Intel Atlas Canyon (NUC11ATKPE) and GEEKOM MiniAir 11 UCFF PCs Review: Desktop Jasper Lake Impresses
by Ganesh T S on July 14, 2022 8:00 AM ESTSystem Performance: Miscellaneous Workloads
Standardized benchmarks such as UL's PCMark 10 and BAPCo's SYSmark take a holistic view of the system and process a wide range of workloads to arrive at a single score. Some systems are required to excel at specific tasks - so it is often helpful to see how a computer performs in specific scenarios such as rendering, transcoding, JavaScript execution (web browsing), etc. This section presents focused benchmark numbers for specific application scenarios.
3D Rendering - CINEBENCH R23
We use CINEBENCH R23 for 3D rendering evaluation. R23 provides two benchmark modes - single threaded and multi-threaded. Evaluation of different PC configurations in both supported modes provided us the following results. It must be noted that this is specifically an academic test for CPU prowess. No consumer should expect to use these low-power systems for serious rendering tasks.
The numbers bring out the Jasper Lake improvements over Gemini Lake perfectly. Between the Jasper Lake systems, we see ordering based on PL1 / PL2 levels - the Atlas Canyon NUC comes out on top, followed by the MiniAir 11.
Transcoding: Handbrake 1.5.1
Handbrake is one of the most user-friendly open source transcoding front-ends in the market. It allows users to opt for either software-based higher quality processing or hardware-based fast processing in their transcoding jobs. Our new test suite uses the 'Tears of Steel' 4K AVC video as input and transcodes it with a quality setting of 19 to create a 720p AVC stream and a 1080p HEVC stream.
Software transcoding rates again see the same behavior as what was observed for 3D rendering - Jasper Lake performs way better than Gemini Lake at similar power levels, but passively-cooled systems do not possess sufficient prowess to match actively-cooled ones for this workload irrespective of SoC generation.
The integrated GPUs are similar in both Gemini Lake and Jasper Lake - therefore, the QuickSync transcode rates (tied to the GPU clocks) scale with the GPU frequency and power budget. Atlast Canyon has the highest power budget, followed by the MiniAir 11 / June Canyon. However, the June Canyon's GPU runs at a base of 200 MHz, compared to the 450 MHz of the MiniAir 11. These dictate the relative ordering of the QuickSync transcode rates in the above graphs.
Archiving: 7-Zip 21.7
The 7-Zip benchmark is carried over from our previous test suite with an update to the latest version of the open source compression / decompression software.
The updated microarchitecture of the Tremont cores enable the actively cooled Jasper Lake systems to get past the June Canyon NUC. Between the Atlas Canyon and the MiniAir 11, the ordering is left to the PL1 / PL2 settings and higher boost clocks for the Pentium Silver N6005 in the former.
Web Browsing: JetStream, Speedometer, and Principled Technologies WebXPRT4
Web browser-based workloads have emerged as a major component of the typical home and business PC usage scenarios. For headless systems, many applications based on JavaScript are becoming relevant too. In order to evaluate systems for their JavaScript execution efficiency, we are carrying over the browser-focused benchmarks from the WebKit developers used in our notebook reviews. Hosted at BrowserBench, JetStream 2.0 benchmarks JavaScript and WebAssembly performance, while Speedometer measures web application responsiveness.
From a real-life workload perspective, we also process WebXPRT4 from Principled Technologies. WebXPRT4 benchmarks the performance of some popular JavaScript libraries that are widely used in websites.
While the artificial JetStream and Speedometer benchmark numbers are along expected lines - the actively-cooled Jasper Lake systems on top, with the MiniAir 11 coming in second due to the lower power budget and clocks. In the real-world WebXPRT4 workload, the JSLM-MINI gets a slight edge despite its passively-cooled nature. With a higher boost clock (3.3 GHz capable of getting reached for short durations), this workload sees it performing better than the MiniAir 11's Celeron N5095 with its 2.9 GHz boost.
Application Startup: GIMP 2.10.30
A new addition to our systems test suite is AppTimer - a benchmark that loads up a program and determines how long it takes for it to accept user inputs. We use GIMP 2.10.30 with a 50MB multi-layered xcf file as input. What we test here is the first run as well as the cached run - normally on the first time a user loads the GIMP package from a fresh install, the system has to configure a few dozen files that remain optimized on subsequent opening. For our test we delete those configured optimized files in order to force a fresh load every second time the software is run.
