Sign in with
Sign up | Sign in

Celeron J1750: Bay Trail Is Faster And Much More Efficient

Bay Trail On The Desktop: Celeron J1750 Gets Benchmarked
By

When Intel introduced us to its Silvermont architecture, the company made grand claims of increased performance at a given thermal ceiling, or similar performance at reduced power. Naturally, we couldn't wait to get our hands on one of the first implementations, but it was understood that the Bay Trail-based SoCs featuring this new design wouldn't be ready until the second half of 2013.

Intel showed off the Atom Z3000 series for tablets at IDF last week, putting real benchmark data behind those earlier claims. And while we're positively inquisitive about how Bay Trail might deliver a better experience in more taxing applications and simultaneously stretch battery life out across a day, we were busy testing a desktop-oriented version of the SoC. Whereas the Atom Z3000s are only running in 32-bit environments, our testing took place under Windows 8 64-bit.

Indeed, there's certainly something to be said for using one form factor to compare multiple products against each other. To that end, our power and efficiency numbers are what impressed me most. It's clear from the logging power over time and charting performance that the dual-core Celeron J1750 isn't as fast as the least-expensive Ivy Bridge-based Celeron you can find on Newegg. And maybe Celeron branding isn't even appropriate for a 10 W SoC in an entirely different league.

But we still see that the entry-level J1750 finishes our suite of tests significantly faster than Atom D2700. Yes, the Atom-based platform has an on-board GeForce GT 520 GPU that we cannot factor out of our power equation, which affects our ability to compare their efficiency directly. The discrete graphics chip also conveys a performance advantage in 3D titles too, though. Just remember that the Atom D2700 is a 10 W part, similar to Celeron D1750, and that GeForce GT 520 uses up to 29 W. Remove the GPU and you'd likely be looking at very similar power from last generation's Atom. Based on our performance data, Bay Trail still comes away with an indisputable blue ribbon for efficiency.

And all of this comes from two Silvermont cores. The Pentium J2850 gives you four of them, the same 2.4 GHz peak core clock, higher graphics engine frequencies, and again, a 10 W thermal ceiling. Naturally, we're expecting an even more compelling performance story in our threaded tests once the quad-core models start surfacing. 

Until then, we walk away from our first experience with Intel's Bay Trail SoC impressed. The company wasn't exaggerating when it suggested that the Silvermont architecture could as much as double performance at a given power limit. Snappy little passively-cooled platforms are almost certainly on their way toward the end of the year. Intel tells us that its partners are already working on fully integrated desktops and all-in-one designs, as well as channel-oriented motherboards with soldered-down CPUs.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 23 comments.
This thread is closed for comments
  • -6 Hide
    SteelCity1981 , September 16, 2013 9:31 PM
    only 2mb of l2 cache for 4 cores. talk about starving 4 cores with 2mb of l2 cache.
  • -6 Hide
    DjEaZy , September 16, 2013 10:11 PM
    ... interesting is the modular core thingy.. it ir like the FX module from AMD... 2 cores on joined L2 cache? Hmm... and GPU on the silicon... it seams, intel waits till the software is there...
  • 5 Hide
    stickmansam , September 16, 2013 10:36 PM
    Quote:
    ... interesting is the modular core thingy.. it ir like the FX module from AMD... 2 cores on joined L2 cache? Hmm... and GPU on the silicon... it seams, intel waits till the software is there...


    Shared L2 cache exists on Intel's side during the Core 2 era with two or more cores sharing the L2 cache, similar to how L3 cache is shared now except there is an additional private L2 cache. Basically, with Nehalem, Intel moved the shared cache a level lower to L3 and put in a new private cache (L2). GPU on the same die/chip has been on Intel's side too for quite a while as well....

    Quote:
    only 2mb of l2 cache for 4 cores. talk about starving 4 cores with 2mb of l2 cache.


    The i5s have actually less cache than the Q9x50's so cache size isn't everything. Their ipc is still lower than the Athlon IIx4's which have similar amounts of cache are not that bottle necked (compared to Phenom II's, maybe 20% slower?). Cache implementation also matters and the shared L2 should be better than the piecemeal Athlon II L2, provided the cores don't thrash each other.

    Bay Trail is a quite interesting chip with good enough performance to pretty much beat out most ARM chips in tablets yet provide comparable power efficiency and graphics. The price is not too high either, with the top end chip ~$40, making it at least somewhat competitive with ARM. The ability to run Android/Linux/Windows 8 means that OEM's can build one product to sell to different markets and save on production line costs. It also lets them adjust the OS to meet market demand on the go potential (ship non selling OS version back to factory and load OS that sells better and send it back out). ASUS seems to have something like that going on with the T100 having buttons half way between Windows and Android and no Windows branding.

