Drivers, Observations, & the Test

With the launch of a new GPU architecture also comes the launch of new drivers, and the teething issues that come with those. We’ll go over performance matters in greater detail on the following pages, but to start things off, I wanted to note the state of AMD’s driver stack, and any notable issues I ran into.

The big issue at the moment is that while AMD’s drivers are in fairly good shape for gaming, the same cannot be said for compute. Most of our compute benchmarks either failed to have their OpenCL kernels compile, triggered a Windows Timeout Detection and Recovery (TDR), or would just crash. As a result, only three of our regular benchmarks were executable here, with Folding@Home, parts of CompuBench, and Blender all getting whammied.

And "executable" is the choice word here, because even though benchmarks like LuxMark would run, the scores the RX 5700 cards generated were nary better than the Radeon RX 580. This a part that they can easily beat on raw FLOPs, let alone efficiency. So even when it runs, the state of AMD's OpenCL drivers is at a point where these drivers are likely not indicative of anything about Navi or the RDNA architecture; only that AMD has a lot of work left to go with their compiler.

So while I’m hoping to better dig into the compute implications of AMD’s new GPU architecture at a later time, for today’s launch there’s not going to be a lot to say on the subject. Most of our usual (and most informative) tools just don’t work right now.

As for the gaming side of matters, things are a lot better. Compared to some past launches, I’ve encountered a surprisingly small amount of “weirdness” with AMD’s new hardware/drivers on current games. Everything ran, and no games crashed due to GPU issues (outright bugs, on the other hand…).

The only game I’d specifically flag here is Assassin’s Creed Odyssey, a DirectX 11 game. With an unlocked framerate, this is not a benchmark that runs incredibly smoothly to begin with; and the RX 5700 series cards seemed to fare a bit worse here. The amount of (additional) stuttering was easy enough to pick up with my eyes, and the game’s own reporting tools recorded it as well. It is not a night and day difference since the game doesn’t start from a great place, but it’s clear that AMD has some room to tighten up its drivers as far as frame delivery goes.

Finally, for whatever reason, the RX 5700 cards wouldn’t display the boot/BIOS screens when hooked up to my testbed monitor over HDMI. This problem did not occur with DisplayPort, which is admittedly the preferred connection anyhow. But it’s an odd development, since this behavior doesn’t occur with Vega or Polaris cards – or any other cards I’ve tested, for that matter.

Meanwhile, as a reminder, here is the list of games for our 2019 GPU benchmarking suite.

AnandTech GPU Bench 2019 Game List
Game Genre Release Date API
Shadow of the Tomb Raider Action/TPS Sept. 2018 DX12
F1 2019 Racing Jun. 2019 DX12
Assassin's Creed Odyssey Action/Open World Oct. 2018 DX11
Metro Exodus FPS Feb. 2019 DX12
Strange Brigade TPS Aug. 2018 Vulkan
Total War: Three Kingdoms TBS May. 2019 DX11
The Division 2 FPS Mar. 2019 DX12
Grand Theft Auto V Action/Open world Apr. 2015 DX11
Forza Horizon 4 Racing Oct. 2018 DX12

And here is the 2019 GPU testbed.

CPU: Intel Core i9-9900K @ 5.0GHz
Motherboard: ASRock Z390 Taichi
Power Supply: Corsair AX1200i
Hard Disk: Phison E12 PCIe NVMe SSD (960GB)
Memory: G.Skill Trident Z RGB DDR4-3600 2 x 16GB (17-18-18-38)
Case: NZXT Phantom 630 Windowed Edition
Monitor: Asus PQ321
Video Cards: AMD Radeon RX 5700 XT
AMD Radeon RX 5700
AMD Radeon RX Vega 64
AMD Radeon RX Vega 56
AMD Radeon RX 580
AMD Radeon RX 570
AMD Radeon R9 390X
NVIDIA GeForce GTX 2070 Super Founders Edition
NVIDIA GeForce GTX 2060 Super Founders Edition
NVIDIA GeForce GTX 2060 Founders Edition
NVIDIA GeForce GTX 1070 Founders Edition
NVIDIA GeForce GTX 980
Video Drivers: NVIDIA Release 431.15
AMD Radeon Software Adrenalin 2019 Edition 19.7.1
OS: Windows 10 Pro (1903)
Meet the Radeon RX 5700 XT & Radeon RX 5700 Shadow of the Tomb Raider
Comments Locked

135 Comments

View All Comments

  • GeoffreyA - Sunday, July 7, 2019 - link

    Many thanks, Ryan, to you and the team for all the hard work. We do appreciate it.
  • catavalon21 - Sunday, July 7, 2019 - link

    Hoping for really competitive results in the mid-range for compute, that AMD doesn't have drivers that support the new architecture is absurd. To not even run on some older computer work means this was clearly not ready for prime time. Shame on you, Lisa.

    I write this, very disappointed that the choice of a mid range GPU right now isn't much more difficult.
  • catavalon21 - Sunday, July 7, 2019 - link

    ...older COMPUTE work...<sigh>
  • just4U - Sunday, July 7, 2019 - link

    Holy crap.. I wasn't actually expecting Amd to come close to Nvidia with these. (Regardless of the hype by Amd) The 5700XT is just a smidge slower than the 2070S.. and it's quite a impressive jump over the RX580/90s they replace.
  • catavalon21 - Sunday, July 7, 2019 - link

    My whining about compute aside, you're right. The 5700XT competes very well against the 2070S - better than I hoped for.
  • DanNeely - Sunday, July 7, 2019 - link

    Yeah. AMD's showing is strong enough I'm wondering if we'll see farther NVidia price cuts in the near future.
  • Kevin G - Sunday, July 7, 2019 - link

    They are indeed impressive agains nVidia's Super cards but by pricing they're more of a Vega 56/64 replacement.
  • just4U - Sunday, July 7, 2019 - link

    I was considering it from a new norm on video card pricing as to me their upper mid range and don't appear to compete with Vega multipurpose cards to replace them.
  • tipoo - Sunday, July 7, 2019 - link

    Looks like that completely outsized Particle Physics subscore was real, from multiple results coming in. Interesting. Given AMD seems to be going for a hybrid RT approach for RDNA 2.0 in 2020, I wonder if this was a half step towards building out this portion of the chip for it.

    https://browser.geekbench.com/v4/compute/4259036

    Under OpenCL, it beats a 2080TI under CUDA, in that one subtest.
  • mildewman - Sunday, July 7, 2019 - link

    Can someone explain to me why Navi requires twice the number of transistors (10.3B) compared to Polaris (5.7B) for the same number of CU's ?

Log in

Don't have an account? Sign up now