https://forum.beyond3d.com/posts/19 97699/ Whoa, now it'

How do you gauge the performance impact of this? Manually setting tessellation to 8x or something?

>>62061192
You don't.
Tesselation is not the only fuck use of geometry.

Incidentally whats with the undervolting performance?

Did AMD choose the wrong power settings as default?

>>62061211
No, this has been a thing for 5 years, gamers always get the worst silicon.

This is the most confusing GPU launch since forever.

>>62061240
It wouldn't be if AMD didn't launch 5 different lines using Zen cores this year.

Scarce resources.

>>62061250
Well they have a LOT to show, so why not?
And new shiny Radeon Pro's are ready to fight Quadro in several markets, mainly VFX one.

>AMD is still trying to figure out how to expose the feature to developers in a sensible way. Even more so than DX12, I get the impression that it's very guru-y. One of AMD's engineers compared it to doing inline assembly. You have to be able to outsmart the driver (and the driver needs to be taking a less than highly efficient path) to gain anything from manual control.
Kek.
Now that's what i call good engineering.

>>62061211
>Did AMD choose the wrong power settings as default?
Yes.
https://www.hardwareluxx.de/index.php/artikel/hardware/grafikkarten/44084-amd-radeon-rx-vega-56-und-vega-64-im-undervolting-test.html
I hope some company will be sensible enough to lower the default voltage.

Well this is just silly.
Shitty default voltage profiles and now an entire uarch feature disabled.

>>62061293
You mean utterly retarded engineering.

>>62061512
Why though.

just hurry up

File: pogchamp.png (14KB, 100x100px) Image search: [Google]

14KB, 100x100px

>>62060873

fuck, I should've bought Vega 64 at MSRP when I had the chance.

This thing is gonna fucking get a price hike by retailers because it will delete 1080Ti from existance

>>62061240
AMD is sandbagging, friend :)

>>62060873
retard here, does this mean the Wait for Drivers™ is not a meme? will we see the Vega crushing the 1080 or what exactly?

>>62061554
>retard here, does this mean the Wait for Drivers™ is not a meme?
Yes, literally AT's main editor tells you to Wait™ for Crimson Magick™ edition.
>will we see the Vega crushing the 1080 or what exactly?
Short answer yes.

>>62061192
it will affect everything, you could arguably count how much triangles vega pushes right now per op, but we can't know how much it will push with a shim
white paper says 17 per op, but it wont' be the case because it's not direct use, it has to go from vertex->primitive process so who knows how much, maybe 11, maybe barely anything

>>62061564
noice, thanks anon.

File: straws.jpg (40KB, 480x270px) Image search: [Google]

40KB, 480x270px

>>62061564

>>62061554
>Wait for Drivers™
This has been a thing for 6 years, Tahiti got a 20%+ boost from magic drivers in several months

>>62061564
>wait for Vega
>wait for drivers
>wait for Navi
>wait for waiting
>wait

>>62061587
or just buy vega now,if you can for good price it's possible in some countries, and enjoy free performance upgrades over the years
it's already 1080 performance will get only better

>>62061574
It's literally 17 through shim. They have troubles exposing it directly to devs.

>>62061612
17 is through manual control as I understand it, if you optimize for the arch
how automatic control will be doing it anyone's guess

>>62061622
There's no "manual control" now. Ryan explains why it's borderline impossible.

File: oiK8Bb9.jpg (739KB, 793x877px) Image search: [Google]

739KB, 793x877px

>>62060873
Waiting for Vega drivers™

Just once, just fucking once, will AMD quit hiding their drivers!

You people expect the same drivers on launch from AMD as you do from Nvidia, while ignoring that RTG is only 3000 people with focus split on APU, while Nvidia is 10000 dedicated to GPUs only.

Not happening.

>>62061753
Well looks like their Pro drivers are working nice and dandy right now.

>>62061768
does NGG work in pro drivers? are there any confirmations?

>>62061794
SPECapc benches from german THG show exceptional geometry perf in the likes of Creo.
>http://www.tomshardware.com/reviews/amd-radeon-vega-frontier-edition-16gb,5128-6.html
Decent for a fresh uarch.

>>62061794
>100% not enabled in any current public drivers
>ANY

>>62061205
but it's by and large the only one that will produce sub pixel geometry so long as the game's lod is worth a damn.