As it turns out, GIMP does optimizations for every CPU thread in the system, which requires that higher thread-count processors take a lot longer to run. So the test runs quick on systems with fewer threads, however fast cores are also needed. All the systems being considered today are 4C/4T in nature, so it is a measure of clock speeds and power budget, with the disk subsystem playing a small role. The Atlas Canyon NUC and the ECS JSLM-MINI takes up the top spots. The CI331 nano and the MiniAir 11 are fairly close together, with the disk subsystem (better SATA SSD in the CI331 nano) giving it a slight edge. The Gemini Lake cores are well behind Jasper Lake for the disk subsystem to not matter in the relative ordering of the June Canyon NUC.
Facebook
Twitter
RSS
21 Comments
View All Comments
flgt - Thursday, July 14, 2022 - link
Nice article. I don’t like how so much performance is driven by relatively hidden PL1/PL2 settings. Have regular NUC12’s been released yet?AdrianBc - Friday, July 15, 2022 - link
Intel has developed a "Wall Street Canyon" NUC with Alder Lake P, as a replacement for the NUC 11 Pro with Tiger Lake, and which has about the same interfaces but with a much faster CPU.Photos of working prototypes have been leaked, but the launch of the product has been delayed for unknown causes, maybe component shortages. Nevertheless, I do not believed that it will be canceled, but maybe it will be launched later this year.
A very similar NUC-like barebone is already available from ASRock Industrial, as "NUC BOX-12xxP", e.g. "NUC BOX-1260xP", which, compared to Intel, has dual 2.5G Ethernet instead of single 2.5G Ethernet, and 3 DisplayPort (2 on TB) + 1 HDMI instead of 2 DisplayPort (both on TB) + 2 HDMI.
AdrianBc - Friday, July 15, 2022 - link
Sorry, I have pressed "Submit" without rereading and there are a couple of typos.The names for the ASRockInd alternatives are "NUC BOX-1260P", "NUC BOX-1240P", etc.
mode_13h - Friday, July 15, 2022 - link
OMG. I thought "Wall Street Canyon" NUC was a joke. Still funny, though.Sivar - Thursday, July 14, 2022 - link
Some means to compare these values vs. a full desktop CPU would be helpful. In isolation, I can see that the Pentium Silver N6005 is much faster than the J5005, but I have no idea if it is 90% the performance of a desktop CPU, or 60%, or 4%, etc.Perhaps a link to a reasonably comparable desktop CPU review.
mode_13h - Friday, July 15, 2022 - link
> Some means to compare these values vs. a full desktop CPU would be helpful.100% agree. We do have a few data points, however. Using data from https://www.anandtech.com/show/17231/the-intel-cor... we can see:
CineBench R23: Single-threaded
-----------------
NUC11ATKPE: 716
Ryzen 3 5300G: 1338
Ryzen 5 5600G: 1434
i3-12300: 1705
CineBench R23: Mulitthreaded
-----------------
NUC11ATKPE: 2521
Ryzen 3 5300G: 6770
Ryzen 5 5600G: 10601
i3-12300: 8598
Obviously, software rendering is not the kind of workload Tremont is optimized for.
Next, there's Handbrake, but the i3-12300 article used version 1.3.2 and this uses 1.5.1. Without at least a benchmark of the same hardware on both versions, we can't know how much variation is introduced by the new software version.
7-zip might have a similar version difference (earlier article references "1900", while this one uses 21.7), and it's not clear if the test cases are even the same.
And that's basically all the overlap I found. That's less than I thought or hoped for. It's disappointing how much the software versions and format of the results changed, such that I can't even tell whether a given test is using the same workload between the articles.
Hresna - Tuesday, July 19, 2022 - link
Funny, I was just thinking this yesterday. It’s widely impractical I know but perhaps a single chart showing the numbers in context of “modern desktop computing” would add to the general consumption-ability for us casual readers.For so many reviews I end up side-channel trying to look up/remember “ok, what’s my firestrike number again?”.
t.s - Thursday, July 14, 2022 - link
"a 2022 consumer-focused NUC without a single Type-C port is strange to see" LOL. Hello. This is Intel we're talking about, bro.abufrejoval - Thursday, July 14, 2022 - link
Well, you certainly did a much better job than I did with my Atlas Canyon NUC and caught me with quite a few mistakes, too. E.g. I had mis-identified the front panel header hidden under the rubber cap as a USB2 port.I also hadn’t really noticed that PL1/2 had gone to 15/25 in the max performance settings, I guess I was still relying far too much on my Gemini Lake observations.
