AMD Kaveri Review: A8-7600 and A10-7850K Tested
by Ian Cutress & Rahul Garg on January 14, 2014 8:00 AM ESTProcessor Graphics: Compute and Synthetics
Our GPU Compute tests are designed to stress the integrated graphics of the system using old and new GPU tools. This is where the benefits of Kaveri should come in – if a benchmark is programmed to take advantage of the GCN architecture then the relevant speed up should be observed. In none of the GCN benefits have any use then we are relying on pure grunt to get the top scores.
CompuBench CL Fluid GPU + Computer Vision GPU
CompuBench CL is an OpenCL compute benchmark designed to test some common in-use algorithms. Due to the way it is designed, any OpenCL compatible device can run the benchmarks, and as such we have run both the Fluid Dynamics and Computer Vision portions on the CPU and integrated graphics on each processor we have tested. Here are the GPU results.
GCN really wins out here, showcasing how important OpenCL compliance can be to extract potential compute.
Facebook
Twitter
RSS
380 Comments
View All Comments
jasonelmore - Tuesday, January 14, 2014 - link
I really wish these were launching in BGA GDDR5 Laptop/Mini ITX Packages.jaydee - Tuesday, January 14, 2014 - link
Pretty much what I was thinking as well. There are two mini-ITX FM2+ motherboards available on newegg, niether are "thin", and neither have DisplayPort. AMD's opportunity here is to market it's 45W Kaveri as the best CPU/GPU for the price in a small package. They NEED to get outside of the typical ATX, micro-ATX, mini-ATX box and into SFF, have all the ports that everyone wants, be creative with packaging and configurations (like GDDR5). They will never win a war with Intel in the traditional form-factor PCs, which is a rapidly shrinking market anyways.takeship - Tuesday, January 14, 2014 - link
Agreed. Any build not restricted to half height GPUs is better off going with a cheap intel cpu & discrete card. AMD really should be targeting ultra SFF type builds where Iris Pro is thermally limited, and a dGPU isn't an option.rhx123 - Tuesday, January 14, 2014 - link
GDDR5 7750's are available half height and at a decent price point, so even in a Low Profile machine a cheap Intel + 7750 is a better option. That's what I'm running anyway. Passively cooled i3 never reaches above 65c and the Saphire 7750 Low Profile is pretty quiet at idle.Mopar63 - Tuesday, January 14, 2014 - link
The last paragraph of this article shows someone that GETS IT, where Kaveri and the APU design in general is heading.nissangtr786 - Tuesday, January 14, 2014 - link
I can't believe how right I was, I was saying i3 4130 cpu performance and 2400-2500 3dmark11 gpu performance similar to my gt650m in my laptop. Funnily enough my laptop with i5 3210m at 2.9ghz gt650m with screen takes 87w, if I had an i3 4130 it would take about 92w lets say so it is about right. I am more shocked how spot on I was.HammerStrike - Tuesday, January 14, 2014 - link
The entire Anand reader base congratulates you on your deep insight and prophetic powers of deduction.nathanddrews - Tuesday, January 14, 2014 - link
I, for one, welcome our new nissangtr786 overlord.Zorba - Tuesday, January 14, 2014 - link
It would have been nice to see some non-integrated chips added to the benchmarks like an FX-6300. Ever since the APUs came out, it seems no reviews actually compare high-end iGPU vs moderate dGPU and CPU. Looking at the price, you could get a decent CPU+GPU for the cost of the A10-7850K, so it would be nice to see that as an option.R3MF - Tuesday, January 14, 2014 - link
"do any AnandTech readers have an interest in an even higher end APU with substantially more graphics horsepower?"Yes, and No.
I do want a higher-end APU, but I'd like to see one with four CPU modules and 256 shaders:
47% of the kaveri die space is GPU
http://www.extremetech.com/wp-conten...d-to-intel....
If you consider that roughly 20% is uncore, that leaves roughly 33% as CPU.
Give or take, 8 shader cores is fifty percent larger than 4 cpu cores.
You could double that cpu portion to 66%, and still leave 14% for shader cores.
Make the total die size just 10% bigger and you have an 8 cpu core APU with 4 HSA enabled shader cores ready to grind through FPU work. pretty much die-size neutral.