Slashdot Mirror
AMD Launches New Richland APUs For the Desktop, Speeds Up To 4.4GHz
MojoKid writes "AMD recently unveiled a handful of mobile Elite A-Series APUs, formerly codenamed Richland. Those products built upon the company's existing Trinity-based products but offered additional power and frequency optimizations designed to enhance overall performance and increase battery life. Today AMD is launching a handful of new Richland APUs for desktops and small form factor PCs. The additional power and thermal headroom afforded by desktop form factors has allowed AMD to crank things up a few notches further on both the CPU and GPU sides. The highest-end parts feature quad-CPU cores with 384 Radeon cores and 4MB of total cache. The top end APUs have GPU cores clocked at 844MHz (a 44MHz increase over Trinity) with CPU core boost clocks that top out at lofty 4.4GHz. In addition, AMD's top-end part, the A10-6800K, has been validated for use with DDR3-2133MHz memory. The rest of the APUs max out at with a 1866MHz DDR memory interface."
As with the last few APUs, the conclusion is that the new A10 chips beat Intel's Haswell graphics solidly, but lag a bit in CPU performance and power consumption.
Accelerated processing unit. Basically a CPU with integrated graphics. Both AMD and Intel's recent CPUs have been APUs.
P.S. --> the score in question from my previous post was for Cinebench 11.5, but there are many many others like it. And don't think that OpenCL holds any miracles for Trinity either, the 4600 is actually a better OpenCL part than it is a GPU.
AntiFA: An abbreviation for Anti First Amendment.
http://en.wikipedia.org/wiki/AMD_Accelerated_Processing_Unit
APU is the only unusual acronym in the summary. It refers to a chip with both the CPU and graphics processor on the same die. It was previously called Fusion, but trademarks got in the way.
Intel can get away with solder in components because they change the socket type so often that people are unlikely to be able to upgrade the processor anyways. AMD OTOH, has a tradition of not forcing you to do that every single time you upgrade.
Personally, I refuse to buy Intel parts, and quite frankly, the way I use my computer, I don't need the overpriced solutions that Intel is pushing.
Huh? The front-side bus hasn't existed in years. AMD abolished it way back in 2003 when they moved the Athlon 64's memory controller on-die. Intel did the same thing with Nehalem in 2008.
Perhaps you just meant that there isn't enough memory bandwidth to use the GPU to its full potential with games? The good news is that AMD's upcoming Kaveri will have GDDR5 support, with a homogenous memory architecture similar to the new consoles.
P.S. --> the score in question from my previous post was for Cinebench 11.5, but there are many many others like it. And don't think that OpenCL holds any miracles for Trinity either, the 4600 is actually a better OpenCL part than it is a GPU.
Really? Because the one OpenCL benchmark I can find in TFA pegs the new chips at 2.5 times faster than the 4600 that comes with the i5-4670k. I wouldn't consider a part that is less than half as fast to be "better." Maybe that's just me? Could be. Also, I wouldn't say "at best" 20% faster when several benchmarks peg it at 30% or more. The Enemy Territory: Quake Wars high-res benchmark, in particular, is... hilariously one sided (and since most people are going to be playing at high-res settings, it's a benchmark that actually matters). Actually, all the high-res gaming tests are, with the new chips often coming in close to twice the Haswell chips. In fact, the Cinebench 11.5 tests peg the Richland at 60% faster than the i5-4670k, so I'm not sure where the hell you got any of your numbers from.
"None can love freedom heartily, but good men; the rest love not freedom, but license." --John Milton
Richland's GPU is at best about 20% faster than the intentionally-midrange HD-4600 GPU in Haswell.
Yes, but what OpenGL features does the Haswell APU have compared to the full GL 4.3 found in the AMD version? How good are the Intel drivers? How many textures can I bind at once? What anti-aliasing modes does it support? What are the max number of shader varying/uniform attribs? How many shader instructions can I fit within my shaders? Back in 1999, comparing raw polygon speed may have meant something, but these days it's not really as interesting as the rest of the details....
