Bay Trail On The Desktop: Celeron J1750 Gets Benchmarked

Status
Not open for further replies.

DjEaZy

Distinguished
Apr 3, 2008
1,161
0
19,280
... 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....



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).
 

runswindows95

Distinguished
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.
 

ojas

Distinguished
Feb 25, 2011
2,924
0
20,810
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.
 


Not according to Tom's ...

ABBYY.png

finereader.png


acrobat.png

acrobat.png


WinZIP.png

winzip.png


handbrake.png

handbrake.png


3dmark.png

3dmark-11.png


power-gaming.png

power.png


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).


 
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.
 

Ilander

Distinguished
Jul 22, 2007
173
0
18,710
...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.
 

cangelini

Contributing Editor
Editor
Jul 4, 2008
1,878
9
19,795


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.
 

cangelini

Contributing Editor
Editor
Jul 4, 2008
1,878
9
19,795


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.
 

MANOFKRYPTONAK

Distinguished
Feb 1, 2012
952
0
19,060
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 $
 

ta152h

Distinguished
Apr 1, 2009
1,207
2
19,285
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.
 

ojas

Distinguished
Feb 25, 2011
2,924
0
20,810
@Wisecracker: You're almost correct, and i say almost because you're comparing a quad-Jaguar part to a dual-Silvermont part.

[strike]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.[/strike]
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:
kraken.gif

7zip-comp.gif

7zip-decomp.gif

x264.gif

handbrake.gif

cinebench-single.gif

cinebench-multi.gif

citadel.gif

icestorm.gif

icestorm-unlimited.gif


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.
 

cangelini

Contributing Editor
Editor
Jul 4, 2008
1,878
9
19,795


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.
 

rootheday

Distinguished
Feb 6, 2009
33
0
18,530
860W power supply? seriously? Chris, if you are going to be doing ANY power comparisons between platforms, the power supply needs to be sized appropriately. Otherwise the power numbers are meaningless in terms of extrapolating to real world usage power burn and perf/watt calculations.
 

SteelCity1981

Distinguished
Sep 16, 2010
1,129
0
19,310
stickman the core 2 quad doesn't have 2mb of l2 cache now does it and yes it does mean something when you are using 4 cores in threaded programs. toms hardware have had countless of benchmarks on that just look at the Athlon x4 minus l3 cache on heavy threaded programs vs the phnoms ii x4 that have l3 cache. there is a big diff with programs that utilize large amounts of cache.
 

hector2

Distinguished
Mar 18, 2011
61
0
18,630
Just like the OEMs did for Atom-based netbooks when they first came out, they will markup anything Intel produces as much as they think they can get away with by pretending they're as powerful as full feature laptops in a smaller form factor. A lot of people bought into that and were disappointed in the slower netbook experience.
 
Status
Not open for further replies.