On the back of AMD’s Tech Day at CES 2014, all of which was under NDA until the launch of Kaveri, AMD have supplied us with some information that we can talk about today.  For those not following the AMD roadmap, Kaveri is the natural progression of the AMD A-Series APU line, from Llano, Trinity to Richland and now Kaveri.  At the heart of the AMD APU design is the combination of CPU cores (‘Bulldozer’, ‘Steamroller’) and a large dollop of GPU cores for on-chip graphics prowess.

Kaveri is that next iteration in line which uses an updated FM2+ socket from Richland and the architecture is updated for Q1 2014.  AMD are attacking with Kaveri on four fronts:

Redesigned Compute Cores* (Compute = CPU + GPU)

Kaveri uses an enhanced version of the Richland CPU core, codename Steamroller.  As with every new CPU generation or architecture update, the main goal is better performance and lower power – preferably both.  AMD is quoting a 20% better x86 IPC with Kaveri compared to Richland when put clock to clock.  For the purposes of this information release, we were provided with several AMD benchmarking results to share:

These results border pretty much on the synthetic – AMD did not give any real world examples today but numbers will come through in time.  AMD is set to release two CPUs on January 14th (date provided in our pre-release slide deck), namely the A10-7700K and the A10-7850K.  Some of the specifications were also provided:

AMD APUs
  Richland
A8-6600K
Richland
A10-6800K
Kaveri
A10-7700K
Kaveri
A10-7850K
Release June 4 '13 June 4 '13 Jan 14th '14 Jan 14th '14
Frequency 3900 MHz 4100 MHz ? 3700 MHz
Turbo 4200 MHz 4400 MHz ? ?
DRAM DDR3-1866 DDR3-2133 DDR3-2133 DDR3-2133
Microarhitecture Piledriver Piledriver Steamroller Steamroller
Manufacturing Process 32nm 32nm ? ?
Modules 2 2 ? 2
Threads 4 4 ? 4
Socket FM2 FM2 FM2+ FM2+
L1 Cache 2 x 64 KB I$
4 x 16 KB D$
2 x 64 KB I$
4 x 16 KB D$
? ?
L2 Cache 2 x 2 MB 2 x 2 MB ? ?
Integrated GPU HD 8570D HD 8670D R7 R7
IGP Cores 256 384 ? 512
IGP Architecture Cayman Cayman GCN GCN
IGP Frequency 844 844 ? 720
Power 100W 100W ? 95W

All the values marked ‘?’ have not been confirmed at this point, although it is interesting to see that the CPU MHz has decreased from Richland.  A lot of the APU die goes to that integrated GPU, which as we can see above becomes fully GCN, rather than the Cayman derived Richland APUs.  This comes with a core bump as well, seeing 512 GPU cores on the high end module – this equates to 8 CUs on die and what AMD calls ’12 Compute Cores’ overall.  These GCN cores are primed and AMD Mantle ready, suggesting that performance gains could be had directly from Mantle enabled titles. 

Described in AMD’s own words: ‘A compute core is an HSA-enabled hardware block that is programmable (CPU, GPU or other processing element), capable of running at least one process in its own context and virtual memory space, independently from other cores. A GPU Core is a GCN-based hardware block containing a dedicated scheduler that feeds four 16-wide SIMD vector processors, a scalar processor, local data registers and data share memory, a branch & message processor, 16 texture fetch or load/store units, four texture filter units, and a texture cache. A GPU Core can independently execute work-groups consisting of 64 work items in parallel.’  This suggests that if we were to run asynchronous kernels on the AMD APU, we could technically run twelve on the high end APU, given that each Compute Core is capable of running at least one process in its own context and virtual memory space independent of the others.

The reason why AMD calls them Compute Cores is based on their second of their four pronged attack: hUMA.

HSA, hUMA, and all that jazz

AMD went for the heterogeneous system architecture early on to exploit the fact that many compute intensive tasks can be offloaded to parts of the CPU that are designed to run them faster or at low power.  By combining CPU and GPU on a single die, the system should be able to shift work around to complete the process quicker.  When this was first envisaged, AMD had two issues: lack of software out in the public domain to take advantage (as is any new computing paradigm) and restrictive OS support.  Now that Windows 8 is built to allow HSA to take advantage of this, all that leaves is the programming.  However AMD have gone one step further with hUMA, and giving the system access to all the memory, all of the time, from any location:

Now that Kaveri offers a proper HSA stack, and can call upon 12 compute cores to do work, applications that are designed (or have code paths) to take advantage of this should emerge.  One such example that AMD are willing to share today is stock calculation using LibreOffice's Calc application – calculating the BETA (return) of 21 fake stocks and plotting 100 points on a graph of each stock.  With HSA acceleration on, the system performed the task in 0.12 seconds, compared to 0.99 seconds when turned off.

Prong 3: Gaming Technologies

In a year where new gaming technologies are at the forefront of design, along with gaming power, AMD are tackling the issue on one front with Kaveri.  By giving it a GCN graphics backbone, features from the main GPU line can fully integrate (with HSA) into the APU.  As we have seen in previous AMD releases and talks, this means several things:

  • Mantle
  • AMD TrueAudio
  • PCIe Gen 3

AMD is wanting to revolutionize the way that games are played and shown with Mantle – it is a small shame that the Mantle release was delayed and that AMD did not provide any numbers to share with us today.  The results should find their way online after release however.

