The AMD Radeon VII Review: An Unexpected Shot At The High-End
by Nate Oh on February 7, 2019 9:00 AM ESTCompute Performance
Shifting gears, we'll look at the compute aspects of the Radeon VII. Though it is fundamentally similar to first generation Vega, there has been an emphasis on improved compute for Vega 20, and we may see it here.
Beginning with CompuBench 2.0, the latest iteration of Kishonti's GPU compute benchmark suite offers a wide array of different practical compute workloads, and we’ve decided to focus on level set segmentation, optical flow modeling, and N-Body physics simulations.
Moving on, we'll also look at single precision floating point performance with FAHBench, the official Folding @ Home benchmark. Folding @ Home is the popular Stanford-backed research and distributed computing initiative that has work distributed to millions of volunteer computers over the internet, each of which is responsible for a tiny slice of a protein folding simulation. FAHBench can test both single precision and double precision floating point performance, with single precision being the most useful metric for most consumer cards due to their low double precision performance.
Next is Geekbench 4's GPU compute suite. A multi-faceted test suite, Geekbench 4 runs seven different GPU sub-tests, ranging from face detection to FFTs, and then averages out their scores via their geometric mean. As a result Geekbench 4 isn't testing any one workload, but rather is an average of many different basic workloads.
Lastly, we have SiSoftware Sandra, with general compute benchmarks at different precisions.
Facebook
Twitter
RSS
289 Comments
View All Comments
Samus - Sunday, February 10, 2019 - link
BenSkywalker, the short answer is this is based on a dated architecture (2 generations behind Turing) so there is no real way it's going to beat it in efficiency: It doesn't even try to compete with the 2080Ti.But the fact that a GCN\Vega-based card can nearly tie a 2080 is commendable. I think the problem this card has is it's $100 too expensive.
BenSkywalker - Monday, February 18, 2019 - link
If we were comparing ray traced performance that would be a valid point, but we are talking about traditional rendering. They have a half node process advantage and are using more power than a 2080 by a comfortable amount.Try finding another chip, CPU or gpu that was built with a half node advantage, used more power *and* was slower.
Either TSMC is having major problems with 7nm or AMD set a new standard for poor engineering in this segment.
Ganjir - Saturday, February 9, 2019 - link
It is a shame the infinity fabric is disabled, because crossfire would actually give these cards a reason to use ALL of that bandwidth and capacity - at least on one card. Is there a way to enable this or is it a hardware limitation?Alistair - Saturday, February 9, 2019 - link
I calculate OxfordGuy has made 11 percent of all comments in this thread ;)Zingam - Sunday, February 10, 2019 - link
AMD should invest in power stations. And maybe even sell their future Radeon XIV in a bundle with a little power station!Crion66 - Sunday, February 10, 2019 - link
Nate or Ian, can AMD choose to enable pci-express 4.0 on this card when Ryzen/TR4 3000 is released?Also can crossfire be implemented by popular gamer demand?
ccfly - Tuesday, February 12, 2019 - link
did anyone test this card in c4d ,radeon pro vs octane for speed ?peevee - Tuesday, February 12, 2019 - link
"Though AMD hasn’t made a big deal of it up to now, Vega 20 is actually their first PCI-Express 4.0-capable GPU, and this functionality is enabled on the Radeon Instinct cards. However for Radeon VII, this isn’t being enabled, and the card is being limited to PCIe 3.0 speeds"Oh God, how much I hate marketoids! Morons who cannot get an A even in the primitive school math are hired into marketing depts, and ruin EVERYTHING.