don't worry we will see the Apple CPU which would be X version of the chip iteration when it finally catches up to the SMT of these SMT until then M1 is the best CPU ever.
TGL machines will throttle to peak with the thin and light garbage heatsinks. That's a given, people should stop buying these parts. Laptop batteries will be destroyed eventually and none of them will have the Dell Desktop Power plan only Workstations have that feature (Lenovo and Dell), Alienware used to have, not sure about now their A51M R1 and R2 also they had their GFX modules smoke, anyways the battery won't be available for the end user to service and the expensive machine will die and BGA with soldered HW to further limit everything, add the overheating NVMe SSDs due to poor ventilation, happens in Alienware machines too which are targeted as maximum performance.
This ended up how I was expecting - superior single-core performance where there's thermal headroom, dropping down to broadly competitive multi-performance at the rated TDP, and with a faintly ludicrous maximum power draw under all-core boost.
I'm glad it's competitive. That's needed. What I'm a little less glad about is that we're almost certainly in for another round of CPU performance varying *wildly* between different designs, which has been true to some extent for a while, but getting steadily worse ever since Ice Lake showed up.
Given most OEMs' approach to cooling, I'd wager that the average device shipping with Cezanne will provide better CPU performance than the average device with Tiger 45 simply because of Cezanne's greater efficiency.
Heard they enabled undervolting again for tiger lake-h, can anyone confirm? I wonder how much undervolting potential there is and if that could balance the equation against AMD.
"The performance lead against AMD’s strongest mobile CPU, the 5980HS"
The 35W R9 5980HS is NOT AMD's strongest mobile CPU Brett. That would be the 45W unlocked & higher clocked R9 5980HX. I expect better from AnandTech... -_-
It is a little bit complicated... the 5900HX appears to beat the 5980HS by a little way in multi-thread tests but fall behind in single-thread, and if you look at things in performance-per-watt terms the 5980HS is easily the strongest. There's also the fact that there don't seem to be any shipping devices with the 5980HX in them. Strange times.
Not really. NUCs normally use the U-series notebook CPUs. That's all a NUC is -- a notebook CPU in a compact enclosure.
NUC Extreme is something completely different. They're more like a normal desktop PC, and the latest NUC Extreme that Intel just announced is the one that will use these H-series CPUs.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
229 Comments
Back to Article
Andrei Frumusanu - Monday, May 17, 2021 - link
As a note, we're just finishing up this review at the very last minute due to us getting our hands on the reference laptop only in the last 48h. I'll be completing the missing page texts in the next few hours as we're tidying up the article.EliteRetard - Monday, May 17, 2021 - link
Did you have a description/specs of the test systems?If it was there I missed it, even after going back to look.
Differences in RAM / storage etc. can affect some tests.
I'm guessing the size based on the name of the Asus...
Looks like you're comparing a 16" workstation vs a 13" thin/light?
Would the AMD CPU perform better in a larger/cooler chassis?
timecop1818 - Tuesday, May 18, 2021 - link
> Would the AMD CPU perform betterlol
Spunjji - Tuesday, May 18, 2021 - link
> timecop1818lol
Qasar - Tuesday, May 18, 2021 - link
gotta love timecrap181...at_clucks - Wednesday, May 19, 2021 - link
Come on, the Intel CPU actually performs decently... for a slowish desktop CPU stuck in a laptop chassis. Still not that bad.Spunjji - Thursday, May 20, 2021 - link
It performs very well, but timcarp1488 was completely misreading what had actually been said just to shitpost his usual anti-AMD nonsense.Spunjji - Tuesday, May 18, 2021 - link
"Did you have a description/specs of the test systems?"A brief description of the Intel reference system is in this review, more detail of the AMD system is available in the review these test results came from.
"Would the AMD CPU perform better in a larger/cooler chassis?"
A 45W variant of the AMD CPU in a larger chassis would see higher sustained multi-core performance, but single-core is probably quite similar.
Gondalf - Wednesday, May 19, 2021 - link
Strange article Andrei.5980HS is rated 35-54 W or 45W+. How can you judge that 45W Intel is less efficient?? Have you data about TDP settings of Asus X13 ? Likely the AMD SKU run at the highest TDP for more performance on Asus device, for several minutes or continuously.
Bet you neeed to be more informed in your articles, OEMs can go at the max TDP of a cpu since the Tskin of the laptop allow this.
Bet Intel Tiger Lake H will be faster than in your article on the right chassis ?
Bet direct power measures are better than generic comments ?
Retycint - Thursday, May 20, 2021 - link
Strange comment Gondalf.The graph of the 5980HS on page 2 shows that the Asus X13 runs at 42W for about 300s and then drops to 35W for the rest of the time.
Bet you didn't read the article and just came down instantly to try and feel smug?
Bet you need to be more informed when making hate posts?
Spunjji - Thursday, May 20, 2021 - link
He measured the power consumption, you pillock. It's right there in the review. Nice work getting your FUD on the front page though, round of applause for gondaft.If Tiger Lake H will be better in "the right chassis", Intel really should have thought of that when they supplied this one. As things stand, it's clear that this chassis wasn't causing the CPU to throttle at 45W, so the only way it would perform better is in a chassis that allows for 65W - at which point you'd find AMD's CPUs performing better, too...
5j3rul3 - Monday, May 17, 2021 - link
It's a big step to intelM1 and Ryzen 5000 are powerful, Intel need more pros to getting the leading performance
mode_13h - Monday, May 17, 2021 - link
This is definitely what Rocket Lake should've been. If they just put this chip in a desktop package, so it could be run with a desktop power budget and cooling, it'd sure be a lot more interesting than it is inside a laptop.Exotica - Monday, May 17, 2021 - link
Yields may have been the primary concern.mode_13h - Monday, May 17, 2021 - link
I get why they didn't do it, but it's clear to me this chip really wants to be a desktop CPU.whatthe123 - Monday, May 17, 2021 - link
it's probably more that they've tweaked their 10nm to hit high boost at the cost of efficiency. I think they increased their gate pitch with "superfin" so you end up with more performance scaling but also more power use. considering how far behind their desktop chips are compared to 7nm chips from AMD they may just be crippling efficiency across the board to get performance parity while their fabs lag behind. they don't seem to have high hopes for 10nm considering their target for market leadership is 2024 with 7nm.laptop users generally stick with bursty operations or video games and in both cases raw throughput isn't as much of a concern. average user would probably not notice or even benefit from the high ST burst performance, but anyone planning on using it professionally would probably be better off with cezanne.
Spunjji - Tuesday, May 18, 2021 - link
It would certainly be able to stretch its legs better there. It would be interesting to see whether it could handle running those higher boost clocks across more cores with a higher TDP. Guess we'll find out with Alder Lake.Lucky Stripes 99 - Monday, May 17, 2021 - link
I thought the same. This chip in a mini-STX case with a desktop cooler would make a great portable system. However, if it is having thermal issues with a full-size workstation laptop, it'll likely struggle in the smallest of SFF cases like the NUC.Azix - Monday, May 17, 2021 - link
the laptop doesn't look that that big. A nuc would have more vertical space for the cooling for example. It would also be easier to throw that heat out.mode_13h - Monday, May 17, 2021 - link
Uh, the mini-STX NUCs don't really have much space. Everything is packed in pretty tightly. Furthermore, they usually top out at 28 W.For Coffee Lake, Intel made a larger system they called a "NUC", but I think they had actual Nvidia graphics cards in them and were bigger than a lot of mini-PCs.
Alistair - Monday, May 17, 2021 - link
no, that's not right, Tiger Lake is mainly clock speed improvements, not IPC, running Tiger Lake or Comet Lake in a desktop at the same 4.8GHZ all core would get you almost exactly the same performanceheickelrrx - Monday, May 17, 2021 - link
are u drunk?laduran - Tuesday, May 18, 2021 - link
Nomode_13h - Tuesday, May 18, 2021 - link
> Tiger Lake is mainly clock speed improvements, not IPC, running Tiger Lake or Comet Lake> in a desktop at the same 4.8GHZ all core would get you almost exactly the same performance
You're confusing Comet Lake with Ice Lake. IPC of Tiger Lake isn't much improved above that of Ice Lake.