Prong 4: Power Optimisations

With Richland we had CPUs in the range of 65W to 100W, and using the architecture in the FX range produced CPUs up to 220W.  Techincally we had 45W Richland APUs launch, but to date I have not seen one for sale.  However this time around, AMD are focusing a slightly lower power segment – 45W to 95W.  Chances are the top end APUs (A10-7850K) will be 95W, suggesting that we have a combination of a 20% IPC improvement, 400 MHz decrease but a 5% TDP decrease for the high end chip.  Bundle in some HSA and let’s get this thing on the road.

Release Date

AMD have given us the release date for the APUs: January 14th will see the launch of the A10-7850K and the A10-7700K.  Certain system builders should be offering pre-built systems based on these APUs from today as well.

Comments Locked

133 Comments

View All Comments

  • herrington - Tuesday, January 7, 2014 - link

    because those loser got nothing to do in their mom basement, so the only thing they can do is trolling all day
  • jabber - Tuesday, January 7, 2014 - link

    Oh I agree. If this was 20 years ago I could understand when you had the poor AMD/Cyrix type CPUs.

    But there really isn't a bad current CPU out there. All of them will get most people through the day.

    Plus as AMD demoed a couple of years ago, even tech fanboys can struggle to tell the difference between a top end AMD and Intel CPU in real world usage.
  • lmcd - Tuesday, January 7, 2014 - link

    Anandtech has demoed the difference, particularly in laptops -- an AMD A10m Richland + Radeon HD 7970m lost to an Intel i7 mobile + Radeon HD 7970m by a significant margin.
  • Notmyusualid - Wednesday, January 8, 2014 - link

    Yes, I saw that article when it came out, shook my head, and issued AMD a 'mental report card' of must try harder, and I made reference to the mobile parts and their lower performance in my comment.

    However, my friend, as I also mentioned, doesn't play games, I do, hence my i7.

    I was merely stating, like another poster later did, that there is not a bad DESKTOP CPU out there. They all pull their weight, and most people can get by with the modern performance they have on offer.

    Hence the stagnation in the Desktop industry, many don't feel a need to upgrade so regularly anymore, having 'enough' performance for their everyday needs, some refused to accept Win 8 (no help either), whilst others moved over to tablets (that I cannot stand).

    Pervioulsy this well-heeled friend of mine, upgraded regularly, handing down his 'old' (lol) motherboard & parts to me as he saw fit. It was a boon for me at the time really, and has stopped since this 6-core AMD came into his life.

    @jabber, have a link to that demo you spoke of?
  • mikato - Wednesday, January 8, 2014 - link

    Here is my example of what you said. I just "upgraded" my wife's gaming computer. She's been gaming fine on a Core 2 Duo for a few years, and I recently put in a better Core 2 Duo (E8500) from ebay, a new video card (GTX 760), and a little more DDR2 memory and she's off to play Call of Duty Ghosts :) I think it will last at least another year that way. The CPU purchase was $30 and put the system over the system requirement there. The memory I scrounged and was gifted to from work. And the video card will obviously be carried over to a new build whenever that happens. So the way I think of it, upgrade cost for this end of the road system was just $30 and that's worth it to me to stave off a new build, new purchases, full reinstall of OS and games etc for a little while longer. Oh yeah, I'll sell that old CPU on ebay as well so net is probably even less. Obviously this is not everybody's situation but it shows us playing a brand new FPS game on pretty old hardware which likely couldn't have been done in the past. Rest assured, when the new build is done eventually it will be screaming fast. I wonder if AMD will have FX CPUs by then.
  • silverblue - Wednesday, January 8, 2014 - link

    That was on an MSI GX70. Both generations of said laptop appear to perform very badly, but no reason was given for it. It could be the CPU, but something doesn't look right.
  • YuLeven - Tuesday, January 7, 2014 - link

    They aren't "that bad". But your friend being able to do something with a particular CPU isn't a compelling reason to make it 'good', specially compared to it's competitors.

    It isn't about being slow or not. Why would any one come to a hardware specialized site and go 'If I'm happy with this computer nothing really matters'? You're clearly missing the point in here.
  • Mystiq - Tuesday, January 7, 2014 - link

    It took me a little while to figure this one out, and I hope it comes true, but I have serious doubts.

    AMD's goal looks to be like this:

    1) Release an APU with a powerful GPU and a good-enough CPU
    2) Develop an architecture that takes advantage of AMD's GPUs and leverages them like a CPU
    3) Develop an API that is light on the CPU to make up for AMD's historically-weak (FPU) CPUs
    4) Lean on said architecture and the API to make the weak CPU irrelevant because the GPU side of the APU is better at the relevant tasks anyway
    5) Profit

    AMD is trying to upend both Nvidia and Intel by trying to make up for their weak CPUs by say "fuck it" and treating the GPU as a powerful vector-coprocessor, much better than AVX. If it works, and games take advantage of both Mantle and HUMA (you have both a Kaveri APU and maybe a Radeon R7 card), I shutter to think of the framerate.

    Of course, we need to get rid of DDR3 already...
  • Mystiq - Tuesday, January 7, 2014 - link

    I'd just like to make it clear that the primary goal of Mantle is probably to take the CPU out of the equation when it comes to graphics performance, making AMD's APUs just as competitive as the Core i7 -- because the CPU has been made irrelevant because of Mantle. You can argue there will come a point again where we're putting out ridiculous photo-realistic graphics and the CPU again becomes a bottleneck but maybe they've thought of that, too. In the mean time, using HUMA can also let AMD slap both Intel and Nvidia. You need to code a program to take advantage of MMX/SSE/AVX/whateverIntelComesUpWithNext (or at least change compilers) so assuming HUMA catches on (a very difficult way forward), this could get interesting.
  • extide - Tuesday, January 7, 2014 - link

    You need to code a program to use HUMA too... It's not a free lunch.

Log in

Don't have an account? Sign up now