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.
289 Comments
View All Comments
tipoo - Sunday, February 10, 2019 - link
It's MI50vanilla_gorilla - Thursday, February 7, 2019 - link
As a linux prosumer user who does light gaming, this card is a slam dunk for me.LogitechFan - Friday, February 8, 2019 - link
and a noisy one at thatBaneSilvermoon - Thursday, February 7, 2019 - link
Meh, I went looking for a 16GB card about a week before they announced Radeon VII because gaming was using up all 8gb of VRAM and 14gb of system RAM. This card is a no brainer upgrade from my Vega 64.LogitechFan - Friday, February 8, 2019 - link
lemme guess, you're playing sandstorm?Gastec - Tuesday, February 12, 2019 - link
I was beginning to think that the "money" was in crytocurrency mining with video cards but I guess after the €1500+ RTX 2080Ti I should reconsider :)eddman - Thursday, February 7, 2019 - link
Perhaps but Turing is also a new architecture, so it's probable it'd get better with newer drivers too.Maxwell is from 2014 and still performs as it should.
As for GPU-accelerated gameworks, obviously nvidia is optimizing it for their own cards only, but that doesn't mean they actively modify the code to make it perform worse on AMD cards; not to mention it would be illegal. (GPU-only gameworks effects can be disabled in game options if need be)
Many (most?) games just utilize the CPU-only gameworks modules; no performance difference between cards.
ccfly - Tuesday, February 12, 2019 - link
you joking right ?1st game they did just that is crysis (they hide modely under water so ati card will render these too
and be slower
and after that they cheat full time ...
eddman - Tuesday, February 12, 2019 - link
No, I'm not.There was no proof of misconduct in crysis 2's case, just baseless rumors.
For all we know, it was an oversight on crytek's part. Also, DX11 was an optional feature, meaning it wasn't part of game's main code, as I've stated.
eddman - Tuesday, February 12, 2019 - link
... I mean an optional toggle for crysis 2. The game could be run in DX9 mode.