FP64 Performance and Separating Radeon VII from Radeon Instinct MI50

One of the interesting and amusing consequences of the Radeon VII launch is that for the first time in quite a while, AMD has needed to seriously think about how they’re going to differentiate their consumer products from their workstation/server products. While AMD has continued to offer workstation and server hardware via the Radeon Pro and Radeon Instinct series, the Vega 20 GPU is AMD’s first real server-grade GPU in far too long. So, while those products were largely differentiated by the software features added to their underlying consumer-grade GPUs, Radeon VII brings some new features that aren’t strictly necessary for consumers.

It may sound like a trivial matter – clearly AMD should just leave everything enabled – but as the company is trying to push into the higher margin server business, prosumer products like the Radeon VII are in fact a tricky proposition. AMD needs to lock away enough of the server functionality of the Vega 20 GPU that they aren’t selling the equivalent of a Radeon Instinct MI50 for a fraction of the price. On the other hand, it’s in their interest to expose some of these features in order to make the Radeon VII a valuable card in its own right (one that can justify a $699 price tag), and to give developers a taste of what AMD’s server hardware can do.

Case in point is the matter of FP64 performance. As we noted in our look at the Vega 20 GPU, Vega 20’s FP64 performance is very fast: it’s one-half the FP32 rate, or 6.9 TFLOPS. This is one of the premium features of Vega 20, and since Radeon VII was first announced back at CES, the company has been struggling a bit to decide how much of that performance to actually make available to the Radeon VII. At the time of its announcement, we were told that the Radeon VII would have unrestricted (1/2) FP64 performance, only to later be told that it would be 1/8. Now, with the actual launch of the card upon us, AMD has made their decision: they’ve split it down the middle and are doing a 1/4 rate.

Looking to clear things up, AMD put out a statement:

The Radeon VII graphics card was created for gamers and creators, enthusiasts and early adopters. Given the broader market Radeon VII is targeting, we were considering different levels of FP64 performance. We previously communicated that Radeon VII provides 0.88 TFLOPS (DP=1/16 SP). However based on customer interest and feedback we wanted to let you know that we have decided to increase double precision compute performance to 3.52 3.46 TFLOPS (DP=1/4SP).

If you looked at FP64 performance in your testing, you may have seen this performance increase as the VBIOS and press drivers we shared with reviewers were pre-release test drivers that had these values already set. In addition, we have updated other numbers to reflect the achievable peak frequency in calculating Radeon VII performance as noted in the [charts].

The end result is that while the Radeon VII won’t be as fast as the MI60/MI50 when it comes to FP64 compute, AMD is going to offer the next best thing, just one step down from those cards.

At 3.5 TLFLOPS of theoretical FP64 performance, the Radeon VII is in a league of its own for the price. There simply aren’t any other current-generation cards priced below $2000 that even attempt to address the matter. All of NVIDIA’s GeForce cards and all of AMD’s other Radeon cards straight-up lack the necessary hardware for fast FP64. The next closest competitor to the Radeon VII in this regard is NVIDIA’s Titan V, at more than 4x the price.

It’s admittedly a bit of a niche market, especially when so much of the broader industry focus is on AI and neural network performance. But there’s none the less going to be some very happy data scientists out there, especially among academics.

AMD Server Accelerator Specification Comparison
  Radeon VII Radeon Instinct
MI50
Radeon Instinct
MI25
FirePro S9170
Stream Processors 3840
(60 CUs)
3840
(60 CUs)
4096
(64 CUs)
2816
(44 CUs)
ROPs 64 64 64 64
Base Clock 1450MHz 1450MHz 1400MHz -
Boost Clock 1750MHz 1746MHz 1500MHz 930MHz
Memory Clock 2.0Gbps HBM2 2.0Gbps HBM2 1.89Gbps HBM2 5Gbps GDDR5
Memory Bus Width 4096-bit 4096-bit 2048-bit 512-bit
Half Precision 27.6 TFLOPS 26.8 TFLOPS 24.6 TFLOPS 5.2 TFLOPS
Single Precision 13.8 TFLOPS 13.4 TFLOPS 12.3 TFLOPS 5.2 TFLOPS
Double Precision 3.5 TFLOPS
(1/4 rate)
6.7 TFLOPS
(1/2 rate)
768 GFLOPS
(1/16 rate)
2.6 TFLOPS
(1/2 rate)
DL Performance ? 53.6 TFLOPS 12.3 TFLOPS 5.2 TFLOPS
VRAM 16GB 16GB 16GB 32GB
ECC No Yes (full-chip) Yes (DRAM) Yes (DRAM)
Bus Interface PCIe Gen 3 PCIe Gen 4 PCIe Gen 3 PCIe Gen 3
TDP 300W 300W 300W 275W
GPU Vega 20 Vega 20 Vega 10 Hawaii
Architecture Vega
(GCN 5)
Vega
(GCN 5)
Vega
(GCN 5)
GCN 2
Manufacturing Process TSMC 7nm TSMC 7nm GloFo 14nm TSMC 28nm
Launch Date 02/07/2019 09/2018 06/2017 07/2015
Launch Price (MSRP) $699 - - $3999

Speaking of AI, it should be noted that machine learning performance is another area where AMD is throttling the card. Unfortunately, more details aren’t available at this time. But given the unique needs of the ML market, I wouldn’t be surprised to find that INT8/INT4 performance is held back a bit on the Radeon VII. Or for that matter certain FP16 dot products.