Here is your Radeon HD7850: http://www.gpureview.com/Radeon-HD-7850-card-678.html
It has 1024 Shader Processors ("Radeon Cores" in the summary), and (stock) is clocked at 860MHz. The 8670D included in this new APU has 384 Shader Processors, and is clocked at 844MHz. So about 2/5ths of the computing power; presuming all other factors are equal.
So while for high-end gaming, it won't quite cut it (Turning on most of the shiny and enabling it across 3 monitors with Eyefinity would make it beg) - it should be plenty powerful for light/medium gaming on a single monitor, or any light/moderate duties across multiple monitors with Eyefinity.
Intel provides rather extensive technical documentation of all their products. http://www.intel.com/content/www/us/en/processors/core/CoreTechnicalResources.html [intel.com] is the page with basic datasheets (basic in this case meaning a couple hundred pages, their more detailed ones are a thousand). If you truly are as interested in the technical details as you pretend, then go look them up.
I've had a look through, but apart from saying "it has 20 execution units", it doesn't really mention any specific figures (for the actually useful information). It does however state that it's OpenGL4.0, which is a little disappointing (a step up from 3.2, but it's still lagging behind AMD & NVidia).
However if you are just throwing out technical shit in an attempt to deflect the argument then knock it off. Particularly since much of what you are asking for are the kind of the things that would be of concern for high end dedicated GPUs for particular applications, not for an integrated controller for general use.
Well, I'm a graphics engineer in the games industry by trade, so I guess you could say I have a passing interest. The things I am asking for, are things that can help improve the performance of the products I work on. Now you might not find this stuff particularly interesting, however I do. So as a very simple example, I have an order-independent-transparency pass to handle pixel perfect transparency. On the current integrated AMD GPU, I can basically pick between any number of algorithms to achieve this (weighted average, dual depth peeling, etc, etc). Now, which one I choose, is going to be largely affected by what GPU resources I need to use for other things, and this includes: memory, the max number of shader attribs, the max number of bindable texture units, etc; but in general, I have resources to spare, so I am free to pick and choose.
The problem with Intel APUs in the past, is that whilst the last generation may have implemented OpenGL 3.2 to the letter, the max attrib counts and shader instructions were significantly lower than the AMD/Nvidia equivalents. This means you typically have to insert an Intel only codepath, where you will either just rip out the nice stuff, or you'll end up using a much slower multipass technique. As a result, making frame-rate comparisons in any game is most likely to be meaningless (since there is a good chance they are running a simplified codepath for intel).
It's all well and good, and matters for certain markets and applications, but those markets are generally not the ones using an integrated GPU. Most people just care how fast it runs their stuff.
Yes, and No. It's very true that most people just want their stuff to run quickly. However, to say that the legions of people out there running low powered ultrabooks and cheap generic laptops don't care about this stuff, is complete and total bullshit. You might imagine that all gamers have £3000 desktop rigs with all the trimmings, but the reality is infact very different. If I can spend a few months optimising the graphics routines to run a game smoothly at 720p on an Intel APU, then the market sector into which we can sell our product, has more or less tripled. Even if you don't go to the effort, you will probably be forced into making those optimisations anyway. Honestly, you would be surprised at just how many people ignore the minimum system requirements on a game, and simply assume their "i3 Dell laptop is brand new, so it should play the latest games". What are you going to do? Refund half of your sales? Or fix it? If you see sense, you'll fix it, and then most of your users will have the luxury of being able to ask how quickly it runs....
If you feel the 7850 is needed then these will be too slow for you.
The GPU in the A10-5800 (the one currently on the shelves) is fairly accurately labeled a 6550d and requires settings to be turned down to Low@720p/1366x768 to get acceptable performance in a game like Battlefield3. The new APU is only incrementally more powerful and faster.
What these "APU" chips (which in my mind includes Haswell Chips) are obsoleting are the lowend budget cards with 64bitGDDR5 and 128bitDDR3 that get put in a lot of office desktops.
"The Adobe Updater must update itself before it can check for updates. Would you like to update the Adobe Updater now?"
And after the APU is done processing, it says in a catchy Middle Eastern accent, "THANK YOU, COME AGAIN!"
India is not in the middle east.
Calling someone a "hater" only means you can not rationally rebut their argument.