Qasar - Wednesday, May 19, 2021 - link
can you blame him ? its time intel started using different names for their cpus.mode_13h - Thursday, May 20, 2021 - link
I didn't mean that in a pointed way. If anything, I thought it would partially validate the statement.And yes, I wish Intel would've left the Lakes behind with 14 nm, but I guess there are just too many "lake" names for them to part with it for the mere sake of naming consistency. More annoyingly, they're even using "lake" names for some things that aren't CPUs.
Qasar - Thursday, May 20, 2021 - link
it seems they are staying with lake and cove names so unless you are using a slide ruler and a decoder ring, you have no idea which cpu is what :-) i gave up trying to keep track of their names are which cpu line a while ago.mode_13h - Friday, May 21, 2021 - link
> it seems they are staying with lake and cove namesSapphire Rapids is the next server CPU. Also, the little cores seem to be Monts, while the big cores are Coves.
I think the biggest groaner is "Lakefield", which is that mobile CPU with one big core, 4 little cores, and a chunk of eDRAM. MS used it in a Surface model.
Qasar - Friday, May 21, 2021 - link
mode_13h, still doesnt change the fact that the names intel gives its cpus, are confusing has he double hockey sticks :-)mode_13h - Sunday, May 23, 2021 - link
Oh, for sure. It was so nice when *Bridge = LGA 1155, *Well = LGA 1150, and *Lake = LGA 1151....then, it seemed like nearly everything became a Lake!
heickelrrx - Monday, May 17, 2021 - link
back when rocket lake design were finalized the 10nm hasn't matured like today10nm has delayed a lot, they simply tired waiting
sandeep_r_89 - Tuesday, May 18, 2021 - link
Ooh yes, I'd like an NUC with Tigerlake-Hmode_13h - Tuesday, May 18, 2021 - link
It should be NUC11 Extreme, if they do it. The Extreme-series are NUCs in name only.Matthias B V - Monday, May 17, 2021 - link
Indeed it is a big and crucial step as it is the first new arch and node on H45+ all predecessors where Skylake and 14nm iterations.However a make or break will be AlderLake as bigLITTLE either is a game changer or an issue. Golden cove will be good but it really depends on the sheduling and Gracemont.
Especially on possible benefits on mobile run time and consumption!
SarahKerrigan - Monday, May 17, 2021 - link
Looks moderately competitive if you ignore power. Better than nothing, I guess.RanFodar - Monday, May 17, 2021 - link
It's very competitive (except efficiency), not moderate. They're now trading blows here.Krysto - Monday, May 17, 2021 - link
So no reason to get one when you can get an AMD alternative that has similar performance for half the power draw.RanFodar - Monday, May 17, 2021 - link
It has platform advantages (i.e. PCIE 4, Thunderbolt) and if anticipated, great gaming performance. As a consumer, it is much better to have a choice with competitive processors. And there will be reasons to buy a Tiger Lake system when it comes up for review.mode_13h - Monday, May 17, 2021 - link
Does PCIe 4 really provide any measurable benefits, in a laptop ???xpclient - Monday, May 17, 2021 - link
Yes I think so. Have you seen PCIe Gen 3 SSDs reach these speeds? https://pbs.twimg.com/media/E1QXL2qVgAAZfnL.pngozzuneoj86 - Monday, May 17, 2021 - link
While it is nice that it supports gen 4, realistically you're just getting SSDs that put out more heat, with more power draw, while gaining performance benefits that are only measurable in benchmarks or very specific situations.I'm sure file copy performance is much higher, but how fast do you need that to be? Assuming you're copying to the drive itself or maybe to a Thunderbolt 4 external drive, it is the difference between copying 1TB of data in 2 minutes versus 6 minutes. You can (theoretically) completely fill a $400 2TB SSD in 4 minutes with gen4 vs maybe 12 minutes with Gen 3. If someone needs to do that all the time, then sure there's a difference... but that has to be pretty uncommon.
For smaller amounts of data, any decent nvme drive is fast enough to make the difference between models almost unnoticeable. For the vast majority of users, even a SATA drive is plenty fast enough to provide a smooth and nearly wait-free experience.
mode_13h - Monday, May 17, 2021 - link
> realistically you're just getting SSDs that put out more heat, with more power draw,> while gaining performance benefits that are only measurable in benchmarks
> or very specific situations.
Exactly. Thank you.
mode_13h - Monday, May 17, 2021 - link
> Assuming you're copying to the drive itself or maybe to a Thunderbolt 4 external driveOops! TB 4 is limited to PCIe 3.0 x4 speeds! So, it'd be little-to-no help there!
Calin - Tuesday, May 18, 2021 - link
Well, you could copy full blast to an external drive and have plenty of remaining performance to do other storage intensive things - that's assuming your external drives is fast enough to suffocate PCIe 3.0 x4, and your internal drive is faster still.mode_13h - Thursday, May 20, 2021 - link
> Well, you could copy full blast to an external drive and have plenty of remaining performanceI'm not one to turn down "free" performance, but PCIe 4 uses significantly more power. In a laptop, that's not a minor point.
inighthawki - Monday, May 17, 2021 - link
Sequential read and write speeds are basically just flexing. Very few people actually ever make significant use of such speeds in a way that saves more than a second or two here or there. Most laptop users are not sitting there copying a terabyte of sequential data over and over again.The_Assimilator - Monday, May 17, 2021 - link
There is no laptop chassis on the market that can adequately handle the excess of 8W of heat that a PCIe 4.0 NVMe SSD can dissipate.Cooe - Monday, May 17, 2021 - link
You're not getting those kind of speeds sustained in a laptop without RIDICULOUS thermal throttling. PCIe 4.0 in mobile atm is just a marketing checkmark & nothing more.Calin - Tuesday, May 18, 2021 - link
It allows faster "races to sleep" for the processor. And, since the Core2 architecture, the winning move was "fast and power hungry processor that does what it must and then goes to a very low power state". This gives you very good burst speed and low average power - as soon as you finish, you can throttle everything down (CPU, caches, SSDs, ...)mode_13h - Thursday, May 20, 2021 - link
> It allows faster "races to sleep" for the processor.Are we still talking about PCIe 4? I don't think it works like that.
> since the Core2 architecture, the winning move was "fast and power hungry processor that does what it must and then goes to a very low power state".
No, it's more energy-efficient to run at a slower clock speed. There's a huge difference between the amount of energy used in turbo and non-turbo modes. As it's far bigger than the performance difference, there's no way that going to idle a little sooner is going to make up for it.
mode_13h - Monday, May 17, 2021 - link
That's clearly not a M.2 drive and therefore not a laptop. Please reread my question.xpclient - Tuesday, May 18, 2021 - link
It is from an M.2 gen 4 drive in a gaming laptop - ASUS ROG Zephyrus S17 GX703 (GX703HS model – Core i9 11900H + RTX 3080 140W, 4K 120Hz screen) but I get your point - at the moment, not many will need such speeds. Gen 3 will serve them fine. Please do not question the benchmark itself. Personally I got an AMD Ryzen 7 5800H-based machine myself, without waiting for Tiger Lake H45.mode_13h - Tuesday, May 18, 2021 - link
xpclient> It is from an M.2 gen 4 drive in a gaming laptop - ASUS ROG Zephyrus S17 GX703xpclient> (GX703HS model – Core i9 11900H + RTX 3080 140W, 4K 120Hz screen)
BS. Look at the numbers: you cannot do 10.5 GB/s read or 9.8 GB/s write over PCIe 4.0 x4.
I don't know what it's from, but it's no mere x4 drive. Maybe a 4-drive RAID-0 or something like that.
Spunjji - Tuesday, May 18, 2021 - link
@mode_13 Those scores are from a laptop that comes with a 3-drive RAID-0 config, which is - quite frankly - an absurd setup to have by default for a gaming system.mode_13h - Tuesday, May 18, 2021 - link
spunji> Those scores are from a laptop that comes with a 3-drive RAID-0 configWow, so I was actually close!
> which is - quite frankly - an absurd setup to have by default for a gaming system.
