What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

Richland, Kaveri, Kabini & Temash; AMD’s 2013 APU Lineup Examined


HardwareCanuck Review Editor
Staff member
Feb 26, 2007
Some pundits have called 2012 the Year of Transition as tech companies came to grips with a rapidly expanding mobile market and many struggled to find their focus. For AMD, 2012 was truly a time of ups and downs. Their Trinity APUs were released to widespread acclaim but ultimately fell short in the OEM market with few design wins. Ironically, the Trinity-based notebooks we did come across were quite impressive. Bulldozer’s enhanced successor (called Piledriver) burst onto the scene in the guise of Vishera processors which offered some great performance numbers relative to their low asking price.

On the mobile side, Brazos 2.0 and Hondo both offered strong platforms but their success was also tempered by limited acceptance among ultra-portable notebook and tablet manufacturers. AMD’s financial and product struggles were the topic of many an editorial and no small amount of erroneous predictions of doom but judging from what we have seen, 2013 may be a turning point for this company.


At this year’s CES, AMD presented their plans for the coming year. There will be refreshes aplenty while additional focus is being put upon efficient low voltage components which are used within slim and light notebooks (read: Ultrabook) and for tablets. Some additional product categories will also be making it into the limelight, allowing AMD to become more competitive against the likes of Intel and NVIDIA’s low power solutions. There was no mention of upcoming processors for smartphones but with that segment already flooded with Intel, Samsung, Qualcomm and NVIDIA solutions, AMD likely feels that it is best to concentrate upon their core x86 technologies for the time being.


Another interesting addition which hasn’t been discussed at length is AMD’s move away from their “Vision” branding. In its place is a more structured approach with simple A-series designations for APUs (both desktop and mobile / low power) and FX branding for unlocked CPUs. The “E2” branding from the Brazos ultrathin category seems to have been morphed into A6 Quad Core and A4 Quad Core banners while the Z-series is now becoming A4 Elite Mobility and A6 Elite Mobility. For those of you wondering, the “Elite” moniker denotes the inclusion of AMD’s new Elite Experience feature set which is discussed below.

AMD has also included a novel approach for the visual representation of additional features. The A10 and A8 Elite Quad Core APUs can have a Dual Graphics logo added if an OEM includes the necessary discrete GPU while systems using the Elite Mobility APUs can utilize the optional Quad Core designation should the higher end SKU be used.


Kicking things off is an overview of AMD’s 2013 platforms which –on the desktop and notebook sides at least- are acting as bridge between the APU products of today and the Heterogeneous Systems Architecture which will be introduced closer to 2014. Trinity as we know it will stick around for the time being but it will be gradually replaced by a slightly revised version code named Richland. This minor step forward precedes Kaveri which is the culmination of AMD’s HSA goals into a single chip design.

Kaveri will presumably use the Steamroller architecture for its x86 cores while incorporating GCN cores for its visual processing needs. A release timeframe of mid 2013 puts it up against Intel’s 22nm Haswell so AMD has a lot riding on this part of their roadmap. For those wondering, it looks like AMD's FM2 socket will stick around for the time being with an FM2+ refresh possibly rolling out in time for Kaveri. Since all FM2 APUs natively support PCI-E 3.0 (the ability hasn't been enabled in Trinity and presumably Richland), there's a good possibility that FM2+ APUs could include this standard.

The real steps forward for AMD in 2013 will come from their mid and entry level product stacks where Brazos 2.0 and Hondo will make way for Kabini and Temash respectively. This may not see like a major transition but just the move from 40nm to 28nm will surely bring about much-needed improvements in power efficiency and manufacturing viability. Considering the massive expansion seen within the tablet and Ultrabook segments, these two new architectures will likely play a pivotal role in AMD’s success or failure this year.

Ironically, there was no mention of non-APU processors so AMD’s plan for a 28nm Vishera successor remains in a state of limbo. If last year was any indication, AMD will likely roll out the new Steamroller core design to APUs like Kaveri and then follow up with the FX-series parts in short order.

Sales of Radeon-branded graphics cards hit record levels last year and AMD intends to follow up with a revised GCN architecture code named Sea Islands (no, not the rebranded HD 8000 OEM chips) for the desktop market. We’ll likely see those cards in the coming months while the mobile Solar System parts are already shipping and have been extensively covered. Graphics technology is a huge priority for AMD so expect some big things in 2013.


Richland will be a transition product between Trinity and the upcoming Kaveri APUs. By utilizing a revised HD 8000G graphics core design, AMD claims Richland outperforms Trinity in graphics intensive workloads by 20-40%. Those are some impressive numbers but how are they derived? There seems to be some wizardry going on behind the scenes since clock speed increases would never account for such drastic improvements. It is possible that AMD is finally integrating their GCN-based architecture into APUs ahead of Kaveri but for the time being, this is just speculation.

These new Richland-based 5000-series APUs are already shipping to OEMs for use in notebooks with desktop variants possibly following at a later date. Just don’t expect it to hang around for all that long since Kaveri will be quickly taking over before the year is up.


Many of Richland’s improvements over Trinity are software-oriented and are lumped into AMD’s Elite Software Bundle. These include automatic face logon, the ability to stream content to multiple displays via Screen Mirror, driver optimizations for games and enhanced gesture control.


Moving down the product stack we come to the A6 and A4 Kab ini APUs. These quad core chips are targeted at the rapidly expanding ultrathin notebook market and small form factor PCs, effectively taking over from Brazos. Kabini will use AMD’s first ever x86 system on a chip design which incorporates an APU's normal components and a Fusion Controller Hub onto a single die. With this being done, secondary chipsets aren’t needed, thus decreasing costs and increasing overall system efficiency.

The real world results seem to be quite impressive as well with AMD claiming a 40% performance increase over Brazos 2.0 while still retaining battery life of up to 10 hours. If these numbers turn out to be true, Kabini could be a perfect fit for its intended niche.


With the desktop, notebook and ultra thin categories covered, AMD’s Temash is an APU specifically designed for the high performance tablet environment. This is a market which doesn’t have much competition since most of the processing options are simply repurposed low voltage CPUs which have been given another lease on life. As a result, the so called “premium tablet” experience has been marred by poor battery endurance and excess heat. Should an OEM try to bypass these issues, sub-par performance or drastically increased size usually follow.

By utilizing a 28nm manufacturing process and an efficient SoC design, AMD hopes their Temash APU will overcome the perceived shortcomings which have plagued high performance tablets. It will be available in dual or quad core form and power consumption should only be around the 5W mark. Meanwhile, we can expect significantly better graphics performance than Hondo was able to provide.

AMD’s 2013 lineup looks extremely impressive and there are plenty of reasons to be optimistic. However, talking about upcoming launch plans is only the first step in what will likely be a long process towards rebuilding their customer base. This is make or break time for AMD; if there’s any chance for success, from here on out, their plans have to be followed without the delays which plagued previous generations. With that being said, this now looks like a company in the throes of evolution and change rather than crisis planning. If they can execute accordingly, we may be about to witness a resurgent AMD as their HSA architecture finally comes to fruition.
Last edited:

Latest posts