Bookmark and Share


At the Computex Taipei 2013 trade-show Advanced Micro Devices officially introduced its long-known A-series “Richland” accelerated processing units aimed at desktop personal computers. The new chips feature higher-clock speeds compared to their predecessors, Trinity, and do not have any micro-architectural improvements. Some of the new APUs will be sold in retail with bundled video games.

AMD’s A-series “Richland” APUs for desktops feature up to four Piledriver x86 cores as well as AMD Radeon HD graphics with VLIW4 architecture (with up to 384 stream processors). Although AMD decided to assign a new model family for the APU family as well as new model numbers for integrated graphics, the new AMD A-series 6000-family APUs with Radeon HD 8000 graphics cores are only slightly better compared to their predecessors. The only difference between the older and newer APUs is about their clock rates, and even this difference is not dramatic: the quad-core A10-6800K and A10-6700 are faster than the A10-5800K and A10-5700 by 5-7% (in terms of both x86 and graphics cores).

A good thing about the new AMD A-series 6000-family chips is that when top models are bought in retail, end-users will also get a copy of a free game, such as Sid Meyer’s Sim City 2013.

Thanks to slightly improved graphics core clock-speed and some other optimizations, when it comes to pure graphics performance the new AMD A10-6800K is clearly faster than much more expensive Intel Core i7-4770K “Haswell” microprocessor. Unfortunately, Piledriver x86 micro-architecture is not efficient enough to beat the competitor in general-purpose applications. As a result, the destiny of Richland will be sitting inside inexpensive desktops that rely on integrated graphics.

“The new AMD A-series APU is ideal for desktop PC builders and mainstream gamers wanting outstanding performance for their money, and today AMD delivers an excellent new follow-on to the recently announced mobile lineup. The combination of high-performance, third-generation desktop APUs with our existing portfolio of low-power, mobile APUs gives us our strongest-ever lineup of products for our customers and our technology partners,” said Bernd Lienhard, corporate vice president and general manager of client products division at AMD.

The new A-series “Richland” are compatible with existing FM2 platforms as well as with future FM2+ sockets. The new chips are made using 32nm SOI process technology by GlobalFoundries.

Tags: AMD, Fusion, Richland, 32nm, Radeon, ATI


Comments currently: 8
Discussion started: 06/06/13 09:47:26 PM
Latest comment: 07/07/13 02:35:39 AM
Expand all threads | Collapse all threads


We are all waiting for killer Kaveri with unified memory space. This is Piledriver 1.1 and is a product of the poor economic times we live in - ie 20% drop in PC shipments.
3 0 [Posted by: linuxlowdown  | Date: 06/06/13 09:47:26 PM]
- collapse thread

agreed, i just crossed my fingers to see Kaveri on 20nm coz researches already said 28nm has considerably high leakage problem,
i know this is difficult but not impossible.
6 0 [Posted by: mudi1  | Date: 06/06/13 11:21:40 PM]
0 0 [Posted by: mudi1  | Date: 07/07/13 02:34:30 AM]
0 0 [Posted by: mudi1  | Date: 07/07/13 02:34:16 AM]

Truth of AMD Kaveri- bright and dark sides-
Evolution or Revolution ??
I found many AMD lovers saying that kaveri will be a killer, really…..let’s see –

Bright sides-

1. All new steamroller core + GCN ……… in top A10 4 x86core + 512 GCN units -total compute more than 1 TeraFlops(wow).
2. It’s a SoC .
3. Revolutionary heterogeneous computing i.e. AMD HSA.
4. New 28 nm process.

Dark sides- here is the real problem

1.have any one noticed that why richland got older VLIW4 GPU not the fireblade GCN ??? coz richland’s piledriver core cannot control GCN’s ground-breaking compute power, yes piledriver core is bottleneck for GCN gpu if u don’t believe than talk to any AMD official or do some test by urself. As AMD officially says stamrollar will be 20% faster clock per clock so I am expecting upto 25% x86 improvement coz 28nm but on gpu side GCN is atleast 50% more powerful than VLIW4, so 25% better cpu but 50% better gpu and some source saying kaveri will have 8gb ddr5 ram, good on paper but not in real world coz…. bottleneck will be worse for sure.
2. AMD HSA -sorry we will not see in near time coz Microsoft will not support that,,, reason is if kaveri got HSA enabled ecosystem it will crush intel core i3,i5 and some i7 coz in HSA lot of precious cpu cycles saved by not doing foolish copying-pasting as cpu and gpu work on same memory space.

I can’t understand why everyone comparing main-stream kaveri(35watt TDP) to top pricy Iris-pro based i7(47 watt TDP)
In cost of one iris-pro i7 chip we can buy a whole kaveri based notebook so plz don’t do that foolish comparison. on other side kaveri can’t beat iris-pro i7 in gpu segment- reason is kaveri has much powerful gpu but unfortunately its stamrollar cpu core is nothing in front of huswell x86 core so kaveri’s performance will be very limited due to it’s decent cpu.

Is there any way to make killer kaveri-
Yes of course
1. kaveri should come on 20nm so AMD can put more cpu clock to avoid cpu related bottleneck.
2. Don’t use 8gb dual channel ram,it will kill any chance of future upgradability. My idea is single chip 512mb ddr5 ram 2.5D stacked to APU since we have 2.5D stacking now and for 3D stacking wait for mid 2014. This will give kaveri a last level cache of 512 mb running at 175 gb/sec at a additional cost of not more than 30$. used for gpu frame buffer as well as for cpu cache this will improve both cpu and gpu performance. And by this 175gb/sec bandwidth kaveri will be worst nightmare for intel but I m 100% sure this is not going to happen.
3. Increase top version kaveri’s TDP to 45 watt to remove cpu bottleneck so it can beat iris-pro i7 which is at 47 watt TDP.

So in my openion kaveri is a evolution if HSA disabled and true Revolution if HSA enabled.
And don’t compare kaveri to top pricy i7 iris-pro,
in the last one thing kaveri will be best APU for notebooks and ultrathins.
5 0 [Posted by: mudi1  | Date: 06/11/13 12:21:52 AM]
- collapse thread

0 0 [Posted by: mudi1  | Date: 07/07/13 02:35:10 AM]
0 0 [Posted by: mudi1  | Date: 07/07/13 02:35:24 AM]
0 0 [Posted by: mudi1  | Date: 07/07/13 02:35:39 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture