• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

[gamegpu.ru] APU gaming including Skylake GT2 and Broadwell Iris Pro 6200

Page 8 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Well, i think it is supposed to have compression that reduces bandwidth requirements, but "much faster" is quite......optimistic I would say. It will most definitely still be a very limited solution.

Yea top performance will not get lot higher, what you will get is higher performance at lower TDPs. Like BristolRidge could be 30-50% faster at the same 65W TDP than Kaveri.
 
Yea top performance will not get lot higher, what you will get is higher performance at lower TDPs. Like BristolRidge could be 30-50% faster at the same 65W TDP than Kaveri.

Don't get me wrong, it IS a good thing... I always enjoy seeing same performance at lower wattage/thermals.

This would be the ideal solution for a NUC/Brix size of machine... if only someone would make one.

I was just hoping for a big performance boost. Dang.
 
Don't get me wrong, it IS a good thing... I always enjoy seeing same performance at lower wattage/thermals.

This would be the ideal solution for a NUC/Brix size of machine... if only someone would make one.

I was just hoping for a big performance boost. Dang.

Unfortunately for us, Big performance boost will come with ZEN APUs some time in 2017.
 
Unfortunately for us, Big performance boost will come with ZEN APUs some time in 2017.

Really? I dont think we know yet. Unless they incorporate HBM or some other technology to overcome the limited bandwidth it is still going to be a very limited solution. Not to mention APUs will be competing with hopefully much faster and more efficient 14/16 nm dgpus.
 
Did a small test to see what kind of improvements does the delta color compression implemented in Carrizo bring in practice. The results are quite depresessing, but pretty much exactly what was expected. It seems that while the DCC slightly improves the situation, for some reason it is not as effective on Carrizo as it is on discrete cards (e.g Tonga).

I fixed the GPU frequency to 400MHz in order to allow it to reach it´s full, non-restricted (bandwidth) performance at the higher memory frequencies. Then I ran the test with different memory speeds. The TDP was set to 65W in order to keep the frequencies stable.

Despite the DCC technology the iGPU still needs around 62MB/s of bandwidth per GFlop in order to reach most (96.8%) it´s full performance. The number is somewhat similar compared to Kaveri (no DCC available), however the delta (performance loss due bandwidth limitation) is smaller on Carrizo thanks to DCC.

Based on these numbers the FX-8800P (800MHz, 512SP GPU) would require 51.2GB/s (819.2 * 62.5) of memory bandwidth in order to be able to completely utilize it´s GPU. This doesn´t look too good for AM4 Bristol Ridge parts which have significantly higher GPU frequency and still have only 38.4GB/s (2400MHz DDR4) of bandwidth available. Ideally the fastest Bristol Ridge AM4 APU would need to be paired with RAM operating at ~ 4400MHz.

Unless Raven Ridge solves the bandwidth issue, AMD APUs are better of dead :'(

afNW4Ru.png
 
65W TDP on a Laptop ??

Edit: I get 1400+ on FireStrike with the 65W TDP A8-7600 and 2133MHz

Edit 2 : Perhaps it needs more GPU perf, try at higher clocks and see if it makes any difference.
 
Last edited:
I don't quite understand the chart above, to me looks like implying the APUs' IMC are limited to 2133MHz and it is already known.
BristolRidge uplift would mostly due to DDR4 2400MHz and a bit higher GPU clocks.
 
65W TDP on a Laptop ??

Edit: I get 1400+ on FireStrike with the 65W TDP A8-7600 and 2133MHz

Edit 2 : Perhaps it needs more GPU perf, try at higher clocks and see if it makes any difference.



Did you actually read anything I wrote? 🙄
 
It really shows that Carrizo 512 Shader iGPU is Memory Bandwidth limited even at 400MHz and that DCC doesnt help that much.

Well perhaps DCC will scale better at high clocks
 
Back
Top