The AMD Radeon VII Review: An Unexpected Shot At The High-End
by Nate Oh on February 7, 2019 9:00 AM ESTRadeon VII & Radeon RX Vega 64 Clock-for-Clock Performance
With the variety of changes from the Vega 10 powered RX Vega 64 to the new Radeon VII and its Vega 20 GPU, we wanted to take a look at performance and compute while controlling for clockspeeds. In this way, we can peek at any substantial improvements or differences in pseudo-IPC. There's a couple caveats here; obviously, because the RX Vega 64 has 64 CUs while the Radeon VII has only 60 CUs, the comparison is already not exact. The other thing is that "IPC" is not the exact metric measured here, but more so how much graphics/compute work is done per clock cycle and how that might translate to performance. Isoclock GPU comparisons tend to be less useful when comparing across generations and architectures, as like in Vega designers often design to add pipeline stages to enable higher clockspeeds, but at the cost of reducing work done per cycle and usually also increasing latency.
For our purposes, the incremental nature of 2nd generation Vega allays some of those concerns, though unfortunately, Wattman was unable to downclock memory at this time, so we couldn't get a set of datapoints for when both cards are configured for comparable memory bandwidth. While the Vega GPU boost mechanics means there's not a static pinned clockspeed, both cards were set to 1500MHz, and both fluctuated from 1490 to 1500MHZ depending on workload. All combined, this means that these results should be taken as approximations and lacking granularity, but are useful in spotting significant increases or decreases. This also means that interpreting the results is trickier, but at a high level, if the Radeon VII outperforms the RX Vega 64 at a given non-memory bound workload, then we can assume meaningful 'work per cycle' enhancements relatively decoupled from CU count.
As mentioned above, we were not able to control for the doubled memory bandwidth. But in terms of gaming, the only unexpected result is with GTA V. As an outlier, it's less likely to be an indication of increased gaming 'work per cycle,' and more likely to be related to driver optimization and memory bandwidth increases. GTA V has historically been a title where AMD hardware don't reach the expected level of performance, so regardless there's been room for driver improvement.
SPECviewperf is a slightly different story, though.
289 Comments
View All Comments
Icehawk - Thursday, February 7, 2019 - link
FFXV results sure look CPU limited to me - why aren't you running at least an 8700 @ 5ghz?Oxford Guy - Thursday, February 7, 2019 - link
They look like GameWorks or something to me but I can't see why anyone cares about FF anyway. I hurt my face smirking when I saw the footage from that benchmark. Those hairstyles and that car... and they're going fishing. It was so bad it was Ed Wood territory, only it takes itself seriously.luisfp - Thursday, February 7, 2019 - link
People don't forget that Vega GPUs have the memory beside the GPU core, therefore making it more hot that normal GPUs out there. That has a lot to do with how hot it seems to be, the temperature tends to raise more due to memory temps in same area.just4U - Thursday, February 7, 2019 - link
True enough but owners of the 56/64 have found many work arounds to such things as the cards have not needed as much power as they push out. My cards (56s) use 220W of power per card They never go over 65c in any situation and usually sit in the high 50s to low 60s. with their undervolts.luisfp - Thursday, February 7, 2019 - link
I believe that Vega GPUs have the memory beside the GPU core, therefore making it more hot that normal GPUs out there. That might have a lot to do with how hot it seems to be, the temperature tends to raise more due to memory temps in same area.just4U - Thursday, February 7, 2019 - link
Better than a 64 in all situations and comparable to a 1080ti in all situations with only 5-6% performance hits against the 2080 which is costing 50-100 more here in Canada (according to pre-order sales) Yep, Im sold.ballsystemlord - Thursday, February 7, 2019 - link
Your favorite spelling/grammar guy is here. (AT Audience: Boo!)"Faced with a less hostile pricing environment than many were first expecting, AMD has decided to bring Vega 20 to consumers after all, duel with NVIDIA one of these higher price points."
Missing words (and & at):
"Faced with a less hostile pricing environment than many were first expecting, AMD has decided to bring Vega 20 to consumers after all, and duel with NVIDIA at one of these higher price points."
"Which is to say that there's have been no further developments as far as AMD's primitive shaders are concerned."
Verb tense problem:
"Which is to say that there's been no further developments as far as AMD's primitive shaders are concerned."
Thanks for the review!
I read the whole thing.
The F@H results for Vega are higher than I predicted (Which is a good thing!).
Ryan Smith - Thursday, February 7, 2019 - link
"Your favorite spelling/grammar guy is here. (AT Audience: Boo!)"You're always welcome here. Pull up a chair!
ballsystemlord - Friday, February 8, 2019 - link
I was joking. Some site content creators call people like me "The spelling and grammar trolls".I can never really be certain, so I try to be a little funny in hopes that no body will take my corrections as "troll" actions.
I don't know how you guys feel, but you've always taken mine and others corrections into consideration.
Ryan Smith - Saturday, February 9, 2019 - link
Our flaws and errors are our own doing. When pointed out, it's our job as journalists to correct them. So as long as people are being polite about it, we appreciate the feedback.