>>62061819
I hope all hell will break lose when it works, spectacle will be fun to watch.

>>62061553
not sandbagging, just their low budget and abysmal gaming sales from the 4000-200 are showing, getting the pro drivers working was important, getting the gaming drivers, well shit, no one buys amd gpus even when they are better.

>>62061554
>>62061564

currently the an undervolt oc of a 56 will be margin of error as good as a 1080, the 64 is also margin of error a 1080, right there is the bottleneck, how far ahead the 56 and 64 will go when a bottleneck that currently allows them 4 when they were designed for 17 is anyone's guess, but lets take amds words when talking to people who can and will sue if they are lied to with some weight 'amd is more than competitive given price' and amd priced the cards at 400 and 500 and 600$ respectively, currently the only one that is more than competitive is the 400$ one.

I am not expecting miracles here, but I am expecting something.

>>62061240
>>62061211
If you couldn't figure it out yet, AMD wanted to fix this in a driver update and magically bring up performance while bringing down power usage. But some faggot had to figure it out too soon.

>>62061585
that was also a 100% new gpu arch, I am fairly sure vega is just a completely reworked version of the same arch with a focus on bottlenecks. Ironicly, currently being heavily bottlenecked by drivers.

>>62061250
5 likes of zen...

you got the 7 the 5 and the 3, then you have thread ripper and epyc, you will also have the laptop one and possibly the apu around christmas

>>62061916
Vega is the biggest change since GCN1, and don't forget that Hawaii(GCN2) got a pretty big boost in performance over its life.

>>62061929
Ryzen 3-7
Threadripper
EPYC
Mobile
Pro
Desktop APU(next year)
5 different lines this year sharing resources with GPUs

Atm every fucking Radeon everywhere in the world is sold out so why wouldn't they make you wait? It's shitty move for customers but on the other hand: money.

Again fuck you miners.

>>62061933
no shit, but it's almost all bottleneck alleviation, something gcn had massive problems with, and if the alleviation works, they can massively scale for navi, as in, mcm without hitting a 'not all shaders are used' problem.

>>62061944
Tahiti had no bottlenecks.
It was also the only one designed by former ATi (canada) team

>>62061944
That's exactly the point of Vega.
Also Vega is exactly the opposite of Paxwell: it goes tall versus wide.

>>62061952
New Zealand confirmed best GPU

>>62061952
Neither had Hawaii.
It's Fiji that was a bottleneckfest.
4k ALUs@4tris/clock was not the best idea i guess.

>>62061940
I can send you vega 64 for 52k rubles, want it?

>>62061975
>пынeбyмaжки
Do not.

>>62061952
the massive bottleneck for tahiti was not present in its first go, the arch was meant to scale but it largely did not scale as far as it was suppose to before full utilization wouldn't happen, see the 290-fury x and current vega

the gpu also had the worst bottneck possible, shitty devs.

see amd uses a hardware scheduler, something a dev needs to program for and around to get the most out of it, while nvidia has a far more flexible but resource intensive software one. nvidia is able to wildly change how the shit runs because it can do it in software and if something breaks they can fix it, in amd's case, when shit works, it works SO much better then nvidia will, but when it doesn't they take a hardware hit. games have been able to multi thread since the dawn of dx11, how many games are properly multithreaded? nvidias gpu forces threading though software, while amd cant.

I would call shit developers a bottleneck that nvidia dealt with on their own, and amd is unable to.

>>62061999
Having only 4 front-ends and nothing else seriosly limits the ability for uarch to scale.
Vega's idea of scaling with ALU count is nice.
Quite an elaborate way to cure inherent bottleneck of GCN.

>>62062020
if they scale near perfectly, this is assuming that 17 happens and it's not just a peak theoretical, than a 16,000 shader gpu would be possible. in bad games it would be bottlenecked a bit, and in well programed ones it would hit dam near a hardware limit bottleneck.

>>62062041
The other bottleneck people ignore is that CU utilization, which is far from stellar.

In short, AMD has issues keeping the cores fed.

>>62062046
IWD fixes that.

>>62060873
And when it's ready volta comes and it's Assfuck Maximizing Devices

>>62062071
>bigger dies
Lmao.
Its not like...
...hmm...
...maybe AMD can launch a refresh with biggur dies too?

