AMD Launches Mobile Kaveri APUs
by Jarred Walton on June 4, 2014 12:01 AM ESTInitial Thoughts
I really wish Kaveri could have launched on laptops earlier in the year. While Trinity was a decent solution, Richland didn't really offer much in the way of real improvements, and then seeing Kaveri on desktops first and laptops second was more than a little disappointing. The good news is that Kaveri laptops should start shipping in the near future, and overall they offer a good blend of performance and features that should help AMD be more competitive in the growing world of laptop computing.
Our initial performance results look about right, perhaps even a little lower than we'll see from final shipping hardware. There's also plenty of potential for improved performance as more applications start to leverage OpenCL, but AMD has been beating that drum for a while and it's been a relatively slow process. Yes, there are applications that can perform much faster with an APU than with an Intel CPU, but we still need more. It's fine to talk about HSA and Compute Cores, but until they make a tangible difference in every day applications they're mostly talking points. For people that truly need compute performance, I suspect they're looking at much higher performance parts than an APU.
One interesting example AMD discussed was using an optimized JPEG decoder to process images and generate thumbnails in a Windows folder. This is actually something I can see as being useful to a lot of people, and AMD was able to speed up the process by 80% compared to an Intel laptop running the stock Windows JPEG decoder. However, it's not clear how much of that performance increase is AMD being faster than Intel as opposed to the default Windows JPEG decoder simply being slow.
Kaveri's Die Up Close
There are some notable omissions in our performance data right now as well. We were only able to test the highest performance Kaveri laptop APU, the FX-7600P, and even that was essentially in "beta" form. I think the 19W FX-7500 will be potentially more interesting, and if AMD is really able to hit close to max turbo speeds most of the time it could prove a potent alternative to Intel's 15W ULV processors. Something else I'm very interested in seeing is what sort of battery life AMD is able to coax out of these APUs, as Llano and Trinity both did quite well – or at least, they did well when the laptop OEM took time to get things right. And that is perhaps the biggest obstacle AMD faces right now: getting their APUs into laptops that don't cut corners in all the wrong places.
As I noted earlier, storage performance (i.e. having a pure SSD solution for the OS and primary applications) is now far more critical for most use cases than the choice of CPU. However, we can't even get $1000+ laptops to universally switch to SSDs, and it's going to be a long row to hoe getting anything priced under $800 to include one. You can just picture the bean counters: "Why are we using a $100 SSD that only holds 256GB instead of a $50 HDD that holds 1TB!? That's a terrible component choice!" On a similar note, getting a laptop with a good keyboard, trackpad, and screen is more difficult than it needs to be even on midrange laptops, and I've seen many an AMD-equipped laptop fall flat on its face thanks to penny pinching and cut corners in these areas. Finally, it's important to note that all batteries are not created equal; while it would be nice if a 56Wh battery was always a 56Wh battery, I know from experience that there's still a wide range of quality, including the ability to store a charge for more than a few weeks without going dead.
But these things cost money, and when you're saving $50-$100 by using an AMD APU instead of an Intel CPU, the mindset often becomes, "Where else can we save money?" The result is a race to the bottom, and if laptop OEMs aren't careful they'll lose more and more market share to alternative devices. (There's a thought: someone make a Kaveri-based Chromebook. That could be interesting!)
Bottom line: AMD's Kaveri APUs show plenty of promise. Now I want someone to build a nice AMD-equipped laptop for under $800 (with or without a ULV APU). Take the core elements of a good Ultrabook, swap out the Intel CPU/platform for an AMD Kaveri APU/platform, and keep the SSD, form factor, and screen. If one of the major OEMs can deliver that sort of product at a lower price than the Intel equivalent, it would be an easy recommendation.
