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
HollyDOL - Sunday, February 10, 2019 - link
Please, read what others write before you start accusing others.eva02langley - Friday, February 8, 2019 - link
Yeah, when your speaker sound is at 70-80 dB next to you when playing CoD... /sarcasmAMD is going to solve the fan problems. Temps are lower than the RTX 2080, they can play with the fan profile a little bit better.
SeaTurtleNinja - Thursday, February 7, 2019 - link
Lisa Su is liar and AMD hates gamers. This is just a publicity stunt and a way to give a gift to their friends in the Tech Media. This was created for YouTube content creators and not for people who play games. Another Vega dumpster fire.GreenReaper - Thursday, February 7, 2019 - link
But many YouTubers play games as their content. And people vicariously watch them, so effectively it's letting many people play at once, just for the cost of the video decode - which is far more efficient!Korguz - Thursday, February 7, 2019 - link
yea.. amd hates gamers.. you DO know AMD makes the cpu and vid cards that are in the current playstation and xbox... right ???Oxford Guy - Thursday, February 7, 2019 - link
Yes, it's difficult to forgot the fiasco that is the Jaguar-based "console"(actually a poor-quality x86 PC with a superfluous anti-consumer walled software garden).
Korguz - Friday, February 8, 2019 - link
how is it a fiasco ??the original xbox used a Pentium 3 and Geforce for its cpu and gpu... the 360, and IBM CPU and ATI GPU...
Oxford Guy - Friday, February 8, 2019 - link
1) Because it has worse performance than even Piledriver.2) Because the two Jaguar-based pseudo-consoles splinter the PC gaming market unnecessarily.
Overpriced and damaging to the PC gaming platform. But consumers have a long history of being fooled by price tags into paying too much for too little.
eddman - Friday, February 8, 2019 - link
Consoles have nothing to do with PC. They've existed for decades and PC gaming is still alive and even thriving.Why do you even care what processor is in consoles?
Oxford Guy - Friday, February 8, 2019 - link
False. The only difference between the MS and Sony "consoles" and the "PC gaming" platform is the existence of artificial software barriers.