>>62062071
>volta comes

Q2 2018?
If anything that's closer to Navi

>>62062080
>AMD bigger dies
Everything is pointing to them not being able to do that. Zen is all 200mm dies, polaris was three small dies as well. Only nvidia has a power to put out a full product stack of dies last year, I know it was the big 14nm refresh, but it was 6 seperate gpu dies in a year which is a hell of a lot, even if it's all the same product with bits chopped off in design.

>>62062126
>Zen is all 200mm dies
Because they don't need bigger ones.
>polaris was three small dies as well
Because it doesn't scale.
Vega does.
There's totally going to be big buff FP64 Vega.

>>62061871
This. Gaymers are the last priority when you have limited resources.

>>62062177
If the gpus actually sold, they would be top priority, but considering gamers refused to reward amd for being the best and at a cheaper price point, they are just giving token effort anymore because the market for gpus is to big to just say fuck you in its entirty to.

>>62062146
I think it's more a problem of a cost. The smaller zen dies have just been revealed to be 40% cheaper, polaris was targeting $200 msrp etc. Even vega10 is quite far from the reticle limit as well and it's being used as amd's primary hpc accelerator.

The rumours of vega20 fp64 are all on 7nm which again will shrink the die size. But GF's 7nm also has an increased ~700mm reticle limit and now amd has some money who knows what they've got lined up outside of mcm.

>>62061553
Second HBM2 supplier won't be in production until Q4. Performance related feature isn't ready at launch. Another mining boom. AMD being mum market pricing and supply issue, contributing to the price shock. That's planning incompetence, not sandbagging.

>>62062253
AMD uses Samsung HBM for V64 and Hynix for V56

>>62061643
can you imagine amd letting the usage of primitives on the hands of the devs? every single nvidia game would have them disabled kek

no wonder why amd is trying to force everything to be done via the drivers without any dev

>>62062253
It's not about HBM2 supply, heck, that's not the problem.
Wafer capacity is the problem.
You know it's silly, but AMD needs a LOT of wafers, like a LOT, they need enough Zeppelins to satisfy 4 out of 7+1.
GPUs are low priority for now.

>>62062071
the true volta will have hardware sc and proper fp16 support...
as long as they dont have that calling them volta is a bit much

>>62062288
No, it's the other way.
>AMD is still trying to figure out how to expose the feature to developers in a sensible way. Even more so than DX12, I get the impression that it's very guru-y. One of AMD's engineers compared it to doing inline assembly. You have to be able to outsmart the driver (and the driver needs to be taking a less than highly efficient path) to gain anything from manual control.
It's too complex.

>>62062337
we already know that amd wont let any dev do the job
they are giving them an abstraction layer via the profiler but thats it the whole project cars fiasco was an eye opener for them on what is to follow if vega actually delivers that magical 17 number per unit...
not many devs took advantage of the culling mechanism on polaris too certenly not many on nvidia games witcher 3 on x8msaa was catastrophic for amd it was clear that the devs didnt bother at all with amd

>>62062337
>too complex
You mean game developers are too retarded.

I'm assuming that when both automatic primitive shaders as well as manual primitive shaders get introduced, AMD will provide ways to get the primitive shader code that AMD generates for your vertex+geometry shader. At that point, it's simply tweaking and profiling to see what works best.
Even when that wouldn't be the case, we'd still see a list of "best practices" come along when it comes to writing efficient shader code.

>>62062391
>You mean game developers are too retarded.
More or less so, yes.
>AMD will provide ways to get the primitive shader code that AMD generates for your vertex+geometry shader.
According to Rys they are not planning to do that now.
Maybe later.
And totally for the next console cycle.

>>62061915
>launch bad product on purpose so you can patch it and turn it into a mediocre product
Why would they want this? Day 1 reviews affect sales more than any driver update would.

>>62062497
>Day 1 reviews affect sales more than any driver update would.
>no stock
>sales
?

>>62062537
Doesn't matter. In 3 months time when there is stock and someone types in rx vega review on google the results they will get will all be day 1 reviews.

>>62062555
...Unless AMD kindly asks everyone to retest Vega, that is.

>>62062497
they knew it was going to sell out for weeks to come anyway.
Better to take advantage of the mining boom while it lasts that to sit on a stockpile of cards waiting for the right drivers.

>>62062560
everyone will anyway, it's like ryzen didn't teach you anything

>>62060873
You're welcome. Next I'm going to see if anyone can confirm or deny whether Mantor's interview to GN was about PDA or actually about culling functionality in prim shaders.

