AMD Launches The A10-7800, The 65 Watt Kaveri

[phoronix]

Phoronix: AMD Launches The A10-7800, The 65 Watt Kaveri

AMD this morning has officially announced the A10-7800, the 65 Watt version of their "Kaveri" APU that's a follow-up launch to the A10-7850K that launched earlier in the year...

http://www.phoronix.com/vr.php?view=MTc1MzE

[jakubo]

1. Is Kaveri open source ready by now?
2. HSA?
3. can a custom/optimised built kernel exceed the performance of win?

[Ziple]

1. Is Kaveri open source ready by now?
2. HSA?
3. can a custom/optimised built kernel exceed the performance of win?

1. Yes, since a long time
2. patches to support HSA have been recently proposed by AMD, they are still waiting to be integrated in the linux kernel
3. ? Don't understand what you really want to know

[oleid]

Michael, when benchmarking the CPU, please throw - mtune=generic into the ring, so that we see how it performs on stock distributions.

[jakubo]

1. Yes, since a long time
2. patches to support HSA have been recently proposed by AMD, they are still waiting to be integrated in the linux kernel
3. ? Don't understand what you really want to know

@3. if linux can be much faster on this rather highly specialised piece of hardware.

[jakubo]

@3. if linux can be much faster on this rather highly specialised piece of hardware.

i mean especially on opencl, and HSA tasks. Or when possible general everyday benchmarks when every kernel or compile tweak is activated.

[Ericg]

@3. if linux can be much faster on this rather highly specialised piece of hardware.

I wouldn't really call this piece of hardware highly specialized, its just an APU like any before it.

[jakubo]

I wouldn't really call this piece of hardware highly specialized, its just an APU like any before it.

generally speaking it has quite somecompute power via its GPU which seems to lack bandwidth and a low performing CPU. Maximum performance is not reached for simple FP operations is it? but for some graphic or OpenCL/HSA stuff. Thats what id call it specialized. At least for the software that exists to this point and is unable to get a hold of the power it could offer. Youd need specially written software. thats why i call it specialised.
(i wouldnt if some Gallium state tracker was able to make its graphic's part's CU's power available for completely general purpose so that (almost) every program that uses the cpu could run on the GPU instead. Or maybe someone will make a framework for such optimisation someday)

long story short: if you wanted a generally good system youd go with an Intel CPU and a discrete Nvidia graphics card (on linux)
AMD is, as a matter of fact, (in) a niche and for lovers
... and budged if you do not rely on fast ram... whats a cheap CPU for when you need f***ing expensive ram withought still exceeding intel

And yes i am very much interested in AMD to succeed and bring some new stuff. They need to really get some kind of feature and make it common and i think HSA is a good approach but with the software lacking so much behind it very much reminds me of the introducion of 64bits when it took years to be somewhat fully used. There are so many people out there craving for some new toys especially in the linux world. They could really be the ones giving hardware to universities for some masters thesis. given they can or do (afford to) open up documentation...
i mean look at raspberry pi. They could do the same if not better. or if you want look at tesla cars. AMD cannot win on a closed market (or maybe with the before mentioned inspiration and a HUGE(!!!) investition as a final trump card... which will not happen due to investors). and the longer they wait the worse it gets. i mean if it goes on like this they may have to ask Intel to manufacture chips for them when GF and TSMC cannot fill their needs...

[rikkinho]

hm

i need to say the single core performance is a mess, the gpu os not bad, but the cpu....

[Ziple]

generally speaking it has quite somecompute power via its GPU which seems to lack bandwidth and a low performing CPU. Maximum performance is not reached for simple FP operations is it? but for some graphic or OpenCL/HSA stuff. Thats what id call it specialized. At least for the software that exists to this point and is unable to get a hold of the power it could offer. Youd need specially written software. thats why i call it specialised.
(i wouldnt if some Gallium state tracker was able to make its graphic's part's CU's power available for completely general purpose so that (almost) every program that uses the cpu could run on the GPU instead. Or maybe someone will make a framework for such optimisation someday)

long story short: if you wanted a generally good system youd go with an Intel CPU and a discrete Nvidia graphics card (on linux)
AMD is, as a matter of fact, (in) a niche and for lovers
... and budged if you do not rely on fast ram... whats a cheap CPU for when you need f***ing expensive ram withought still exceeding intel

And yes i am very much interested in AMD to succeed and bring some new stuff. They need to really get some kind of feature and make it common and i think HSA is a good approach but with the software lacking so much behind it very much reminds me of the introducion of 64bits when it took years to be somewhat fully used. There are so many people out there craving for some new toys especially in the linux world. They could really be the ones giving hardware to universities for some masters thesis. given they can or do (afford to) open up documentation...
i mean look at raspberry pi. They could do the same if not better. or if you want look at tesla cars. AMD cannot win on a closed market (or maybe with the before mentioned inspiration and a HUGE(!!!) investition as a final trump card... which will not happen due to investors). and the longer they wait the worse it gets. i mean if it goes on like this they may have to ask Intel to manufacture chips for them when GF and TSMC cannot fill their needs...

I don't really know HSA is going to be used in real world so I can't tell you if it is going to become a key feature everyone will want to have.
On the paper it is really interesting though, and lots of applications could benefit from it I guess: from video decoding to scientific computing I think.

I would not be so negative about the usefulness of recent AMD processors: besides from being really damn cheap, they perform quite well with heavy threaded applications (compared to their single core performance) for their price. They also include a fully featured GPU that can help for computing tasks.
I am a scientist doing lots of computations (I develop the software I use), and for my needs AMD products are more than good enough. If I need serious computing power, I use the computer grid in my facility... It depends on the needs of each one.

As I see it: Intel has been really good at marketing and lots of people just know Intel, so they buy Intel; The ones who knows AMD buy Intel procs because they think that it will run faster. Lots of people who use their computer only for emails and browsing the internet would not see the difference between an AMD proc and an Intel one...