    This all makes me want to grab a Bay Trail and run both Android and Windows on it, have Windows when I use it connected to a screen for desktop and run desktop apps and then Android on the go so I get the larger app store (Windows if I am lazy).
  • 6 Hide
    vipervoid1 , September 16, 2013 10:56 PM
    There is Kabini in the review ??
    Why compare Richland with this ??
    Isn't Kabini is the one to compare ??
  • 2 Hide
    runswindows95 , September 16, 2013 10:58 PM
    Then again, the thing to keep in mind these CPU's aren't gaming / workstation CPU's. These CPU's will quite honestly work for the majority of PC owners, who mainly do social media and Youtube. A quad-core that only uses 10W intrigues me a lot since I don't game, but do a lot of heavy word processing.
  • 2 Hide
    Cryio , September 17, 2013 12:30 AM
    Hey Tom. Winrar 5 is out. Could you please use that? :D 
  • 4 Hide
    ojas , September 17, 2013 3:12 AM
    Quote:
    There is Kabini in the review ??
    Why compare Richland with this ??
    Isn't Kabini is the one to compare ??

    Agreed.

    Though, Tech Report and AnandTech have previewed the Z3770 and put it up against mobile chips and Kabini.

    (hint: the 4w Z3770 matches a 15w A4-5000 Kabini and soundly thrashes ARM in CPU performance)

    http://techreport.com/review/25329/intel-atom-z3000-bay-trail-soc-revealed

    http://www.anandtech.com/show/7314/intel-baytrail-preview-intel-atom-z3770-tested
  • 3 Hide
    de5_Roy , September 17, 2013 3:38 AM
    i sorely missed a kabini setup in the benches and efficiency tests. i woulda liked to see both bay trail and kabini socs run 1080p and 1600p gaming (tablet oriented).

    a few nitpicks:
    in the test hardware chart - a4 4000 doesn't have L3 cache. afaik, neither does baytrail (1MB shared L2).
    in the bga 65w skus vs bga 10 skus table, the core i- cpus clockrates are base clockrate, turbo is missing while baytrail socs' burst clockrate is reported while base clockrate is absent.
  • -5 Hide
    Wisecracker , September 17, 2013 6:33 AM

    Quote:
    Quote:
    There is Kabini in the review ??
    Why compare Richland with this ??
    Isn't Kabini is the one to compare ??

    Agreed.

    Though, Tech Report and AnandTech have previewed the Z3770 and put it up against mobile chips and Kabini.

    (hint: the 4w Z3770 matches a 15w A4-5000 Kabini and soundly thrashes ARM in CPU performance)

    http://techreport.com/review/25329/intel-atom-z3000-bay-trail-soc-revealed

    http://www.anandtech.com/show/7314/intel-baytrail-preview-intel-atom-z3770-tested


    Not according to Tom's ...



















    Power consumption looks great ... especially compared to a 65w Richland desktop (WTF, THG?) ... but the A4-5000 remains quite formidable in efficiency according to Tom's own testing

    Graphics performance compared to the AMD SoCs must blow, or it would have been hyped to the max. I suspect this means Bay Trail will be Temash'd (or, Kabini'd).


  • 0 Hide
    CaedenV , September 17, 2013 7:08 AM
    Looks like these new Atom based Celerons and Pentiums are what I want to look for in my little always-on server build I am prepping for. Extremely low power, enough performance to run a gigabit NAS, and hopefully some passive or other extremely quiet cooling solutions. I just hope that the motherboards offer some RAID options to work with in FreeNAS and the price is appropriately cheap.
  • 2 Hide
    RedJaron , September 17, 2013 7:59 AM
    Now stick this new chip in something like a Surface so I can finally have a good x86 tablet for under $600.
  • 3 Hide
    Ilander , September 17, 2013 8:20 AM
    ...What difference in efficiency numbers should we expect if you're not using an 860 W power supply? Or do you all now have a meter that measures at the motherboard? For those interested, the AX860i advertises 85% efficiency at 10% total power usage, meaning 86 Watts. Everything here is below that, meaning the numbers are actually all scaled upward by a factor inversely proportional to their loads, meaning the lowest wattages get the worst handicap. An 80+platinum 400 W would have been much better, such as the SeaSonic SS-400FL2. At least then, the efficiency at 40 Watts would be documented (82%). Still, overall, very interesting.
  • 1 Hide
    RedJaron , September 17, 2013 9:01 AM
    Quote:
    ...What difference in efficiency numbers should we expect if you're not using an 860 W power supply? Or do you all now have a meter that measures at the motherboard? For those interested, the AX860i advertises 85% efficiency at 10% total power usage, meaning 86 Watts. Everything here is below that, meaning the numbers are actually all scaled upward by a factor inversely proportional to their loads, meaning the lowest wattages get the worst handicap. An 80+platinum 400 W would have been much better, such as the SeaSonic SS-400FL2. At least then, the efficiency at 40 Watts would be documented (82%). Still, overall, very interesting.

