AMD's A10-5750M Review, Part 1: The APU and Radeon HD 8650G Performance
by Dustin Sklavos on June 28, 2013 12:00 PM ESTConclusion: Surprisingly Potent Refresh
Without getting into the nitty gritty of the MSI GX60 that houses our review APU, AMD's A10-5750M, it seems like AMD's new APU is a net victory...with some caveats.
I imagine at the time of Richland's development, graphics performance wasn't a huge concern. With Haswell, that performance target shifts a little bit, but as long as we're not heavily CPU-bound, AMD continues to offer superior mobile graphics. Richland seems to be most aggressively focused on shoring up the primary weakness of AMD's existing architecture: the CPU itself. Piledriver was a decent improvement on Bulldozer and, ironically, a mild one on Llano, but it's nowhere near enough. Bumped up clock speeds and improved turbo help close the gap at least a little bit, but we're still dealing with 35W AMD APUs struggling to hit the same performance levels at 15-17W Intel chips.
Arguably more impressive is that this refinement was possible at all. AMD was able to take Trinity, tune the silicon ever so slightly, and extract a healthy gain in CPU performance from it. Graphics performance seems to have held flat from Trinity, but an essentially free performance boost on the CPU is welcome.
I am, however, forced to address a few elephants in the room that are getting glossed over. As consumers, we need AMD to succeed. Lack of competition is showing in a major way: desktop Haswell is a joke, Haswell's GT2 IGP is a minor improvement yet promises to be the most common one in Intel's lineup, and Intel seems to be planning to mostly coast on Haswell for two years while focusing on Atom's successor.
Yet the ugly truth about Richland and Trinity before them is that these reviews are covering the fastest models available. A8 chips lose a third of their GPU hardware across the board, and A6 chips lose another third. If you do some quick and dirty math, that means that anything below an A10 is going to be almost directly inferior to Haswell or Ivy Bridge. Graphics performance will at best be slightly above parity, while CPU performance takes a bath.
The other problem is that AMD is still targeting 35W as the mainstream TDP, but that's a target that's actually quietly shifted in the marketplace. This isn't 2008 anymore and Intel isn't charging a fat premium for its low-voltage hardware. The market that needs 35W CPUs is shrinking, being devoured at the low side by tablets and systems with ULV CPUs that still offer enough performance to handle the majority of tasks end users will need them for. And anyone who needs more performance than that can simply make the jump to a system with a quad-core Intel CPU that has more muscle. In this reviewer's opinion, 35W isn't the target, it's the halo. 15W-17W is the target, and while AMD has offerings at those TDPs, they're woefully uncompetitive.
AMD doesn't just need Kaveri. We need Kaveri. We need the Steamroller architecture update, and we need the graphics cores to switch over to GCN from VLIW4. Hopefully AMD will be able to produce a Kaveri part that has a fighting chance against Intel at 15W/17W, since Kabini and Temash are destined for smaller form factors. For now, the Richland A10-5750M is a good option and a solid offering for a refresh, but I don't think anyone can rely on it as a stopgap for too much longer.
Facebook
Twitter
RSS
82 Comments
View All Comments
monstercameron - Friday, June 28, 2013 - link
don't think it is fair comparing TDPs, we all know that they mean slightly different things for the two, intel 17W parts blow past 30+ watts from time to time.andrewaggb - Friday, June 28, 2013 - link
Ultimately the power measurement's that matter are battery life in various use cases and how much heat/active cooling is required. 35W under full gpu load is probably acceptable as long as the idle power usage is competitive with haswell. (I'm doubtful that it is though)monstercameron - Friday, June 28, 2013 - link
yeah idle is where haswell has richland and kabini beat...Khato - Friday, June 28, 2013 - link
While I doubt anyone would dispute the fact that Intel allows its processors to turbo past their specified TDP (considering that, ya know, it's kinda part of Intel's specifications) your argument would be better served by providing actual numbers instead of inflating them into the realm of fantasy. Specifically, Notebookcheck's power numbers for systems using the i7-3667U show a delta of roughly 23W between maximum idle and maximum load. Meanwhile their review of the A10-4600M shows a delta of 44W between idle and load.Regardless, going over specified TDP isn't really an issue, in fact it's typically a good thing. But it definitely means that actual power draw must be considered when comparing performance.
monstercameron - Friday, June 28, 2013 - link
really bro? http://www.notebookcheck.net/Review-Fujitsu-LifeBo...idle 9W, maxed out 40W...and that is only an i5.
Darkstone - Friday, June 28, 2013 - link
Download throttlestop. Click on the button that says 'tpl'. Expected output: power limit #1: 17W. power limit #2: 21W. Turbo time: 28s.Review the stresstest screenshot in this review:
http://www.notebookcheck.net/Review-Acer-Aspire-M3...
max
Max. package power, 19w, current package power, 16.5w.
Although the power usage can definitely exceed the TDP, it only does so for a short time. The effect on games or benchmarks taking >5 minutes is too small to make a difference. A processor with a TDP of 45w can be cooled by a heatsink rated at exactly 45w, but it might not always enter turbo mode for the full amount of time.
But that's not all, this review compares the graphics performance of an 17W tdp CPU with an 35W AMD part. The intel ULV parts are heavy power constrained. An 35W i5 part would probably be ~ 30% faster in games. Review notebookcheck, for example, starcraft 2 17W TDP ivy bridge: 31 fps. 45W part: 41 fps. Starcraft 2 does not scale above 2 cores. Check Dead Space or Hitman Absolution for more numbers that tell the same story.
Khato - Friday, June 28, 2013 - link
Bravo at finding a single example of a 17W SKU behaving abnormally in their review database. If you notice I specified a particular part which outperforms the one included in your linked review, and all reviews notebookcheck has done with that part show a delta of roughly 23W between maximum idle and maximum load.Just because there's an outlying result doesn't mean that it's the norm.
wumpus - Friday, June 28, 2013 - link
Are you seriously suggesting that Intel draws more power than TDP for long enough to soak the thermal mass of the CPU+recommend heat sink? The whole point of TDP means "thermal design power", and needs to be taken into account only for heatsink and mobile manufacturers.If you want to know what maximum current an Intel chip will draw, pull the datasheet (not the stuff made for marketing or consumers: it should be a pdf with several hundred pages. If you really want to build a motherboard; sign the NDA for the real one with the bugs included). Intel will list the requirements for the motherboard's power supply, and don't expect them to draw more than that (even then they may include a certain capacitance and frequency limits for the power supply. Intel is still free to draw however much they wish as long as the average within one period of the switching frequency is within the limits and can be supplied by the capacitance).
Breaking the specs is huge sin in this industry. Breaking what consumers think the specs are is irrelevant.
name99 - Friday, June 28, 2013 - link
This reminds me of the whining that occurred when Intel first added turbo support to its CPUs --- apparently it's "unfair" to use the laws of thermal physics to improve the performance of devices.Look, Intel has done an INCREDIBLE job of allowing its devices to run at short high speed bursts, for responsiveness, while generally using extremely low power. This is a tradeoff that meets most people's needs very well, even if it's not an appropriate tradeoff for a server chip that's going to be running at 95% utilization 24/7.
Others should be emulating Intel, not complaining that what they are doing is "unfair".
MrSpadge - Friday, June 28, 2013 - link
Excellent posts here by you, wumpus, darkstone and others!