The Desktop Kabini Review Part 1: AMD Athlon 5350 (AM1) Tested
by Ian Cutress on April 9, 2014 8:00 AM ESTThe Competition
It is no secret that AMD is attempting to fire a shot across Intel’s Bay Trail. The low power x86 desktop space is almost all AMD vs. Intel (VIA still produces x86 parts), and the socketed direction for AMD’s Kabini is a new approach in this area. The claim of low power, quad core and low cost is something that entry-level desktop integrators might find hard to ignore – in fact AMD have stated that the feedback from their Latin America integrators for an upgradeable Kabini solution is very good.
While we have not necessarily looked at Bay Trail from a desktop perspective, there are products on the market today. In the UK for example, it is easy enough to purchase an Intel Celeron J1800-based motherboard and have it shipped next-day delivery.
AMD considers the Athlon 5350/5150 parts (quad core, 2.05 GHz and 1.6 GHz) in line with Intel's Pentium J2850/J2900, and the Sempron 3850 with the J1850/J1900 - all Silvermont based SoCs. In fact, I think the 5350 vs the J1900 is a better fit:
| AMD Athlon 5350 vs. Intel Celeron J1900 | ||||
| Athlon 5350 | Celeron J1900 | |||
| CPU Architecture | Jaguar | Silvermont | ||
| CPU Cores | 4 | 4 | ||
| CPU Frequency | 2.05 GHz |
2.0 GHz 2.4 GHz Turbo |
||
| GPU Cores | 128 SPs | 4 EUs | ||
| GPU Frequency | 600 MHz | 688 MHz | ||
| Memory Interface | 1 x 64-bit | 2 x 64-bit | ||
| Memory Frequency | 1600 MHz | 1333 MHz | ||
| L2 Cache | 2 MB | 2 MB | ||
| TDP | 25 W | 10 W | ||
| Price | $55 | $82 | ||
The big issue that AMD will point out is the price of the J1900. One of AMD’s big selling points will be the price of an APU and a motherboard, which as we discussed earlier should stretch from $56 to $90 depending on the APU/motherboard. On ark.intel.com, Intel does list the tray price of the J1900 as $82, however you can find a motherboard with integrated J1900 at Newegg for $92. Now either the motherboard manufacturer is getting a good deal on the CPU below tray price (most likely), or Intel is subsiding the cost, or the tray price is incorrect. We can only speculate, but it does mean that the Athlon 5350 and J1900 square off in terms of cost.
For CPU core counts and frequency, the 5350 and J1900 are closely matched with both being quad core parts at ~2.0 GHz, although the J1900 can boost up to 2.4GHz. AMD likely holds the GPU advantage with its R3 graphics/Radeon HD 8400 compared to Intel's 4 EU HD Graphics. With the Athlon there is a higher supported memory frequency, but only a 64-bit wide memory interface. That might hamper the IGP in our testing, and provide memory limited benchmarks an easy ride on the J1900. There's a pretty substantial TDP difference between the two as well, with Intel holding the theoretical power advantage. Intel does make a 20W Silvermont based SKU, the Atom C2750, although that is an 8 core module aimed at servers and costs $171.
The Test
Our AM1 Kabini coverage will be in two parts due to time constraints. This first part of the review is to explain the ecosystem with some Athlon 5350 numbers to compare against other platforms including a couple of Bay Trail and older Intel parts. We aim to publish a second review next week with more numbers, specifically a wider range of Kabini APUs and the key battle of the 5350 against the J1900. We were unfortunate to not be able to source a J1900 in time for this launch.
Our main Kabini Test Setup is as follows:
| Test Setup | |
| CPU |
AMD Athlon 5350 Quad Core, 2.05 GHz |
| Motherboard | GIGABYTE AM1M-S2H |
| Memory | 2x4GB DDR3-1600 9-10-10 |
| SSD | SF-2281 |
| Power Supply | Antec High Current Pro 1200 |
| Graphics | Integrated |
| Graphics Drivers | 14.3 Beta |
For other platforms:
| Test Setup | |||||
| CPU | Motherboard | Platform |
Cores / Threads |
Frequency | IGP |
|
AMD A6-5200 |
ASRock IMB-A180-H |
Kabini | 4 | 2.0 GHz | HD 8400 |
|
Intel Celeron J1800 |
GIGABYTE J1800N-D2H |
Bay Trail | 2 | 2.4 GHz | HD (Ivy) |
|
Intel Atom C2750 |
ASRock C2750D4I |
Avoton | 8 | 2.4 GHz | None |
|
Intel Celeron G1101 |
MSI Big Bang Fuzion |
Nehalem | 2 | 2.3 GHz |
Not Tested no IGP outputs |
|
Intel Celeron G465 |
ASUS Maximus V Gene |
Sandy Bridge | 1 / 2 | 1.9 GHz | HD (Sandy) |
|
Intel Celeron G2030 |
ASUS Maximus V Gene |
Ivy Bridge | 2 | 3.0 GHz | HD (Ivy) |
Other results in this review were taken from our AMD Kaveri launch review.