Facebook
Twitter
RSS
125 Comments
View All Comments
CoronaL - Wednesday, June 4, 2014 - link
lol me toomax1001 - Wednesday, June 4, 2014 - link
I would love to see a nicely spec ultrabook with this APU and $800-$1k price point that can do decent gaming.AnnonymousCoward - Wednesday, June 4, 2014 - link
It'd be fun to throw a GTX 760 in the mix, just to see where we're at.CoronaL - Wednesday, June 4, 2014 - link
Wonder if they will pair that up with a cheap 250x mobile version for some X-fire gaming on laptop. I bet that would beef up the graphics a fair bit. IMO the cpu part is pretty respectable trading blows with the i7 and i5 for the most part, which AMD usually gets trounced in.azazel1024 - Wednesday, June 4, 2014 - link
Well it does look a lot better than Richland and price might be a big driver in making these interesting (I see no prices?), but 19w Kaveri versus 15w Haswell ULT...the 15w Haswell ULT, depending on the turbo performance of the 19w Kaveri part looks to run roughly as fast to a very sizeable 20-30% lead in CPU performance and with the GPU cut down to roughly half performance between core and clock reduction...the Haswell ULT is likely to be on par graphically +/-10%. In a lower power consumption package...and if the Kaveri has turboing issues or the GPU is thermally constrained in this package it could be a much more significant lead.The 15w Kaveri doesn't look like it would be on the performance map at all (<<<50% of the performance of Haswell ULT). The standard voltage parts actually look the most interesting, especially if the price is moderate. That would probably allow you to make a decent performing machine (70-90% of an Intel's CPU performance) with a very nice iGPU for a rather low price point (assuming the FX-7600p is very price competitive to the Intel Haswell SV dual core parts).
azazel1024 - Wednesday, June 4, 2014 - link
I guess I missed something with the Intel chips in regard to the TDP. My experience is vastly different. Most Intel chips, both desktop and mobile, don't seem to come close to hitting max TDP under full CPU load. Especially in the desktop space I see something like my i5-3570 with a TDP of 77w is hitting around a 35w delta between idle and full load based on wall plug data, considering losses from the power supply and assuming a fairly low (CPU) idle number, thats only in the area of 30-40w total power consumption. That isn't simply under load, the processor is clocked up to 4.2GHz single core and 4GHz all 4 cores turbo. That isn't a max burn situation where every single itty bitty capacitor and transistor is loaded like Intel does in their TDP tests, but that is under 100% sustained CPU load across all 4 cores.From what I have seen with Ivy Bridge testing (which ain't Haswell I'll admit) a fully loaded i5-3317u seems to only use in the area of 8-10w with both cores fully loaded max turbos 100% CPU load. Its the GPU that uses a huge whack of power, >12w under max load and turbos.
I'd assume Haswell is pretty close there, at least with the CPU, since the turbo core speed is the same, same lithography, very similar architecture. So I doubt a ULT Haswell is using more than 10w under max CPU load and turbos. Its the GPU that is going to be the power hog.
No idea what AMD is capable of on these, but we know they are using a less energy efficient process, so I'd assume/guess that their CPU is probably below the cap under max CPU load, but it might be much closer, maybe in the 12-15w range under max turbo, meaning GPU load is going to cause the CPU to scale pretty far back, even on the 19w chips.
worm - Wednesday, June 4, 2014 - link
It seems like any benchmarks of the Ax-7xxxP should be against an ix-4xxxM, not MQ, like over at Tom's, and the 7xxx, should be against the ix-4xxxU, at approximately the closest price point. That leaves plenty to choose from, in laptops in the market. Hopefully we can get that data so a real comparison can be made. I hope we are just waiting on OEMs to release their Kaveri laptops, in both 19w, and 35w forms, to make it worthwhile?JarredWalton - Wednesday, June 4, 2014 - link
I am actually testing the first dual-core standard voltage Haswell laptop right now, so I'll have that data added to Bench in the next week.meacupla - Wednesday, June 4, 2014 - link
still waiting on A6-7600K.I know it's a desktop CPU, but c'mon, it's been four months since Febuary and I don't even see it in stock at newegg.
MLSCrow - Wednesday, June 4, 2014 - link
Why are they comparing Kaveri to the 15W ULV i7? Simple, because it's a more fair comparison for multiple reasons:A) That i7 is a dual core with hyperthreading (4 threads). Kaveri is a dual module with modular multithreading (4 threads). An AMD module is what you compare to a single Intel Core with hyperthreading. That is the fair comparison. It wouldn't be fair to compare a dual core vs a quad core now would it?
B) Although the Intel chip is still more expensive than the Kaveri, it is much more closely priced than the quad core version. Price ranges should always be taken into consideration when comparing offerings of like-capabilities from different manufacturers.