Yeah, I'd say a 3-drive RAID-5 might make sense in a mobile workstation for editing digital cinema footage on-location.
xpclient - Wednesday, May 19, 2021 - link
@mode_13h and @Spunjji, my apologies. I didn't notice the 3 drive RAID config in that review article of an ASUS laptop and missed that completely. My bad.mode_13h - Thursday, May 20, 2021 - link
> my apologies.No problem. It did spark an interesting tangent about RAID in laptops.
Thanks for the follow-up. It's a good idea to sanity-check the numbers, since that's what first caught my attention.
Spunjji - Thursday, May 20, 2021 - link
@xpclient - no harm no foul!Bagheera - Tuesday, May 18, 2021 - link
let's not forget that Intel was 2 years late to PCIe4 on DESKTOP and Intel fans didn't seem to mind.mode_13h - Tuesday, May 18, 2021 - link
> let's not forget that Intel was 2 years late to PCIe4 on DESKTOPIt's there now. If you weren't in the market for a new PC in the past 2 years, what does it matter?
> and Intel fans didn't seem to mind.
Not even just Intel fans. AMD was early with their PCIe 4, on the desktop. That's why they caught Intel by surprise. Because, at the time, PCIe 3 was good enough. We're only just starting to see some minor advantages for PCIe 4, on the desktop. It's no game changer.
Honestly, of all the criticisms you could make of Intel, this is one of the weaker ones.
back2future - Tuesday, May 18, 2021 - link
it's almost one could skip PCIe4 if early 2022 PCIe5 is stable on power management and performance expectations on mainboards?mode_13h - Thursday, May 20, 2021 - link
> it's almost one could skip PCIe4 if early 2022 PCIe5 is stable ... on mainboards?Uh, I'm still eager to see exactly how Intel is going to use PCIe 5, in Alder Lake. I suspect it'll be used only for the DMI link to the chipset, in fact.
Since graphics cards and M.2 SSDs aren't even close to maxing PCIe 4, I struggle to see why they would bother with the added cost and potential issues of supporting 5.
heickelrrx - Monday, May 17, 2021 - link
you can put 4x link on Video card and get 8x speed on Gen 3mean they can put more stuff, with less link, not faster stuff
mode_13h - Tuesday, May 18, 2021 - link
> you can put 4x link on Video card and get 8x speed on Gen 3In terms of power-efficiency, I'd bet the wider, slower link is better.
> mean they can put more stuff, with less link, not faster stuff
It's a laptop. So, prolly not gonna run out of PCIe lanes.
gagegfg - Monday, May 17, 2021 - link
"and if anticipated, great gaming performance"...Inside this notebook case he had a hard time controlling the temperature, if you add a 100W GPU, where is the rest for this cpu?
mmm .... it's going to be interesting.
Matthias B V - Monday, May 17, 2021 - link
Most OEMs still prefer Intel as it has capacity that AMD can't offer and even more it has better features and integration such as AV1 coding, USB / TB 4.0, Intel WIFI etc.Also Intels provides better support for OEMs in design and issues.
Gigaplex - Monday, May 17, 2021 - link
AMD systems can provide TB support, there's no technical limitation preventing it. Intel WiFi chips are standalone cards, which also work fine in AMD systems (my AMD board has Intel WiFi). There's no reason to use an Intel CPU for either of those features.Retycint - Monday, May 17, 2021 - link
The fact that not a single AMD laptop has thunderbolt, points to an issue with cost of implementation/PCI lanes limitations etc. which apparently doesn't exist on Intel CPUs, given how many Intel laptops come with TB as default. This is a fact, and talking about what's possible theoretically doesn't change the facts that AMD systems lack TBCityBlue - Monday, May 17, 2021 - link
> The fact that not a single AMD laptop has thunderbolt, points to an issue with cost of implementation/PCI lanes limitations etc.Perhaps. Or it's simply a reflection of the fact that there is only niche demand for TB.
It's on Intel based laptops because it's supported by the chipset so pretty much a no-brainer (or alternatively, Intel mandates it is included, in order to try and make it more relevant?)
However the vast majority of laptop consumers don't need, want or care about TB, so the extra cost to include it in AMD laptops doesn't appear justified. I'm sure a vendor could include TB on an AMD laptop if they ever thought they'd get a reasonable return on the extra cost.
And maybe now that Intel have been kicked in to touch by Apple, Intel might lose interest in TB in future.
TB has its fans, but it also has the distinct whiff of being the next FireWire.
RobJoy - Tuesday, May 18, 2021 - link
The fact that TB still exists, baffles me.We all should move on.
mode_13h - Tuesday, May 18, 2021 - link
It's now royalty-free and completely intertwined with USB4. So, no... it's not going away.drothgery - Monday, May 17, 2021 - link
This presumes anything resembling parity in both availability and quality of the laptops the CPUs are in which historically has ... not been the case.eastcoast_pete - Monday, May 17, 2021 - link
Unfortunately, it's more "..if you can get.." rather than "..when you can get an AMD alternative".Azix - Monday, May 17, 2021 - link
power draw on a laptop is always going to be paired with battery capacity. It's about battery life right? Or maybe its about the heat on the bottom of the laptop.End of the day its mostly down to laptop design. The power consumption is likely to be transparent to the end user.
timecop1818 - Tuesday, May 18, 2021 - link
The Intel part would actually work tho, unlike AMD.Spunjji - Tuesday, May 18, 2021 - link
So many productive comments, and then this.Spunjji - Tuesday, May 18, 2021 - link
Not exactly. Between availability and incidentals like Thunderbolt, there are now reasons to opt for Intel where before they were nowhere near as compelling.I'd still err on the side of AMD as I prefer efficiency, but I'm sure others would go the other way.
Hifihedgehog - Monday, May 17, 2021 - link
LOL. No, it is not competitive. >90W boosts is NOT competitive. In long gaming sessions, its UNcompetitive power hungry soul is going to hamstring the GPU that shares thermals in a notebook chassis.Hifihedgehog - Monday, May 17, 2021 - link
And even with its increased power envelope, 8-core Tiger Lake H's multicore performance falls short of the best 8-core Ryzen 4000 series CPU (Ryzen 9 4900HS).SaturnusDK - Monday, May 17, 2021 - link
No, it's not competitive at all. Even if you ignore efficiency, you can't ignore the price.Intel laptops with mediocre CPUs are already more expensive than clearly superior AMD alternatives. These models will just widen that gap.
The unfortunate conclusion is that in 2021 isn't even remotely competitive in the laptop market.
danjw - Monday, May 17, 2021 - link
No, not really. This is Intel's REFERENCE SYSTEM and it only trades blows with an AMD system that is a product. How is this competitive? You have to realize that the fans on this system aren't tuned for a consumer, they are tuned to make Intel's processor look better. If you read Andrei's conclusions, it is a processor for a laptop no one is selling anymore. It is a 65W processor battling a 35W processor.Their are two reasons this may sell well. AMD's systems are still hard to find and the fact that many consumers still believe that the Intel Inside label is important.
mode_13h - Monday, May 17, 2021 - link
> You have to realize that the fans on this system aren't tuned for a consumer,> they are tuned to make Intel's processor look better.
Not to argue with your main point, but it's worth noting that even when Intel gets to design their own thermal solution, it still fell on its face @ the stock 65W settings. That's pretty bad.
mode_13h - Monday, May 17, 2021 - link
Maybe they should've had the team design it who rigged up that Cascade Lake workstation demo to run all cores at like 5 GHz. Sure, it'd have been the size of a briefcase and sounded like a leaf blower, but at least the it'd clock well!Andrei Frumusanu - Monday, May 17, 2021 - link
Just to make it clear and visible: The i9-11980HK is advertised as a default 45W CPU. The fact that the system came in 65W mode shouldn't be seen as a "stock" behaviour of that SKU.mode_13h - Monday, May 17, 2021 - link
> The fact that the system came in 65W mode shouldn't be seen as a "stock" behaviour of that SKU.So, what are we to make of it? Was Intel trying to rig the benchmarks, then ???
jospoortvliet - Wednesday, May 19, 2021 - link
Pfffif they were they did it in a stunningly incompetent way... hahaSpunjji - Thursday, May 20, 2021 - link
@mode_13h - they did that with their previous Ice and Tiger Lake reference platforms (100% fan speed constantly, yes please) so it makes sense they did the same again here. 😬morello159 - Monday, May 17, 2021 - link
Another thing to consider is that Intel platforms have been much more stable, for me, than AMD. My ASUS G14 with the Ryzen 4900HS, for example, *can* deliver both outstanding battery life and amazing performance. However, there are often times when the system draws extra power for seemingly no reason. There are whole forums dedicated to tweaking the G14's power settings to fix high idle draw. I've also experienced some weird freezes, lockups, etc. It's a great laptop, but I wouldn't use it in a professional setting where I need it to work all the time.My i7-10810U powered Dell Latitude 9510, while quite slow in comparison, gets 12 hours of battery life every time and can run days at a time without any hiccups.
