New Performance Benchmarks of AMD's Vega Frontier Edition Surface

[john_]

This is disappointing. I wonder if they had to lower the IPC -compared to Fiji - to get higher frequencies. In any case I don't expect anything from drivers. Either RX Vega will be some kind of different in hardware, or it will have to be able to sustain a frequency close to 1700MHz to be highly competitive.
For now Vega looks like the GPU big companies where expecting, not like the GPU gamers where expecting.

 

[r9]

I hope is a driver issue.
Otherwise would be a major fail for AMD.

 

[Countryside]

People are still having hard time understanding that this gpu is not meant for gaming.

 

[ratirt]

This is disappointing. I wonder if they had to lower the IPC -compared to Fiji - to get higher frequencies. In any case I don't expect anything from drivers. Either RX Vega will be some kind of different in hardware, or it will have to be able to sustain a frequency close to 1700MHz to be highly competitive.
For now Vega looks like the GPU big companies where expecting, not like the GPU gamers where expecting.

it's totally different than fiji and It's not for gamers but it gives some information. if in fallout 4 this Vega shows the performance of 1080TI maybe Vega gaming edition will be as fast as1080 TI or even better. Since it's not gaming card and pulls of that much FPS in one game that can be an indication of the speed of RX Vega but across all the games not just one. It would seem that Vega is capable of reaching 1080 Ti's performance.

 

[RejZoR]

The chip is Fury X on steroids (imagine Fury X at 1,6 GHz) in its worst case scenarios and yet it sometimes performs even worse than old Fury X. How it doesn't click in anyone's heads that this just doesn't compute on any level in any way, makes no sense and is entirely illogical?

Old Fury X alone could be ultra competitive if they could run it at 1.6 GHz. So, seeing brand spanking new core with a lot of things further optimized and also learned from mistakes on Fury X from design perspective just doesn't make any sense for it to be still slower.

 

[robert3892]

One thing that everyone seems to have forgotten is that games haven't been optimized for the Vega platform.

 

[xkm1948]

Launch was crappy, but lets be honest, this is a production card, not a gaming one. It's not meant to be released with all the colorful and noisy PR that we expect with gamer cards. Anyone remembers a lot of fanfare around every Quadro card release? I sure as hell don't. When was the last time anyone ran Fallout 4, Dirt, Heaven and 3DMark on them (be it FirePro or Quadro)? I honestly can't remember a single time. It doesn't matter what they say, basing whole RX Vega state on FE card is like evaluating gaming performance of GeForce cards using Quadro. Yes, they can run games, but they usually do it like shit as well.

So, people, don't be stupid. With all this excitement of finally having a first actual Vega core, people forgot they just threw all the logic out the window by testing it as a gamer card. If gaming RX Vega will be rubbish, piss on it by all means, but doing that now just makes everyone look like absolute cretins. Yes, I watched PCPer's live stream, but I still believe the same to be true.

I am going to mark this post and come back to it after July30th. Let's see how people are going to spin after the RX Vega drops. It will be glorious.

And for people calling FineWine, better driver maturation. Here is a little comparison of how much performance Fiji has improved over its current life.

First benchmark right after I got my card, no GPU overclocking. Using launch driver from AMD
http://www.3dmark.com/fs/5488050


2yrs of driver optimization, no GPU overclocking. 17.6.1 driver
http://www.3dmark.com/fs/12815443

Not the perfect analysis, but basically over the span of 2yrs I got additional 5% performance increase. That might give you some glimpse of how much FineWine you may get for Vega.

Power to you if you want to buy Vega.

The chip is Fury X on steroids (imagine Fury X at 1,6 GHz) in its worst case scenarios and yet it sometimes performs even worse than old Fury X. How it doesn't click in anyone's heads that this just doesn't compute on any level in any way, makes no sense and is entirely illogical?

Old Fury X alone could be ultra competitive if they could run it at 1.6 GHz. So, seeing brand spanking new core with a lot of things further optimized and also learned from mistakes on Fury X from design perspective just doesn't make any sense for it to be still slower.

FuryX is 4096bit
Vega is 2048bit.

So that fancy HBCC does not counter the loss of memory bandwidth.

 

[Aenra]

A bit of a perspective here.

Unlike myself, my bro limits his budget on principle. Also unlike myself, he plays all those stupid, shallow, 193784645287 FPS minimum games i just... anyway, you get the picture.
He had an Ati 77xx, forget its name. He could run everything, never complained or asked for 'more'. *edit: or is it 66xx? Been a while, not certain*
He replaced it with a Fury X? X Nitro? The 4gb liquid cooled one. Has it still, plays everything, never complained.
He will replace it with the new Vega. I bet my hairy behind he will also be able to play everything and not complain.

Because why complain when you can run everything?


Just another perspective. Will leave (some of) you to your flame wars.

 

[Frick]

I am going to mark this post and come back to it after July30th. Let's see how people are going to spin after the RX Vega drops. It will be glorious.

And for people calling FineWine, better driver maturation. Here is a little comparison of how much performance Fiji has improved over its current life.

First benchmark right after I got my card, no GPU overclocking. Using launch driver from AMD
http://www.3dmark.com/fs/5488050


2yrs of driver optimization, no GPU overclocking. 17.6.1 driver
http://www.3dmark.com/fs/12815443

Not the perfect analysis, but basically over the span of 2yrs I got additional 5% performance increase. That might give you some glimpse of how much FineWine you may get for Vega.

Power to you if you want to buy Vega.

Meh, $/performance is the only true metric. Not everyone's an overclocker.

 

[kruk]

The FE Vega performance is way off and the most probable reason for that are massive driver problems. Tile based rasterization might not be working properly, HBCC might have issues, primitive discard acceleration is breaking, etc. The drivers might be in fallback mode, because otherwise the games are unplayable. Only AMD driver team knows what is wrong, everything else is pure speculation. If the performance of this card would not be fixable, the card would be released months ago. Why drag the launch date otherwise?

I reserve my judgment of Vega's gaming performance for the RX Vega launch (as any sane person would do) ...

 

[xkm1948]

Meh, $/performance is the only true metric. Not everyone's an overclocker.

AMD should position RX Vega no more than $399 to be competitive. $349 would be sweet.

They surely love their new slogan "Disruptive" so I am waiting for some disruptive pricing. I agree, if the final gaming variant comes out with a good surprise in pricing it may still sell some.

 

[john_]

The chip is Fury X on steroids (imagine Fury X at 1,6 GHz) in its worst case scenarios and yet it sometimes performs even worse than old Fury X. How it doesn't click in anyone's heads that this just doesn't compute on any level in any way, makes no sense and is entirely illogical?

Old Fury X alone could be ultra competitive if they could run it at 1.6 GHz. So, seeing brand spanking new core with a lot of things further optimized and also learned from mistakes on Fury X from design perspective just doesn't make any sense for it to be still slower.

If I am not mistaken, usually when someone is trying to create/change an architecture to work at higher frequencies, it ends up lowering the IPC. Pentium 4 was slower than Pentium III but could go at much higher frequencies. AMD FX was slower than Phenom II but could work at higher frequencies. Yes, these are CPUs not GPUs, but it could be the same case here.
It wasn't making sense to me either when AMD was introducing the 8150. My reaction was the same as yours. We have seen the failure of Pentium 4. How can they come 5 years latter and create a Pentium 4? Why not enhance Thuban cores, shrink them at 32nm and come out with a real 8+ core Thuban monster at 4GHz?

it's totally different than fiji and It's not for gamers but it gives some information. if in fallout 4 this Vega shows the performance of 1080TI maybe Vega gaming edition will be as fast as1080 TI or even better. Since it's not gaming card and pulls of that much FPS in one game that can be an indication of the speed of RX Vega but across all the games not just one. It would seem that Vega is capable of reaching 1080 Ti's performance.

That Fallout 4 score is a big hope for RX Vega, but I am not holding my breath.

 

[Frick]

AMD should position RX Vega no more than $399 to be competitive. $349 would be sweet.

They surely love their new slogan "Disruptive" so I am waiting for some disruptive pricing. I agree, if the final gaming variant comes out with a good surprise in pricing it may still sell some.

So they have to do a Ryzen or burn? I don't think it's that bad.

 

[xkm1948]

So they have to do a Ryzen or burn? I don't think it's that bad.

How much do you think AMD should price this? Anything over current 1080 price line-up will be bad.

 

[cdawall]

How much do you think AMD should price this? Anything over current 1080 price line-up will be bad.

Depends how it works in rx form. If it competes with the 1080/1080ti it can be priced as such just like the fury

 

[RejZoR]

If I am not mistaken, usually when someone is trying to create/change an architecture to work at higher frequencies, it ends up lowering the IPC. Pentium 4 was slower than Pentium III but could go at much higher frequencies. AMD FX was slower than Phenom II but could work at higher frequencies. Yes, these are CPUs not GPUs, but it could be the same case here.
It wasn't making sense to me either when AMD was introducing the 8150. My reaction was the same as yours. We have seen the failure of Pentium 4. How can they come 5 years latter and create a Pentium 4? Why not enhance Thuban cores, shrink them at 32nm and come out with a real 8+ core Thuban monster at 4GHz?