>>62062746
It was definetly, 100% totally primshader.
PDA is Polaris tech, it won't be discussed.

>>62062761
Yes, that's a reasonable assumption but I want to try and get it confirmed on the record by someone who spoke with Mantor.

>>62062808
Ask curlyhair.

>>62060873

What does that mean, summarised? Can we expect a better performance from the Vega cards, in the future?

>>62062996
FineWine®

>>62062996
>What does that mean, summarised?
GCN is bad at chewing triangles.
This feature (primshader) makes it good at chewing geometry.
It's currently disabled.
>Can we expect a better performance from the Vega cards, in the future?
Oh yes.
They can literally name next Crimson a "magic edition".

>>62061643
am I the only one who thinks gigaprimitives per second sounds fucking retarded

>>62063008
I love your memes

>>62063036
Yes.
Learn what geometric primitive is.

>>62063052
I just feel like you can't affix giga to whatever you want

>>62063045
th.. thanks :3

>>62063014
>They can literally name next Crimson a "magic edition".
not FineWine Edition? they are loosing the meme wars

>>62063066
You can.
>>62063081
Get back to work you lazy pajeet.
I need driver for my future 56 Nitro+.
>>62063094
Whatever.
The age of magick drivers is back, it's almost early 2000's.

>>62060873
DELET THSI

File: 1485076808448.gif (2MB, 320x218px) Image search: [Google]

2MB, 320x218px

>>62063104
>You can.

>>62063113
Yes, soon we'll measure EPYC performance in dead gigajews per second.

15-30% boost is possible with the meme drivers? Holy shit.

>>62060873
Yeah no. I got myself a 1080. Fuck AMD GPUs at this point.

>>62063132
Yeah.
You just need to read the whitepapers and look at B3D suite results to guess it.
>>62063138
Hi Jensen.
Thank you for magical Titan drivers.

>>62063159
Is that your sad attempt at portraying me as shill?

>>62063172
No, it's my funny attmept at portraying you as retarded shitposter.
Get the fuck out of this thread.

>>62063181
Funny how mad you brandcucks get. Do you also have a Vega dildo or buttplug?

File: 1.jpg (57KB, 455x400px) Image search: [Google]

57KB, 455x400px

>>62063189
>getting this angry
Whoa.

>>62063195
>no u anime shitpost is all he can come up with
K.

>>62063138
Enjoy your incipient buyers remorse :^)

File: 1500647069908.jpg (75KB, 720x389px) Image search: [Google]

75KB, 720x389px

>>62063094
fino vino, rogacci

AMD has always done weird stuff, the 4870x2 was the first try for a MCM gpu, it has a high bandwidth side channel to the other core that was never enabled.

>>62063245
Honestly that was pretty low effort bait.
(You) should try harder.
>>62063276
No, Sideport was different.

File: 1472944354661.png (473KB, 590x332px) Image search: [Google]

473KB, 590x332px

>>62063273
in all seriousness, next crimson iteration might be called just that

>>62063269
Enjoy yours. 1080 for 490€ is a good deal when Vega 64 stock costs 650€ but doesn't hold up to the 1080.
>inb4 muh Freesync
1080 still wins.

>>62062177
Over 60% of nvidia's profits are from gamers

>>62063364
Because children love nVidia.
Radeon stopped selling somewhere during X1950 times.

>>62063336
yeah, 490+200=500 obviously

>>62063387
>fixed price of 200
Yeah no. Still doesn't change the fact that 1080 beats Vega AND is cheaper as Vega.

>>62063387
vega 56 is 399 and beats 1080 when undervolted
enjoy your goyworks

File: 1502455530194.png (38KB, 682x758px) Image search: [Google]

38KB, 682x758px

>>62063402
>Still doesn't change the fact that 1080 beats Vega
whatever you say, nobody denying price is beyond sane, but at least do not lie about performance, at worst it's 3-5% slower than 1080

Even sebbbi thinks prim shader smells really funny and can do a LOT of things.

>>62063485
>cherry picking one specific game nobody gives a fuck about
20 game average or kindly fuck off.