Hifihedgehog - Monday, May 17, 2021 - link
> "Intel platforms have been much more stable, for me, than AMD"LOL. Even with Xe, I still see major graphical issues with 3D games which in some cases even refuse to render. It has gotten way better than five years ago, but AMD's graphic drivers are still far and away better. Stop reaching...
Spunjji - Tuesday, May 18, 2021 - link
This reply doesn't really contradict morello159's main point, though.I've had similar experiences - my 8th gen Intel Dell work system is rock solid, if unspectacular.
My 4800H + 5600M Dell gaming system has... issues. A lot of them appear to be Dell's fault, TBH, but not all of them are.
schujj07 - Monday, May 17, 2021 - link
You are comparing a gaming laptop against a high end professional laptop. First the 4900HS is a 35W CPU and the 10810U is a 15W CPU. If both laptops have equally size batteries, the one with the lower TDP "should" have longer battery life. On top of the the G14 has a 120Hz display and a dGPU. Both of those will pull extra power and the screen was specifically talked about in reviews of the laptop. Setting the screen to a 60Hz refresh rate instead of 120Hz significantly increased battery life. Finally the weird freezes is most likely due to the dual GPU design and switching between the iGPU and dGPU. Unless you are using so much RAM that you are page swapping.Otritus - Wednesday, May 19, 2021 - link
@schujj07 I have the same zephyrus laptop as morello159. I haven't experienced weird freezes when switching between gpus on mine, or my old laptop with an intel processor and nvidia gpu, so optimus working isn't likely to be causing the freezing. The random high power draw is a valid complaint though. I think the randomness is caused by Asus's turbo settings, which was mostly fixed by me modifying power limits and disabling turbo. But, the default experience is the processor randomly boosting ridiculously high when it should be in a near idle state and not clocking anywhere near as high. Like the chip randomly pushes all 8 cores to 3.8Ghz, when it should be running in the 1.4-1.7Ghz range.bji - Monday, May 17, 2021 - link
Why should I care AT ALL that one platform has been more stable *for you* (your words)? You are irrelevant. Just one piece of anecdotal data.Calin - Tuesday, May 18, 2021 - link
They are trading blows in performance, but AMD is doing that on 35W instead of 45W for Intel.For manufacturers that use the same chassis with Intel AND AMD processors, the Intel one will run hotter, be noisier and/or have lower battery life when working hard (I don't seem to find anything related to idle/low power consumption).
jenesuispasbavard - Monday, May 17, 2021 - link
If you're planning on further testing, maybe using Intel XTU you can limit the PL1/PL2 to 45W and see how that performs?jenesuispasbavard - Monday, May 17, 2021 - link
Maybe I should scroll to page 2 before commenting on page 1...vyor - Monday, May 17, 2021 - link
I'm sorry, but your SPECFP2017 results are just wrong. There is no possible way that the 1185G7 is faster than the 11980HK by 2x in 503.bwavesThat's just absurd, especially when every other test bar 3 shows the exact opposite results, and even of those that show similar results it isn't nearly to the same degree baring 549.fotonik, and that one has the 4900HS somehow being faster than the 5980HS.
So no, your testing is just wrong and broken.
Otritus - Monday, May 17, 2021 - link
The 1185G7 being twice as fast is a little questionable, and possibly the results for the Tiger Lake processors were switched accidentally.As to the 4900HS being faster than the 5980HS in one very specific subtest, I suppose companies have never released a new CPU architecture slower than the old one. That's why Bulldozer was well received for its incredible performance over Thuban. Rocket Lake was well loved for consistently beating Comet Lake and Zen 3 in gaming, with the 11900K always at the top of the chart. Broadwell-S of course isn't better than Skylake or competitive with Coffee Lake in gaming.
vyor - Monday, May 17, 2021 - link
Except that Zen3 is consistently faster in almost every way.Otritus - Monday, May 17, 2021 - link
Keyword "almost"Zen 3 does not win every benchmark over Zen 2, just the vast majority of them due to superior clock speeds and IPC. In 1 very specific subtest, out of all the test conducted, is it really unreasonable to see the older architecture get a win. The last time I can think of a new architecture winning every single benchmark was Conroe. Sandybridge might also get this title with workloads that didn't need more than 4 cores, but I don't exactly recall. Remember IPC is an average of performance at a given frequency, so if a few benchmarks have negative improvements in IPC, but most have large positive improvements, you can easily see a 20% IPC uplift.
vyor - Monday, May 17, 2021 - link
Worst case for Zen3 is matching Zen2. That's the *worst* case. Name a single actual workload it's slower in.Otritus - Monday, May 17, 2021 - link
Vermeer was consistently faster than Matisse, but Milan was not consistently faster than Rome. Cezanne is faster than Renoir in all but 1 subtest. All 3 comparisons are Zen 3 vs Zen 2. Also SPEC isn't an actual workload by the standards of it's something people run for work or entertainment. It's just a series of industry-standard benchmarks to evaluate the performance of processors. In all of the real workloads Cezanne wins.mode_13h - Monday, May 17, 2021 - link
> Milan was not consistently faster than Rome.Because the IO die is consuming too much power @ the higher frequency it uses in Milan. Not due to the cores, themselves.
Bagheera - Tuesday, May 18, 2021 - link
Rocket Lake was well loved.... by who? it was universally panned by reviewers. the lower end sub-$300 i5 may be good value, but that's about it. the high end parts not only lose to Zen 3 but loses even to CML in some cases.Makste - Monday, May 31, 2021 - link
Take a sarcasm 😉Hifihedgehog - Monday, May 17, 2021 - link
Exactly. Generally, I find the results here very accurate here, but that needs serious attention.vyor - Monday, May 17, 2021 - link
I find that his Spec testing has gotten worse and worse over the years. Andrei honestly just don't know how to use the suite and it almost always makes some parts look better than others when they really shouldn't be. Just look at the M1 tests for that, where the single thread perf in SPEC vastly exceeds that scene in any other test.Andrei Frumusanu - Monday, May 17, 2021 - link
You're welcome to demonstrate what is flawed with actual technical arguments.The M1 exceeds because it's that good, we're missing it in many other benchmarks simply because they aren't ported to macOS or currently don't have data on them.
vyor - Monday, May 17, 2021 - link
"it's just that good" except in every single case it isn't.Name a single workload where the spec results line up with application performance.
Ppietra - Monday, May 17, 2021 - link
Single thread performance seems to align quite well with other tasks!Look at Cinebench single thread performance. Look at compiling performance. Look at javascript performance, etc, etc!
Qasar - Monday, May 17, 2021 - link
" Name a single workload where the spec results line up with application performance"post a single link that shows you are right, and Andrei is wrong, as so far, it seems you are just typing FUD.
personally, im going with Andrei.
Spunjji - Tuesday, May 18, 2021 - link
Why don't you name some where it doesn't, given that you're the one making the extraordinary claim here?Andrei Frumusanu - Monday, May 17, 2021 - link
I've added in the text to those pages now, and I explain why they would end up like that.The TGL-H system has half the memory level parallelism with its 2x64 DDR4 channels versus the 4x16b LPDDR4 channels of the TGL system, and those two workloads are characterised by heavy parallelised memory bandwidth.
We've seen a 66% performance difference on a 5950X between 2x SR and 4x SR DIMM memory in the MT test, it all depends on the DRAM configuration and what kind of parallelism it allows.