Also on the chopping block is full-chip ECC support. Thanks to the innate functionality of HBM2, all Vega cards already have free ECC for their DRAM. However Vega 20 takes this one step further with ECC protection for its internal caches, and this is something that the Radeon VII doesn’t get access to.

Finally, Radeon VII also cuts back a bit on Vega 20’s off-chip I/O features. Though AMD hasn’t made a big deal of it up to now, Vega 20 is actually their first PCI-Express 4.0-capable GPU, and this functionality is enabled on the Radeon Instinct cards. However for Radeon VII, this isn’t being enabled, and the card is being limited to PCIe 3.0 speeds (so future Zen 2 buyers won’t quite have a PCIe 4.0 card to pair with their new CPU). Similarly, the external Infinity Fabric links for multi-GPU support have been disabled, so the Radeon VII will only be a solo act.

On the whole, there’s nothing very surprising about AMD’s choices here, especially given Radeon VII’s target market and target price. But these are notable exclusions that are going to matter to certain users. And if not to drive those users towards a Radeon Instinct, then they’re sure to drive those users towards the inevitable Vega 20-powered Radeon Pro.

Vega 20: Under The Hood Meet the AMD Radeon VII
POST A COMMENT

292 Comments

View All Comments

  • Kevin G - Thursday, February 7, 2019 - link

    Not a bad showing by AMD but this card isn't the victory that they needed either. The gaming side is OK and lines up with the GTX 1080 Ti and RTX 2080 fairly well. On the compute side it is actually very good with the extra memory capacity and more bandwidth. I have a feeling that this card should have shipped with 128 ROPs which would have given it an edge at higher resolutions.

    I'm also curious as to how this card would fair at even higher resolutions like 5K and 8K. The memory bandwidth is there to humor that idea and might be feasible to get playable frame rates on specific modern games. I'd also be interesting to see how it'd fair with some older, less demanding titles at these resolutions too.
    Reply
  • Holliday75 - Friday, February 8, 2019 - link

    This card feels like its meant to full the gap and now allow Nvidia to be the only player in the game for an extended period of time. This buys them time for their next architecture release. Reply
  • brokerdavelhr - Thursday, February 7, 2019 - link

    Can You please retest running the Radeon VII (an AMD part) on a Ryzen II with X470 with 16 gig of RAM? You always run AMD parts on a non AMD processor. Please retest and post results! Reply
  • mkaibear - Thursday, February 7, 2019 - link

    The point of comparative benchmarking is to change just one thing so you can see the impact of the thing you're changing. Reply
  • brokerdavelhr - Thursday, February 7, 2019 - link

    SO why do they only test on Intel machines? Why not run the same tests on an RYZEN/Nvidia and Ryzen/Radeon combo? My point is that it simply never happens. Put aside the fact that Radeon always fairs better on a AMD machine, it just seems odd is all. For the longest time, nearly every Intel machine ran Nvidia graphics. You are more likely to find a Radeon in a AMD machine than you will an Intel one.
    See my point?
    Reply
  • DominionSeraph - Thursday, February 7, 2019 - link

    Even AMD benches their video cards on Intel processors. Intel is just faster. Reply
  • brokerdavelhr - Thursday, February 7, 2019 - link

    What link is that DS - and if you ask me too google it, I will not take anything you say seriously. Or are you deliberately trolling? I know they do a side by side with intel processors with their own to show the diff, bu thats all. What is the link to the tests you are referring to? Either way - it is unbiased as they bench with both. Not so here which was my point. Reply
  • Klimax - Friday, February 8, 2019 - link

    So can you post AMDs PR results that use AMD CPUs? Reply
  • krazyfrog - Sunday, February 10, 2019 - link

    From AMD's Radeon VII page:

    "Testing done by AMD performance labs 1/21/19 on an Intel Core i7 7700k, 16GB DDR4 3000MHz, Radeon VII, Radeon RX Vega 64, AMD Driver 18.50 and Windows 10. Using Resident Evil 2 @ 3840x2160, Max settings, DirectX® 11:Radeon VII averaged 53 fps. Radeon RX Vega 64 averaged 41 fps. PC manufacturers may vary configurations yielding different results. All scores are an average of 3 runs with the same settings. Performance may vary based on use of latest drivers. RX-291"
    Reply
  • mkaibear - Thursday, February 7, 2019 - link

    Because they are for the most part running gaming tests, and if you want to remove CPU bottlenecks you pick the CPU which you have that's fastest in games.

    Which is Intel.

    If you pick anything else then you are artificially constraining performance which tends to show a regression to the mean - in other words it'll make the difference between AMD and nVidia smaller (whichever one wins)

    Equally the fact that AMD works best with AMD means they absolutely should *not* put an AMD processor in the system - that way they are artificially boosting system performance and skewing their benchmarks.

    You really need to do some reading on how you do a/b testing. Wikipedia has a good article.
    Reply

Log in

Don't have an account? Sign up now