File: Screenshot_20170822_at_9.56.06_AM.png (68KB, 611x621px) Image search: [Google]

68KB, 611x621px

>>62063570
Nevermind that, he is using a stock performance chart in a couple versatile about how Vega 56 performs undervolted

>>62063485
Nice cherry picking

File: 1493659133408.png (72KB, 676x952px) Image search: [Google]

72KB, 676x952px

>>62063718
here is the worst performing game on vega, 10% off

File: Screenshot_20170822_at_9.55.12_AM.png (71KB, 607x615px) Image search: [Google]

71KB, 607x615px

>>62063742
>Stock voltages
>Day 1 drivers
Get with the times, gramps.

>>62062080
They can't because GCN is limited to 64CUs. There's no indication that has changed. Maybe it will if Navi is mcm since it's no longer a conventional configuration

>>62062391
>You mean game developers are too retarded
Fuck off. Game engine development is actually one of the few places where math is rampant and interesting. They're just not going to fuck with architecture specific programming

>>62063402
gibbo gtfo of /g/

>>62063132
Only in geometry intensive scenarios. Fanboys are conveniently ignoring that Vega still has bandwidth and texture and pixel throughput issues, literally half the throughput of big pascal

>>62064068
you dont really know much about technology eh?

>>62061999
>games have been able to be multi thread since the dawn of dx11
That's not true. AMD had to fight tooth and nail to get their hardware scheduler exposed in Vulkan and DX12. Don't you remember Mantle? AMD didn't just develop an API and then chuck it in the trash for no reason; they gave the API away to anyone who wanted it and it was incorporated into the aforementioned because no one was going to do the work to expose the AMD hardware scheduler, just like when ATI shipped cards that had tessellation in 2002, it wasn't utilised. You are correct, however, that Nvidia uses a software scheduler that nobody is has any idea how it works outside nvidia because it's more or less rocket science.

>>62064068
Until the front end bottleneck is relieved it's not possible to even fairly evaluate what other bottlenecks may or may not exist.

>>62064093
Do you? The Dirt 4 MSAA kerfuffle shows that Vega chokes when bandwidth requirements go up. Culling with primitive shader will improve culling but its a victory over a margin, any bandwidth reduction will be small. Vega remains a deeply flawed architecture.

>>62064183
anon, what bandwidth is used the most for in games?

>>62064178
Bottlenecks are entirely dependent on the usage case. But one thing is clear, Vega is not on par with big pascal is several ways. Also, with 4k textures and 4k resolution gaining momentum at the top end where Vega competes you can be sure texture and pixel throughput will be weaknesses. Vega is not a well thought out architecture or at the very least AMD's not certain where it should be headed

>>62063742
Holy shit the R9 295x is still relevant in high end.

>>62064227
Entire dependent upon the game. It's a question with a false premise.

Don't hold your breath. It takes amd at least 3 months to push any new drivers out.

>>62064242
....and Vega buttfucks Pascal at compute, so I think you don't actually know what you're talking about.

File: aHR0cDovL21lZGlhLmJlc3RvZm1pY3JvLmNvbS9SLzgvNjkzMDQ0L29yaWdpbmFsLzAzLUNyZW8tU2NvcmUucG5n.png (37KB, 711x533px) Image search: [Google]

37KB, 711x533px

>>62064183
stop shitposting since you dont know what you are talking about

>>62064265
I think you need to look up what is polygon and how gpu handle it through rendering pipeline.

>>62064011
What the fuck is that meme?

>>62064305
Creo is CAD you retard. The only thing going for it is somewhat high poly but almost guaranteed lower than games because you'll be working on one or two objects at a time that are approximated from parametric calculations into a polygonal model and have the most basic color and shader data as possible. Compared that to a game with multiple models, each with texture and various shader maps that could be 1k or 2k resolution in a modern title. Creo probably demands a fraction of the bandwidth that a game does.

>>62064408
Are trying to meme that Vega is BW starved?
Oh boy.

>>62064408
do you hear your self? do you even see that vega is rendering a 4K creo ? holy fuck just stop SHITPOSTING you are embarassing your self

also LOL creo needs less bandwidth than games..
k gibbo we know its you just go back to try and sell cards on lies

>Vega is bandwith starved
>OCing stacks on 64 does nothing
>V-Vega is totally BW starved believe m-me!
Meh.