Our testing is correct and we have the correct understanding of the microarchitectures and workloads.
vyor - Monday, May 17, 2021 - link
Thanks for finally actually giving reasons, should have been there before publishing.And no, no it isn't. You don't even publish your compiler settings.
Andrei Frumusanu - Monday, May 17, 2021 - link
The compiler settings are literally on the SPEC page and have been there the whole time, and have been set in stone on the Windows side for over a year now for every article.vyor - Monday, May 17, 2021 - link
I do not believe those are the actual compiler settings. Because if they are, you fucked up hard.mode_13h - Monday, May 17, 2021 - link
Outlier results should be investigated and understood. They might be very informative of edge cases. Or, they might indeed expose procedural errors in the testing. Either way, your attitude of dismissing them as erroneous and abusing the testers is not helpful.It's fine to call attention to anomalies and ask questions, but abuse is not called for and shouldn't be tolerated.
vyor - Monday, May 17, 2021 - link
Except that he's been getting called out for this for the last year+.Andrei Frumusanu - Monday, May 17, 2021 - link
And every time I've demolished the unsubstantiated empty argument with data and facts. If you do not have any actual technical argument to make then don't make any.ballsystemlord - Monday, May 17, 2021 - link
I have to back up Andrei here. You've only given us hyperbole so far.Which compiler settings do you have a problem with exactly?
As a former Gentoo Linux user, I don't see a problem with them. Of course, -Ofast shouldn't be used in a production system -- but he is benchmarking here.
SarahKerrigan - Monday, May 17, 2021 - link
Of course. It must be some kind of dark conspiracy to hide the real compiler settings. The truth is out there! Trust no one!Spunjji - Tuesday, May 18, 2021 - link
Counterpoint: You're full of it, and blowing hard.repoman27 - Monday, May 17, 2021 - link
Andrei, TGL-U (UP3/UP4/H35) LPDDR4/X is actually 8x16. Two memory controllers, each with four x16 channels.Andrei Frumusanu - Monday, May 17, 2021 - link
Yes, brainfart.mode_13h - Monday, May 17, 2021 - link
Wow!So, how are they mapped? How much interleaving, and at what granularity?
mode_13h - Monday, May 17, 2021 - link
Incidentally, I have a Phenom II motherboard that allows me to configure page-granularity interleaving. Not sure how common it is, but I don't think my Intel workstation board gives me that option!KarlKastor - Monday, May 17, 2021 - link
Doesn't sound like a good CPU benchmark to me.mode_13h - Monday, May 17, 2021 - link
So, you want a suite of benchmarks that all behave similarly and don't stress the platform in various and different ways?Suit yourself, but I think a good benchmark suite should have enough diversity to hit different edge cases, as long as it's not doing anything unrealistic. And, as far as I can tell, the SPEC 17 tests are entirely comprised of real-world programs.
Otritus - Monday, May 17, 2021 - link
Interesting how much power Tiger Lake H needs to draw to be competitive with Cezanne. At this point it's clear that Intel's big cores are bloated when AMD has higher IPC and frequency at lower power draw with a comparable node. Little cores in Alder Lake may help with efficiency, but they are taking power budget away from the big cores which hurts their frequency. Intel probably needs to redesign their big cores from the ground up rather than continuing to refine and improve Pentium-M.On a side note I'm conflicted on your decision to omit AVX-512 on NAMD. On one hand you are not testing AVX-512, but on the other hand you are omitting a possibly real world scenario for someone. Intel's marketing on AVX-512 and its inclusion in consumer processors are questionable choices, but that still is a valid, functional feature built into the chip. Perhaps a good compromise would be to add in the updated version for AVX-512 processors only.
zaza - Monday, May 17, 2021 - link
Most workloads that can run avx256 can easily be extended to AVX-512. In some cases, you need just to recompile with AVX-512 optimization floag on. Even Skylake-X and cascadelake-X there is a noticeable improvement in performance in AVX-512Otritus - Monday, May 17, 2021 - link
And that's why if there is an option to run AVX-512, I'd like to see it being run. Also with the massive efficiency deficit of Tiger Lake, and AVX-512 requiring even more power, it's plausible Cezanne might be competitive at the same power limits. Although with NAMD, I'd expect Tiger Lake to top the chart.vyor - Monday, May 17, 2021 - link
That is not how AVX512 works.mode_13h - Monday, May 17, 2021 - link
Depends on how well the compiler can vectorize your workload or if you're using something like OpenMP. However, if I really wanted max performance from AVX-512, I'd be using the intrinsics.BTW, it's worth noting that you can't simply disable AVX-512 with build-time compiler flags, for software that performs runtime code-generation (usually via LLVM). Many popular deep learning frameworks fall in this category.
mode_13h - Monday, May 17, 2021 - link
> Even Skylake-X and cascadelake-X there is a noticeable improvement in performance in AVX-512Not always. Clock throttling is so bad in Skylake SP & Cascade Lake that you need an AVX-512 -heavy workload to see a net-benefit.
zaza - Monday, May 17, 2021 - link
I actually ran that test myself in my university lab. we ran AI workloads and vectorized workloads on avx2 and avx512. Running avx512 on all threads would result in a significant clock drop, but despite this, I was testing 20% faster than AVX 256 (they were using the same power ~200 watts). When you mixing several workloads (AVX and non-AVX), you don't see the same drop unless more than 50% of the cores are running AVX. Granted this is anecdotal evidence, but I think the power budgeting across the chip was working well to maximize performance.mode_13h - Monday, May 17, 2021 - link
> I actually ran that test myself in my university lab. we ran AI workloads and vectorized> workloads on avx2 and avx512. Running avx512 on all threads would result in a
> significant clock drop, but despite this, I was testing 20% faster than AVX 256
> (they were using the same power ~200 watts).
Depends on your network architecture. We saw the opposite, and this was confirmed by engineers at Intel. To resolve the problem, they sent us a patch to disable AVX-512.
> When you mixing several workloads (AVX and non-AVX), you don't see the same drop
> unless more than 50% of the cores are running AVX.
I'm talking specifically about AVX-512. And when I had a lot of threads using it for maybe only 10% of the time (different scenario than above), I also saw clock drops big enough to decrease overall system throughput.
This was all on 14 nm CPUs, so I'm eager to try Intel's 10 nm chips.
mode_13h - Monday, May 17, 2021 - link
> I'm conflicted on your decision to omit AVX-512 on NAMD.Let's remember that this is a notebook processor. Sure, it's what most Intel-based mobile workstations will probably use, but most users of this processor aren't going to be recompiling their apps with -march=native.
In other words, I think the case for testing AVX-512 on this CPU is a lot weaker than on server CPUs or even desktop processors.
ballsystemlord - Monday, May 17, 2021 - link
Good point!Techtree101 - Monday, May 17, 2021 - link
Dwarf Fortress looks like a great benchmark tool for judging heavy single threaded AI/Simulation games?Could I use these benchmark results with it, loosely, to extrapolate what this CPU can do for Civilization VI, Cities Skylines, Minecraft, etc.?
Techtree101 - Monday, May 17, 2021 - link
And Dolphin 5.0 I suppose too.yeeeeman - Monday, May 17, 2021 - link
Frankly, while power consumption is a big problem and we know 10nm is not that great, the performance is good and actually intel providing a reference system for review is a good sign.Spunjji - Tuesday, May 18, 2021 - link
They've provided reference systems for launches twice before now - with Ice Lake and Tiger Lake (U) - and for both of those launches, the reference system outperformed comparable devices available at retail. Given that history it's not surprising they pushed this out with a 65W TDP, but it is very amusing that the cooling system couldn't handle it.Techtree101 - Monday, May 17, 2021 - link
I wonder how this will compare to Alder Lake laptops later this year...shabby - Monday, May 17, 2021 - link
Aren't reference designs usually ringers?psyclist80 - Monday, May 17, 2021 - link
Thanks for the review guys! It beat a laptop half its weight by only 7-10% while using 25% more power...The ROG X13 is awesome but its only 2.8 lbs and 16mm thick. That 16" inch Intel machine outclassed it thermal capabilities easily and likely weighed in at ~6lbs... Looking forward to reviews in comparable chassis.
