The AMD Radeon VII Review: An Unexpected Shot At The High-End
by Nate Oh on February 7, 2019 9:00 AM ESTFP64 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.
289 Comments
View All Comments
KateH - Friday, February 8, 2019 - link
thirded on still enjoying SupCom! i have however long ago given up on attempting to find the ultimate system to run it. i7 920 @ 4.2Ghz, nope. FX-8150 @ 4.5Ghz, nope. The engine still demands more CPU for late-game AI swarms! (and i like playing on 81x81 maps which makes it much worse)Korguz - Friday, February 8, 2019 - link
Holliday75 and KateHive run supcom on a i7 930 OC'd to 4.2 on a 7970, slow as molasses late in the game VS the AI, and on my current i7 5930k and strix 1060 and.. same thing.. very slow late in the game.... the later patches supposedly helped the game use more then 1 or 2 cores, i think Gas Powered games called it " multi core aware "
makes me wonder how it would run on something newer like a threadripper, top en Ryzen or top end i7 and an i9 with a 1080 + vid card though, compared to my current comp....
eva02langley - Friday, February 8, 2019 - link
Metal Gear Solid V, Street Fighter 5, Soulcalibur 6, Tekken 7, Senua Sacrifice...Basically, nothing from EA or Ubisoft or Activision or Epic.
ballsystemlord - Thursday, February 7, 2019 - link
Oh oh! Would you be willing to post some FLOSS benchmarks? Xonotic, 0AD, Openclonk and Supertuxkart?Manch - Friday, February 8, 2019 - link
I would like to see a mixture of games that are dedicated to a singular API, and ones that support all three or at least two of them. I think that would make for a good spread.Manch - Thursday, February 7, 2019 - link
Not sure that I expected more. The clock for clock against the V64 is telling. @$400 for the V64 vs $700 for the VII, ummm....if you need a compute card as well sure, otherwise, Nvidia got the juice you want at better temps for the same price. Not a bad card, but it's not a great card either. I think a full 64CU's may have improved things a bit more and even put it over the top.Could you do a clock for clock compare against the 56 since they have the same CU count?? I'd be curious to see this and extrapolate what a VII with 64CU's would perform like just for shits and giggles.
mapesdhs - Friday, February 8, 2019 - link
Are you really suggesting that, given two products which are basically the same, you automatically default to NVIDIA because of temperatures?? This really is the NPC mindset at work. At least AMD isn't ripping you off with the price, Radeon VII is expensive to make, whereas NVIDIA's margin is enormous. Remember the 2080 is what should actually have been the 2070, the entire stack is a level higher than it should be, confirmed by die code numbers and the ludicrous fact that the 2070 doesn't support SLI.Otoh, Radeon II is generally too expensive anyway; I get why AMD have done it, but really it's not the right way to tackle this market. They need to hit the midrange first and spread outwards. Stay out of it for a while, come back with a real hammer blow like they did with CPUs.
Manch - Friday, February 8, 2019 - link
Well, they're not basically the same. Who's the NPC LOL? I have a V64 in my gaming rig. It's loud but I do like it for the price. The 2080 is a bit faster than the VII for the same price. It does run cooler and quieter. For some that is more important. If games is all you care about, get it. If you need compute, live with the noise and get the VII.I don't care how expensive it is to make. If AMD could put out a card at this level of performance they would and they would sell it at this price.
Barely anyone uses SLI/Crossfire. It's not worth it. I previously had 2 290X 8GB in Crossfire. I needed a beter card for VR, V64 was the answer. It's louder but it was far cheaper than competitors. The game bundle helped. Before that, I had bought a 1070 for the wife's computer. It was a good deal at the time. Some of yall get too attached to your brands get all frenzied at any criticism. I buy what suits my needs at the best price/perf.
AdhesiveTeflon - Friday, February 8, 2019 - link
Not our fault AMD decided to make a video card with more expensive components and not beat the competition,mapesdhs - Friday, February 8, 2019 - link
Are you really suggesting that, given two products which are basically the same, you automatically default to NVIDIA because of temperatures?? This really is the NPC mindset at work. At least AMD isn't ripping you off with the price, Radeon VII is expensive to make, whereas NVIDIA's margin is enormous. Remember the 2080 is what should actually have been the 2070, the entire stack is a level higher than it should be, confirmed by die code numbers and the ludicrous fact that the 2070 doesn't support SLI.Otoh, Radeon II is generally too expensive anyway; I get why AMD have done it, but really it's not the right way to tackle this market. They need to hit the midrange first and spread outwards. Stay out of it for a while, come back with a real hammer blow like they did with CPUs.