    Methinks their normal testbed has that PSU simply to accommodate any kind of platform ( even up to SB-E w/ SLI/XFire. ) You're right, no one using Bay Trail in a desktop would have such a huge PSU.
  • 3 Hide
    cangelini , September 17, 2013 9:18 AM
    Quote:
    There is Kabini in the review ??
    Why compare Richland with this ??
    Isn't Kabini is the one to compare ??


    Operating from memory, I believe Kabini is available on an HP all-in-one and a handful of notebooks currently. We don't have the HP in-house to test, and the notebook-oriented products don't fit with the desktop processors tested here. We bought the cheapest Richland and Ivy Bridge CPUs on Newegg, and dug up the old Atom D2700 (it's only a shame we couldn't get around its discrete GPU).

    I'd love to get my hands on a desktop Kabini-based setup to test for comparison, but we simply don't have that yet.
  • 2 Hide
    cangelini , September 17, 2013 9:22 AM
    Quote:

    Graphics performance compared to the AMD SoCs must blow, or it would have been hyped to the max. I suspect this means Bay Trail will be Temash'd (or, Kabini'd).


    Or maybe there's just not much of a point running a bunch of desktop 3D workloads when we already know what six EUs at higher clocks can do from HD Graphics 2000. None of the platforms we tested are even good for WoW at 720p.
  • 0 Hide
    MANOFKRYPTONAK , September 17, 2013 10:21 AM
    This is great, finally Intel is getting serious about mobile. The old atoms sucked so bad... This will be great for the end consumer. I mean Arm, Intel and AMD? 3 competing to be number one in mobile, means better performance for less $
  • -1 Hide
    ta152h , September 17, 2013 10:51 AM
    Another disappointing article from Tom's. Being late, I was still waiting for a 'real' review from this site compared to the others, so I could actually get a feel for the chip. But, nope.

    Isn't it pretty obvious that this chip will competing in a major way with the Jaguar? I think someone is lurking at Tom's with a stupid stick waiting for anything related to the Jaguar to pop up. Benchmark the Jaguar against the i3. Benchmark the Bay Trail against the Richland. Huh?

    After years of Tom's doing interesting stuff like matching clock speeds to see the IPC, and other interesting tests, we get this. The other processors are fine to put in, but really, they aren't the main competitors. Even so, interesting data points. Leaving out Jaguar is just bizarre and seriously dilutes the value of it. In fact, I stopped on page three once I realized it REALLY wasn't being compared. It took me that many pages to actually believe it.
  • 0 Hide
    ojas , September 17, 2013 10:58 AM
    @Wisecracker: You're almost correct, and i say almost because you're comparing a quad-Jaguar part to a dual-Silvermont part.

    Also, look the WinZip EZ and CPU results again, their order is different on both charts. Dual-Silvermont has a ridiculous advantage over Kabini in the EZ test, and is pretty similar in the CPU test. Heck, even the OpenCL results are very close.
    Those are definitely not comparable, i think the file sets are different, i don't see how the ivy bridge based celeron can beat a core i3. Or, how Bay Trail can beat pentium and Ci3 in the EZ test.

    Look at the AnandTech piece (i'm reading the TR article right now, hadn't till now) to see what happens when you go quad-Silvermont.

    It's absolutely crazy what Intel has done here. Crazy. Reminds you of how mature x86 is, compared to ARMv7.

    Extremely interested to see how the Apple A7 compares to the Z3770, though i think it would be a better idea to compare it to a Z3600 part.

    I think Apple and Intel have both outdone themselves. Former was a surprise, latter not so much.

    And yeah, in terms of GPU performance, Kabini >> Bay Trail.

    TR seems to pretty much confirm AT's tests:











    Note: Epic Citadel is On-screen, so is the first 3DMark; the Bay Trail system has a 1440p display, Nexus 7 and TF Infinity are 1080p.
  • 1 Hide
    cangelini , September 17, 2013 1:07 PM
    Quote:
    Another disappointing article from Tom's. Being late, I was still waiting for a 'real' review from this site compared to the others, so I could actually get a feel for the chip. But, nope.


    You may have missed the part where a number of other sites were able to preview tablets at Intel's HQ in Santa Clara and where we got our hands on a very early motherboard with the Celeron. This wasn't titled as a review. It was a look at what we should expect from Bay Trail when it becomes available. We can hope that, by then, more Jaguar-based SoCs will be available for comparison.
  • 0 Hide
    Durandul , September 17, 2013 1:29 PM
    I want a new phone.
Display more comments