Glad to see the performance is there, but too hot and power hungry for a laptop. 10nm Superfin, still cant catch TSMC 7nm, with 5nm coming soon...
Hifihedgehog - Monday, May 17, 2021 - link
Hopefully, Alder Lake rectifies the power efficiency gap between Ryzen 5000 and Tiger Lake because... yikes. Now, I can see why 8-core Tiger Lake was mysteriously held back for so long. These 90-95 degree temperature peaks are going to seriously hamper GPU performance in the shared thermals of a very compact notebook chassis. Never mind that 8-core Tiger Lake's peak power exceeds AMD's own Ryzen 5600X desktop part.Hifihedgehog - Monday, May 17, 2021 - link
And even with its increased power envelope, 8-core Tiger Lake H's multicore performance falls short of the best 8-core Ryzen 4000 series CPU (Ryzen 9 4900HS).zodiacfml - Monday, May 17, 2021 - link
quite surprising. considering the performance of quad core tiger lakes, i estimated the Intel eight cores to be on par or easily beat AMD. it also doesnt seem Intel will be selling the 6-8 cores at lower tdps soonSpunjji - Thursday, May 20, 2021 - link
They had to hit high clocks to get that performance, at a disproportionately high power cost. With 8 cores going at once, they simply don't have the thermal headroom.IGTrading - Monday, May 17, 2021 - link
Intel's 8C "mobile" chip is not worth the money ...Unless you have some badly optimized code, where the extra ST performance will out weigh the extra money spent for Intel, the increased heat generated, the lower battery life and the bulkier / heavier laptop.
AMD wins this round as well.
Ppietra - Monday, May 17, 2021 - link
The M1 Mac mini peak power makes no sense in that graph!You are comparing the Mac mini Total Power Draw on the Wall, with other devices’ CPU peak power - clearly completely different things.
Andrei Frumusanu - Monday, May 17, 2021 - link
I think that was a leftover from Ian or a misunderstanding, the M1 does have around 32W peak package power, but you're right, CPU only is only around 21W, I've edited that.Ppietra - Monday, May 17, 2021 - link
ok! I understand, I think it was the data from the original article where you weren’t able to measure CPU power. The value makes more sense now.yankeeDDL - Monday, May 17, 2021 - link
This is not surprising, and it is in line with the TL-U results.I think TL-U is a compelling option, but given the possibility, I'd go for an AMD-based laptop: 30 more minutes of battery life are well worth 7-10% single-core performance disadvantage, all the rest considered. IMHO.
tipoo - Monday, May 17, 2021 - link
Moar 👏Watts 👏Feels like all Intel has now
jagoanjoko - Monday, May 17, 2021 - link
Damn I still expect a little bit better (or much better) result from H45. Many Core i7 10870H can reach 1.600+ points on Cinebench R15 MT. We suppose to wait for final product. But still too disappointing :(Fortunately intel will trading blow with AMD today and for the rest of 2021. Intel can't be strong enough to compete with AMD if they haven't TGL-H45 series
Yojimbo - Monday, May 17, 2021 - link
Isn't the unplugged, battery-only behavior the power usage that matters for a laptop?jagoanjoko - Monday, May 17, 2021 - link
I think it's matter for ultrabook and any ultra portable laptopsAnd become less relevant for thicker laptops
But it's nice to have decent battery life on your thicker laptops so you don't have to bring those heavy charging bricks all times.
mode_13h - Monday, May 17, 2021 - link
Ask people who run demanding games or run heavy workloads on their laptops (who are precisely the market for this thing) and you'll probably find they spend most of their time plugged in.Yojimbo - Monday, May 17, 2021 - link
I myself have a desktop replacement laptop that I use almost exclusively plugged in. When it's plugged in I certainly care about noise, but I don't care about power usage. However I do sometimes use it on battery power, both on power hungry tasks (with which I try to have it plugged in when running) and less power-hungry tasks. That's when battery life, and hence power draw, becomes important to me for the laptop.So, although I use my laptop mostly plugged in and I do care about power draw, the power draw I care about is almost entirely for when the laptop is unplugged. And of course I also care about the performance I get for that power draw in those situations. The noise factor must be considered exclusively laptop to laptop, so looking at power draw in plugged in situations isn't very useful. And frankly, I can't see a good reason that many consumers to be looking at the situation differently and would be concerned about the power draw of the laptop when plugged in.
Yojimbo - Monday, May 17, 2021 - link
Should read "And frankly, I can't see a good reason for many consumers to be looking at the situation differently such that they would be concerned about the power draw of the laptop when plugged in."I'm not saying that plugged in power usage is useless to consider, just that it seems to me much less important, as far as power-usage is concerned (even for a desktop replacement) than battery-powered power usage and performance. Maybe others feel differently but I don't understand why. It's not like any laptop is a real power hog unlike some desktop systems can be. We're talking about, what, plus-or-minus 20 watts here? 30 watts? 30 watts plugged in means nothing to me. Does it mean a lot to most others, and if so why?
Bik - Monday, May 17, 2021 - link
It's the capability of the laptop to disperse heat. More watt = more heat. The heat is the issue (loud fan, cpu throttle).Yojimbo - Monday, May 17, 2021 - link
But that varies widely from laptop to laptop. And it's not just a function of the heat output, it's a function of the cooling system, which is related to both cost and weight. So you don't really get helpful information for noise or throttling just by looking at plugged-in power usage.vegemeister - Tuesday, May 18, 2021 - link
More power = more noise for the same cost and weight, or more cost and weight for the same noise.repoman27 - Monday, May 17, 2021 - link
Is there a reason why TGL-U is referred to (somewhat confusingly) in the article as just TGL? I know Intel (also somewhat confusingly) uses the TGL-U 4+2 LP die for three separate platforms (UP3, UP4, and H35), but they're all still considered TGL-U, aren't they? Whereas Tiger Lake is the codename for the whole range of processor families including UP3, UP4, H35, and H.Maybe TGL 4+2 and TGL 8+1 would be more succinct?
Andrei Frumusanu - Monday, May 17, 2021 - link
Fair, I'll change the terminology.bernstein - Monday, May 17, 2021 - link
@Andrei Frumusanu :how is it that the amd 5800x (and others) spec2017fp_r results differ by as much as 7 points while the spec2017int_r values are basically on point? (there seem to be minor differences for the 49/4800U in spec2017int_r values too. plus large diff for the i9-10900K).
comparing to : https://www.anandtech.com/show/16252/mac-mini-appl...
Andrei Frumusanu - Monday, May 17, 2021 - link
In that article we were using only the C/C++ sub-benchmarks due to not having a functioning Fortran compiler on the M1 at the time. So it's apples-and-oranges in terms of the scores between the articles. The integer suite only has 1 Fortran workload, the FP suite has much more.Since, I've rerun the M1 ST scores on a vanilla LLVM and Gfortran toolchain to get all workloads, and anyhow all articles except for that initial M1 piece have the full subset of workloads. The M1 MT scores are missing from this piece as I never ran that (brainfart) and no longer have an M1 system at hand.
bernstein - Monday, May 17, 2021 - link
thanks for clearing that up. great articles btw!also thx for anticipating (and answering) my next question!
Ppietra - Monday, May 17, 2021 - link
As far as I know the results in the Mac mini review aren’t the full SPEC 2017, because some tests require a Fortran compiler that didn’t exist for the M1.gagegfg - Monday, May 17, 2021 - link
Where is the AMD "H" series? Like the 5980HX or the 5900H. It should have better multicore performance.Fulljack - Monday, May 17, 2021 - link
umm Ryzen 9 5980HS is "H" series...gagegfg - Tuesday, May 18, 2021 - link
HS <= 35WH / HX >= 45W
Linustechtips12#6900xt - Monday, May 17, 2021 - link
I find it hilarious that a desktop CPU 5600x maybe even the 57/5800x would be about the same if not better power consumption with better performance LOL especially performance per watt lol.Yojimbo - Monday, May 17, 2021 - link
Why? It's plugged in so what's the difference?Otritus - Wednesday, May 19, 2021 - link
I would assume because desktop cpus are typically tuned for performance at the cost of efficiency, and mobile processors are tuned for efficiency at the cost of performance. Power efficiency still does matter when plugged in for cooling purposes. Tiger lake needing a lot more power to deliver equal performance means higher temperatures, louder fans, or a more expensive cooling system.mode_13h - Thursday, May 20, 2021 - link
> I would assume because desktop cpus are typically tuned for performance at the cost> of efficiency, and mobile processors are tuned for efficiency at the cost of performance.
