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
eddman - Tuesday, February 12, 2019 - link
Just to clarify my comment; there was no proof that nvidia deliberately implemented the tessellation feature badly to cripple AMD.just4U - Thursday, February 7, 2019 - link
At the moment I am not concerned about the drivers. This card comes in at pretty impressive numbers.. looks to be slightly better than the 1080ti but with 16G of mem.. and not cheap mem either so it will be useful in a few years (likely) I want one!!cmdrdredd - Thursday, February 7, 2019 - link
Slightly better than 1080ti which is what 3 years old now? Not impressedjust4U - Thursday, February 7, 2019 - link
Which is pretty much the state of affairs regardless is it not cmd? Are you majorly impressed with the 2080ti??? it's only marginally faster than the 3 year old 1080ti as well.I own 1080s and vega56s. Those vega56s would be a huge upgrade if I went to the new Vega. The 1080s? Meh.. yeah a little .. not much.. not worth the upgrade.
LogitechFan - Friday, February 8, 2019 - link
it's 30% on average. if this is only marginally better for you, then of course you deserve an amd card :Deddman - Friday, February 8, 2019 - link
... for a 43% higher launch MSRP, or if we compare it to the currently cheapest 2080 Ti at $1150, 64%.This is one of the worst generational launches so far, where price/performance actually went DOWN.
Gastec - Tuesday, February 12, 2019 - link
Time is relative. What if Nvidia and everybody else would choose to release a new generation every 5 years? Most so-called gamers in the World don't even have the "old" GTX 1080Ti.kostaaspyrkas - Sunday, February 10, 2019 - link
you are totally right...i wonder why no reviewer ever says that... its been many times proven that all radeon cards 6 months after release always take lead from their nvidia competitors...nvidia leads in older games...amd future proof...i dont buy a 700 euro card for 1 year..i keep its 3 plus years at leastGastec - Tuesday, February 12, 2019 - link
That's the difference between you and these tech reviewers and their accompanying "unbiased" trol...I mean bragge...commentators, COMMENTATORS! They "upgrade" to the latest and greatest each new generation :)boozed - Thursday, February 7, 2019 - link
I was underwhelmed at its launch because it seemed like just a speed bump; on paper, it didn't seem that impressive.I am now suitably whelmed.