Facebook
Twitter
RSS
126 Comments
View All Comments
jabber - Wednesday, April 9, 2014 - link
Yep slap a 120GB SSD in there and you have a nice little office system for not a lot of outlay. Doesnt matter if its SATA2, its all in the access times.meacupla - Wednesday, April 9, 2014 - link
what would be nice is high bit rate software 1080p playback, for when DXVA doesn't work.I remember my E-350 getting choppy on those.
Medallish - Wednesday, April 9, 2014 - link
Well the one I built feels pretty responsive, even with a mechanical drive. You do need to install the drivers, but once they were on there it didn't feel at all sluggish, I tried loading up a bunch of heavily advertised pages on chrome, and didn't really notice any impact on performance. I must admit I haven't tried any 1080p Youtube videos, but I will give those a go, I imagine it runs fine, I had a Quad Core "Phenom II" Mobile CPU that ran 2GHz, performance should be pretty close to this I imagine. And yeah I did a test on that running a youtube video @ 1080p and a 1080p video on VLC at the same time, now this was running a 6670m which is bound to be a lot better than this, but the CPU wasn't holding it back atleast.gandergray - Wednesday, April 9, 2014 - link
Hello Ian. Thank you for the article. In the second to last sentence of the paragraph that follows the Athlon v. Celeron table in the “Competition” section, the word “subsiding” should be “subsidizing”.JDG1980 - Wednesday, April 9, 2014 - link
The Cinebench 10 benchmark indicates that Kabini's IPC is only slightly below that of Intel's old Conroe architecture (E2180, running at the same 2GHz clock speed). For such a small die and low TDP, that's actually pretty good. Integer IPC seems to be better than Intel's Baytrail series, though floating-point lags a bit (at least if 3D Particle Motion is a good test - never heard of it before).IPC for AMD's big cores is still not much better than Conroe, and lags behind Nehalem. Steamroller was supposed to help, but didn't do much for IPC (even though it did reduce the CMT penalty). This calls into question why AMD's 'construction equipment' cores are even still being developed. If the small 'cat' cores can do as well as they do with only a dual-issue front end, and a bunch of other missing optimizations (e.g. no decoded micro-op cache), then beefing up the basic design for desktop/server use would probably beat Steamroller in IPC while having lower power usage. It wouldn't close the gap with Intel's big cores, but it would at least provide a solid foundation to build on. This would be the same thing Intel did themselves back when they ditched the unviable Netburst design in favor of one derived from the mobile Pentium-M.
mrdude - Wednesday, April 9, 2014 - link
Yea, I think many people would agree with you. I like the Jaguar architecture quite a bit, as it seems to be very well balanced. The 4-way shared L2 and integer performance seem like very solid foundations to build upon. The fact that it has AVX whereas Intel's Atoms and low end Celerons don't is also an awesome feature....but it has no turbo. AMD's turbo core is actually really advanced, dynamically adjusting clock speeds and voltages depending on the CPU or GPU load or both. Even the steaming pile of poo that was Bulldozer had a great turbo, but for some reason AMD decided not to dedicate the resources and engineering talent to fit Kabini with the same feature.
I'd love to see AMD dump the construction line and work on something similar to Jaguar that scales upward and wider more easily. It might not be a monster, but at least it offers decent perf-per-watt.
errorr - Wednesday, April 9, 2014 - link
Pretty sure the 3d particle motion test was written by Ian and I vaguely recall it being related to his PhD Thesis.lever_age - Wednesday, April 9, 2014 - link
Just a small suggestion, but for comparative performance tables like the one on the last page, could you mark benchmarks by whether a higher or lower number is better (like on the larger graphs)? I guess this could be done either in the margin by the benchmark name or by coloring the winning column.mr_tawan - Wednesday, April 9, 2014 - link
Looks a lot like P3 or Athlon board to me, especially when the cpu+cooler is installed. Feel nostalgic.errorr - Wednesday, April 9, 2014 - link
Well except the lack of North Bridge and no diarrhea brown AGP slot.