I think we've established that the H-series processors are basically desktop chips in a BGA package.
> Tiger lake needing a lot more power to deliver equal performance means higher
> temperatures, louder fans, or a more expensive cooling system.
Yup. Loud fans are why I disabled turbo on my H-series Dell Precision laptop that I use for work. The only thing I hate more than performance bogging down is screaming fans in my face. And yes, I have used pressurized air to blast any dust and debris from the cooling channels.
Also, a better cooling system tends to add bulk and weight.
cyrusfox - Monday, May 17, 2021 - link
One spelling comment, you have "GP Us" instead of "GPUs" on the first page, I use Text to speech, easy to catch it with that. Sorry to be the spelling guy. Thanks!cyrusfox - Monday, May 17, 2021 - link
Also on the last page should be"Where things aren't" not
"Where things are quite as straightforward, is the multi-threaded performance, as this is where we have to mention TDPs, power limits, and just the result of the Intel reference platform laptop we’ve tested today."
Thank you for the indepth review! Interesting stop gap to Alder lake, With apple in the market with a pending M2, going to be a very interesting space to watch.
Linustechtips12#6900xt - Monday, May 17, 2021 - link
Just wondering but could there be a comparison to an AMD 5800x or something like that just to put an idea on the power draw for the performance/ performance per watt? I was kinda curious after reading through the article a couple of times.eastcoast_pete - Monday, May 17, 2021 - link
A key question is now if Intel can further improve its 10 nm superfin process in time for Alder Lake. This TL is at least getting somewhat close to AMD's monolithic Zen3, but Rembrandt is around the corner, and that'll be an even more capable competitor. Right now, Intel retains its market share mostly because AMD can't deliver as many CPUs as people would buy.hfm - Monday, May 17, 2021 - link
I'm looking forward to an i5 or i7 design with no dGPU and that sweet embedded TB4. Probably going to be a small subset of the offerings like the lower tier XPS 15/17. Interested to see what comes about later in summer.evilspoons - Monday, May 17, 2021 - link
It'd be helpful to see power-normalized graphs, some of these results are a bit of a double-edged sword.outsideloop - Monday, May 17, 2021 - link
I want to see a comparison of the 11980HK with the 5800X clocked down to 65W, apples to apples. Let's compare the thermals of the AMD 8-core desktop to this "desktop replacement" Intel 8-core.Hifihedgehog - Monday, May 17, 2021 - link
Core i9-11980HK:https://images.anandtech.com/doci/16680/P95-45W_57...
Ryzen 9 5980HK:
https://images.anandtech.com/doci/16446/Power-P95-...
Just to add some further insight on these two charts, here is some breakdown. What ultimately happens is under sustained heavy loads, Ryzen 5000 series can maintain 8 cores at higher sustained clock speeds (~3.7 GHz) with lower power draw (35W). Bear in mind also that Zen 3 has a slight IPC advantage over Tiger Lake, meaning at a lower clock speed, it performs the same or does the same amount of work as Tiger Lake at a higher clock speed. Yet here we are where Ryzen 5000 can clock higher, do even MORE work, and draw less power. Meanwhile, Intel is struggling to reach similar sustained clock speeds (~3.2 GHz) at 45W sustained and it has slightly lower IPC. That is, Ryzen 5000 is ~10% faster clock-for-clock (or in IPC) than Intel's Willow Cove (Tiger Lake 11th Gen), Cypress Cove (Rocket Lake 11th Gen) or Sunny Cove (Ice Lake 10th Gen) which all three share roughly the same IPC amongst the whole trio (link: https://www.guru3d.com/articles_pages/intel_core_i... ). Ryzen 5000's synergy (higher clocks, lower power, higher IPC) sounds like a recipe for disaster for Intel, no? Alder Lake needs to come sooner rather than later if you ask me. Let's just hope Intel is throwing the full weight of their massive workforce of software developers at the problem of Alder Lake's heterogenous architecture because they will certainly need it working smoothly for it to shine.
lmcd - Monday, May 17, 2021 - link
Can we pause to note that MSI delivering bad thermal performance is characteristic of every single one of their laptops, bar none?lmcd - Monday, May 17, 2021 - link
Like, obviously that doesn't solve all the problems here, but how on earth with all the delays TGL-H(45+) got is this the OEM Intel picked?Spunjji - Tuesday, May 18, 2021 - link
It's a very odd choice. But then, didn't they use MSI for the original TGL reference platform too? That one actually outperformed most shipping devices, although IIRC it did so by running the fans at 100% 🤷♂️lmcd - Tuesday, May 18, 2021 - link
I put it on twitter also but my opinion is that the Tiger Lake MSI design is actually about the cooling and size that MSI would use for an H series processor normally, such as the MSI Creator.This implies that the MSI's thermal overhead is pure luck on Intel's part in that MSI didn't have time to reduce the thermal performance accordingly.
Spunjji - Thursday, May 20, 2021 - link
That would make sense!boozed - Monday, May 17, 2021 - link
"Power Hungry" lol shock mesellappa - Monday, May 17, 2021 - link
Searched for "battery life" and couldn't find it. Waiting for battery life data.Brett Howse - Monday, May 17, 2021 - link
This is an engineering sample. We won't be doing battery life testing on it.mode_13h - Monday, May 17, 2021 - link
> This is an engineering sample. We won't be doing battery life testing on it.WTF? You mean the CPU isn't final production-run? If so, why is this labelled a "review" and not a "preview"?
Dolda2000 - Monday, May 17, 2021 - link
The laptop is an engineering sample, not the CPU.Andrei Frumusanu - Tuesday, May 18, 2021 - link
We purposefully called it "Performance Review" of the CPU in the title.The laptop itself is generally irrelevant as you will not be able to buy it, besides the fact that it's a an engineering sample.
mode_13h - Tuesday, May 18, 2021 - link
> it's a an engineering sample.Do you use the terms "engineering sample" and "reference design" interchangeably, or is there a significant distinction?
mode_13h - Tuesday, May 18, 2021 - link
FWIW, I think there *is* a distinction and that the laptop is really a reference design. If Intel were selling their own laptops, then you could call a pre-release laptop an "engineering sample". If it's just a demonstration vehicle for their chips, then it's a "reference design".Where the waters could get muddy is if Intel's lawyers have a lot of scary contracts threatening to sue you into oblivion if you sell on an engineering sample, as sometimes happens. And maybe they just chose to call the laptop an "engineering sample", so they could reuse those same legal agreements, rather than having to edit them so they instead apply to its reference boards/laptops.
isthisavailable - Monday, May 17, 2021 - link
AMD clearly has the "flagship" laptop CPU yet Intel still has the audacity to make new high end laptops exclusive to their processors by bribing OEMs.Spunjji - Tuesday, May 18, 2021 - link
To be fair, some of the OEMs do not seem to require any bribery.HendoAuScBa - Tuesday, May 18, 2021 - link
How confident are you with that Compile test result? You have the i9-11980HK at 86.9 compiles per day which is a huge jump higher than the best desktop CPUs listed on your benchmark page (the best of which is the i9-11900K at 77).https://www.anandtech.com/bench/CPU-2020/2974
Also, that benchmark page is missing Zen 3 mobile results that you've included in this article.
mode_13h - Tuesday, May 18, 2021 - link
It's eye-catcing, alright. I was also wondering about it.Could it be due to the laptop simply having more RAM or an Optane SSD or something? Mitigations are another thing that comes to mind.
RobJoy - Tuesday, May 18, 2021 - link
Intel is about 1.5 years behind the competition.Once their 5nm fab starts puking out some silicon, we might see them return in the fold.
But that's like 2023 or even 2024.