I’ve never actually observed 25 Watts with HWinfo, the iGPU never goes beyond 5 Watts and the CPU will stay shy of 15 resulting in a 20 Watt total.
For the NUC’s WIFI the most important aspect is that it’s socketed, unlike e.g. on the Tiger Lake NUC11. I had bought a bunch of AX200 cards some time back, because at just €20 they were twice the price of shipping and I replaced the WIFI before I even booted the system.
I got a whole box of below-acceptable WIFI cards, that’s just electronic waste from the factory, because quite a few high-range notebooks also come with such crippling kit.
Likewise, I have another box of RealTek based USB3 2.5 Gbit/s Ethernet adapters, to bring a bit of balance to these systems, which I tend to use with GlusterFS.
I also didn’t have DDR4-2933 SO-DIMMs lying around and was ever so glad the 2x 32GB DDR4-3200 I borrowed from my Tiger Lake NUC11 worked, even if they took quite a bit of time at the initial boot to be configured properly.
DDR4-2400 SO-DIMMS will work just as well and honestly there is very little real difference in performance. The memory bandwidth on Geekbench 4 will change from 16.9/GBs to 17.3GB/s for single core and from 22.2GB/s to 25.6GB/s on multi core. The same DDR4-3200 SO-DIMMs deliver 35.6GB/s single core memory bandwidth with the Tiger Lake’s i7-1165G7 and 39.7GB/s on the multi-core variant, which would almost seem to indicate, that the latest Atom continues to be a single-channel design, like the J5005, N3700 and J1900 predecessors, where the 2nd module never delivered more than a 10% bandwidth increase.
Jasper lake drops to 12.8GB/s with a single module on both the single and the multi core variants of the Geekbench 4 memory bandwidth benchmark and I’m sure the impact on the iGPU would be rather significant, even if I didn’t measure to confirm.
Next I dropped PL1/PL2 to 10/12 Watts (the BIOS won’t allow 10/10) and TAU to 1 second, just to see differentiate properly between the generational improvements of Jasper Lake vs. Goldmont Plus and the additional TDP budget: it barely made a difference on Geekbench 5, whilst HWinfo did confirm that the lower TDP limits were indeed observed.
It takes Prime95 to confirm, that the TDP budget difference has an impact on the clocks, Geekbench is just too light a workload. And in combination with Furmark, you can also nicely observe that the iGPU TDP share is fixed at 5 Watts, while the CPU core have to manage with what’s left at 25 or 15 Watts after TAU.
I do believe the Atlas Canyon NUC11 is a rather good deal for the €200 price, if you can get one. I’ve found a niche dealer here in Germany (minipc.de), that still has dozens in stock but that seems a rare exception. There are still some N6005 based firewall appliances available from China, even fully passive but at closer to €500 before taxes.
Ian started to ruminate on how he’d be able to measure the generational improvements of Grace Mont over Jasper Lake by using Lasso to control CPU core assignments on an Alder Lake base. Too bad he then never got around testing that, because it could have helped to gauge a hypothetical all-E-core chip.
Jasper Lake does rather well against say a Broadwell based Xeon D-1541 at 2.7GHz so it’s easy to see why they are not to keen on seeing these low-end devices compete in the mini-server market. Elkhart Lake Atoms variants which support inline ECC would certainly create an issue, if they sold for a similar price than Jasper Lake (I heavily suspect they are the same silicon). But a SuperMicro mainboard with zero other distinguishing features (e.g. only Gbit Ethernet) is listed at €800, way beyond what I’d want to pay for ECC alone.
mode_13h - Friday, July 15, 2022 - link
> DDR4-2400 SO-DIMMS will work just as well and honestly there is very little real difference in> performance. The memory bandwidth on Geekbench 4 will change from 16.9/GBs to 17.3GB/s
> for single core and from 22.2GB/s to 25.6GB/s on multi core.
> ... the latest Atom continues to be a single-channel design
> Jasper lake drops to 12.8GB/s with a single module on both the single and the multi core
That's a 35% benefit for single-core and a 100% boost for multi-core. Whatever is going on there, I think it's simplistic to say the SoC is simply designed for single-channel.
It's weird that they hampered it, because they're just leaving performance on the table. I wonder if maybe the memory controller is more optimized for LPDDR4 and the regular DDR4 performance is more of an afterthought.
BTW, thanks for your TDP testing, also.