That Fallout 4 score is a big hope for RX Vega, but I am not holding my breath.

That's nonsense. You don't understand the principles or basics of chip designs. No one "lowers IPC" to gain clock. IPC and clock are entirely separate things. Clock only depends on the chip design. NVIDIA is currently using narrow but faster pipeline. AMD is using wide but slower pipeline. Because, if you want to achieve high clocks, you're required to have a lot of stages in the pipeline, making it long. And that isn't always a best thing (Pentium 4 was a huge failure because of this) because whith longer pipeline, you're gaining latency and discarding things half way through costs more, causing even higher performance penalties.

IPC on the other hand means Instructions Per Cycle (IPC). It doesn't matter whether core has 500MHz or 3GHz. One cycle is 1Hz essentially. So, IPC tells you how much work a chip can perform in 1 cycle. That's it.

 

[xkm1948]

Depends how it works in rx form. If it competes with the 1080/1080ti it can be priced as such just like the fury

I am gonna watch more amd commercial and wait for it to happen then.

In other news, trolling is more fun when discussing Vega with diehard AMD boys.

 

[dwade]

AMD has unofficially lost the GPU war. Volta is coming and that GTX 2060 will plow the fastest Vega.

 

[Franzen4Real]

In my opinion only, I think the biggest problem is the fact that they released FE months ahead of RX. If it is true that RX will increase in performance due to drivers, clocks, etc., AMD did themselves NO favors by releasing FE first. My thinking on this is, had the roles been reversed and FE came out a couple months after RX, I seriously doubt it would have cost them lost money due to the card not being on the market for those months. However, what this launch did do was provide plenty of time for forums to buzz about how bad RX is going to be due to tests on a non-gaming version of the card. With the great momentum they have currently in the CPU realm, it really could carry over to the GPU launch in a big way (and no, I do not think 'any publicity is better than no publicity' in this case)

on a quick side note... I was under the impression that this is not a pro card (FirePro) that competes with Quaddro and it is not a main stream gaming card, but more of a prosumer (i.e. Titan) card. And if that is the case, then I don't think it's right to say this is a non-gaming card so we can forgive crappy results in game testing. I mean, wouldn't we have to say the same thing about Titan too? Except, Titan happens to also be a top end card for gaming performance. If I am wrong in this assumption, flame on....

For a company hoping to follow the grand slam that was Ryzen, with a walk off game winner in Vega.... They should have played the cards much closer to their chest just as they did with Ryzen and dropped a bomb out of nowhere with Vega (of course, only assuming that they already know for sure that they have a real competitor). They have Intel in scramble mode, and if RX is the real deal, they could have repeated with Vega and really disrupted the status quo.

 

[cdawall]

AMD has unofficially lost the GPU war. Volta is coming and that GTX 2060 will plow the fastest Vega.

Volta isn't coming they are refreshing pascal

 

[HD64G]

Just by seeing Vega FE matching 1070 on Witcher 3 @4K, it is a SOLID proof about poor performance due to DRIVERS! Fury X is exactly there: https://www.techpowerup.com/reviews/MSI/GTX_1080_Gaming_X_Plus_11_Gbps/25.html

No more talk needed, just patience until RX Vega is out.

 

[rtwjunkie]

I find it amusing people still trying to defend a failed product launch and a bad flagship produxt.

Flagship of what? The gaming line of cards? Ha!

I'm amazed at how people are disappointed or amazed that performance is all over the place or not as great as hoped for.

THIS IS NOT YOUR GAMING VEGA. RELAX.

Rant over. Move on everyone, nothing to get disappointed or excited for on either side. Come back when RX Vega is released.

**and no, not a fanboy for either camp. I like both, and am not in the market for anything new right now; frankly, I can play everything I want very well, and that's all anyone needs.

 

[Hood]

AMD has unofficially lost the GPU war. Volta is coming and that GTX 2060 will plow the fastest Vega.

That can't be right, because God looks out for fools, drunks, little children, and AMD fanboys. So (their thinking goes), Vega will wipe the floor with the GTX 2080...because a million fanboys can't possibly be wrong...

 

[phanbuey]

Volta isn't coming they are refreshing pascal

If that's true this 1080 is gonna last alot longer than i thought

 

[KainXS]

PcPer's review is up
https://www.pcper.com/reviews/Graphics-Cards/Radeon-Vega-Frontier-Edition-16GB-Air-Cooled-Review