Until then, accept the fact that Intel HAS competition.
mode_13h - Tuesday, May 18, 2021 - link
> puking out some siliconLOL. I used to work with a guy who used another bodily function as an analogy for the operation of a systolic pipeline. You wouldn't have to think very hard to guess it.
usiname - Tuesday, May 18, 2021 - link
More like 2025, i doubt they will realese just 1 gen with 7nm and will rush to new processdrothgery - Wednesday, May 19, 2021 - link
I wouldn't be shocked to see them rebrand their "7nm" as something with a 5 in it that gets called "5nm" by the press; it wouldn't be unreasonable.LordSojar - Tuesday, May 18, 2021 - link
Good lord the power consumption on these chips... Intel DESPERATELY needs 7nm.usiname - Tuesday, May 18, 2021 - link
You know their 10nm has same transistor density as 7nm TSMC? They don't need new proces, they need new engineersmode_13h - Tuesday, May 18, 2021 - link
> their 10nm has same transistor density as 7nm TSMC?Which 10 nm, though? From what I heard, Ice Lake's density is lower than Cannon Lake's. And I'm not sure if SF or ESF reduced it, further.
Otritus - Wednesday, May 19, 2021 - link
Ice lake having a lower density isn't demonstrative of differences in process density. When designing Sunny Cove, the engineers may not have cared about density, and instead focused on performance and efficiency, resulting in Sunny Cove being less dense than Palm Cove (Cannon Lake). Intel's 10nm being slightly denser than TSMC's 7nm also doesn't mean that it is more efficient. When moving from TSMC's less-dense 7nm to Samsung's more-dense 5nm, mobile SOCs appeared to suffer from a regression in efficiency. Intel needs a node that is both performant and efficient and better engineering because their architectures are clearly less efficient than the competition. Golden Cove might fix Willow Cove's poor density and performance per watt, or we might be waiting till 2023-4 when Intel expects to be properly competitive again.Bagheera - Tuesday, May 18, 2021 - link
Intel isn't gonna have enough EUV in time to ramp 7nm by 2023. they are in serious trouble and floating on borrowed time, most analysts just aren't aware.https://semiwiki.com/forum/index.php?threads/will-...
Intel's 10nm is indeed competitive with TSMC 7nm in terms of density, but AMD will be moving to 5nm with Zen 4 next year, what can Intel's response be? They can increase outsourcing to TSMC but that means less utilization of their own fabs which is bad. They absolutely won't be able to get 7nm ready in time to compete with AMD on TSMC 5nm. It will be back to the status quo of Intel lagging behind AMD by one full node, and likely foregoing power efficiency for performance parity.
Bagheera - Tuesday, May 18, 2021 - link
no actual semiconductor professional expected Intel 10nm to surpass TSMC 7nm in any tangible way. the only people who expected otherwise are uniformed enthusiasts (usually gamers, who the to be partial to Intel)The gap will only widen from here. Intel really shot itself in the foot with bad EUV planning.
https://semiwiki.com/semiconductor-services/ic-kno...
watzupken - Tuesday, May 18, 2021 - link
I feel this review concludes that Intel have effectively lost their competitive edge when their fab started to lag behind. In fact, its also conclusive that the SuperFin is really nothing super at all even when compared to TSMC's 7nm. Its just 10nm on steroids just like what they have been doing to their 14nm. From an architect standpoint, Willow Cove is decent, but the bulk of the performance is due to pushing for very high clock speed at the expense of very high power consumption. If this was released on a desktop, it will be a hit. But on mobile, I don't think one can easily find a laptop that have the cooling capability to tame the heat output and also maintain a decent battery life. Especially this processor will likely be paired with a high end GPU. To me, this is a worrying trend for Intel because they will likely have to stick around with 10nm for another couple of years at least. If their new CPU architect is unable to provide decent IPC gains without bursting the power limit, they will surely be in trouble, especially when AMD's 5nm chips may appear in the market first.mode_13h - Tuesday, May 18, 2021 - link
> If this was released on a desktop, it will be a hit.Yes.
> I don't think one can easily find a laptop that have the cooling capability
> to tame the heat output and also maintain a decent battery life.
At 35 W, it would probably make a fine laptop. Unfortunately, competitive pressure is pushing Intel to juice their CPUs more than they really should.
sandeep_r_89 - Tuesday, May 18, 2021 - link
Can you please please stop using the word BIOS for modern devices? Pretty much all devices have been on UEFI only for several years now.Silver5urfer - Tuesday, May 18, 2021 - link
Ah the M1 fastest CPU ever, doesn't make it to SMT SPEC scores for some reason, like always. Don't worry we will see the Apple CPU which would be X version of the chip iteration when it finally catches up to the SMT of these SMT until then M1 is the best CPU ever.TGL machines will throttle to peak with the thin and light garbage heatsinks. That's a given, people should stop buying these parts. Laptop batteries will be destroyed eventually and none of them will have the Dell Desktop Power plan only Workstations have that feature (Lenovo and Dell), Alienware used to have, not sure about now their A51M R1 and R2 also they had their GFX modules smoke, anyways the battery won't be available for the end user to service and the expensive machine will die and BGA with soldered HW to further limit everything, add the overheating NVMe SSDs due to poor ventilation, happens in Alienware machines too which are targeted as maximum performance.
Spunjji - Thursday, May 20, 2021 - link
🤪🤡😤🤬🤥💩mode_13h - Friday, May 21, 2021 - link
Oof. Looks like *someone* is giving Emojipedia a workout!: )
Spunjji - Tuesday, May 18, 2021 - link
This ended up how I was expecting - superior single-core performance where there's thermal headroom, dropping down to broadly competitive multi-performance at the rated TDP, and with a faintly ludicrous maximum power draw under all-core boost.I'm glad it's competitive. That's needed. What I'm a little less glad about is that we're almost certainly in for another round of CPU performance varying *wildly* between different designs, which has been true to some extent for a while, but getting steadily worse ever since Ice Lake showed up.
Given most OEMs' approach to cooling, I'd wager that the average device shipping with Cezanne will provide better CPU performance than the average device with Tiger 45 simply because of Cezanne's greater efficiency.
tekit - Tuesday, May 18, 2021 - link
Heard they enabled undervolting again for tiger lake-h, can anyone confirm? I wonder how much undervolting potential there is and if that could balance the equation against AMD.Bbdffd - Tuesday, May 18, 2021 - link
I think AMD still not able to defeat intel in Gaming even with their 7nm processor (5980hs).Cooe - Thursday, May 20, 2021 - link
"The performance lead against AMD’s strongest mobile CPU, the 5980HS"The 35W R9 5980HS is NOT AMD's strongest mobile CPU Brett. That would be the 45W unlocked & higher clocked R9 5980HX. I expect better from AnandTech... -_-
Spunjji - Thursday, May 20, 2021 - link
It is a little bit complicated... the 5900HX appears to beat the 5980HS by a little way in multi-thread tests but fall behind in single-thread, and if you look at things in performance-per-watt terms the 5980HS is easily the strongest. There's also the fact that there don't seem to be any shipping devices with the 5980HX in them. Strange times.ottonis - Friday, May 21, 2021 - link
So well, according to Intel's advertising materials, their new 11th gen Tiger Lake based 8c mobile CPUs were supposed to wipe the floor with AMD.Well... not really, according to this review, at least not within the same power consumption envelope and in multicore tasks.
block2 - Monday, May 24, 2021 - link
Running Intel at 35w if possible would be interesting.Unclear on quick read if external GPUs were disabled so that these tests aren't in reality a GPU test.
JayNor - Friday, May 28, 2021 - link
news out today in tomshardware that there is a B series of the 8 core TGL that boosts to 5.3GHz. This is even for parts with the GPU ...mode_13h - Saturday, May 29, 2021 - link
About right, for a desktop CPU.Makste - Monday, May 31, 2021 - link
This is a NUC part, not a laptop part.mode_13h - Tuesday, June 1, 2021 - link
Not really. NUCs normally use the U-series notebook CPUs. That's all a NUC is -- a notebook CPU in a compact enclosure.NUC Extreme is something completely different. They're more like a normal desktop PC, and the latest NUC Extreme that Intel just announced is the one that will use these H-series CPUs.