>>62064431
>chokes with MSAA at 1080p in dirt 4
>chokes at 4k in dirt 4
>dirt 4, the most advantageous title for Vega where a vega 56 beats the shit out of a GTX 1080 at 1080p with no AA or cmaa (compute intensive, bandwidth light)

Yea, it's clearly bandwidth starved. You just don't see it immediately because it's choked elsewhere too but in scenarios where Vega isn't choked by some part of the front end its bandwidth problems become quickly apparent.

/g/ is full of retarded /v/babbies who shit talk game engine architects without even understanding how interesting and vast the subject actually is. Good retards

>>62064559
>Yea, it's clearly bandwidth starved.
>OCing HBM2 does nothing
>Yea, it's clearly bandwidth starved.
(You).

File: 7.jpg (13KB, 200x200px) Image search: [Google]

13KB, 200x200px

>>62064559
that would have been the case if amd didnt had z and colour compression retard
the bandwidth req for x8 msaa while having z and colour comp is nothing
but you already know that and if you dont i feel sorry for you

>>62064559
t. sopa engineer

File: 14992235892430.jpg (16KB, 424x501px) Image search: [Google]

16KB, 424x501px

>>62060873
kek, gameworks is dead

>>62064559
Amd bad at AA since 2900xt

>>62061915

RX480 came overvolted too. It lets them use more chips

>>62061192
you can't, honestly. it all depends on the implementation which is done at multiple levels and not entirely controlled by AMD. some people think it's going to be as much as Kepler -> Pascal but that's wishful thinking and almost certainly not the case

>>62064769
>not entirely controlled by AMD
Primshader is literally controlled by AMD, from start to finish.
It's not a part of any API currently available.

Primitive discard accelerator feature should huge deal. now it enable, it barely do anything. wft

Amd no driver isn't a joke, Hire better driver team.

>>62064949
Did you had a stroke while typing that?

>>62064949
PDA is not in any way related to primshaders. It's a part of the old pipeline.

>>62064985
just mad

>>62064949
primitive shading is the huge deal not primitive discarding

>>62064949
its not enabled on the gaming cards only on the workstation ones

>>62064949
Because PDA is too late in the pipeline to fix GCN's front end geometry bottleneck. You won't see the benefits of PDA on Vega until after prim shaders are enabled.

>>62064788
vulkan
https://vulkan.lunarg.com/doc/view/1.0.30.0/linux/vkspec.chunked/ch19s02.html

>>62065049
That's usual vertex shading times many.

>>62064635
if only

>>62065258
dx12 and vulkan doesnt get well with 3rd party api's...

>>62063378
the 4000 and 5000 kicked the shit out of nvidia by a margin that should have made amd top of the gpu market, both in price and performance, and the best they got was 30-40% they then went on to be the best option for 3 more generations till the 900 started and amd was arguable, especially when it came to price for what you got... fucking sad really.

>>62064243
shit is a monster when crossfire works well.

>>62065312
That's why AMD heavily focuses on VFX markets right now.
At least there if your hardware is better and you provide support people WILL buy it.

>>62065312
yeah, if only they didn't rewrite whole driver every other week breaking everything and fixing again and breaking again
GCN is heaven compared to what was going on then

>>62064114
If I remember right, civilization 5 was the first game that used dx 11's multithreading.

This was a game that at the beginning, it showed nvidia what a gpu can do if properly utilized, and because of how fucking shit every god damn game dev is, how almost all of them stuck with single core.

dx12, vulcan, mantle are just ways to drag those devs kicking and screaming into doing better, along with forcing them to utilize gpu's hardware better. Apparently so many devs were complacent shit that when a few wanted something close to a console/better access to hardware, amd provided them with an answer.

Now, develop this on your own or hand everything over to kronos so it's more likely to gain wide support? the answer there is fairly obvious.

>>62065428
Welp that's VLIW for you.
>>62065454
Mantle was literally started by DICE as a way to replicate their expirience developing Bad Company games for consoles.
Though not every dev likes to do it console-style.

>>62065428
I had a 5770 and another 4780, never once encountered a problem outside of the mouse cursor would corrupt every now and then, up through my 280x that was an issue but with the 280x it was never a permanent (till restart) thing.

at least gaming wise, the gpus were fucking great.

at least aside from opencl... my 5770 would work with it, but my 280x never used it once, shit was broke as far as i'm aware with everything passed the 6000 series, dont know about polaris or vega.

can i get a quick rundown on what this all even means

>>62065571
Fun things are fun.

File: 1478735458761.gif (628KB, 516x402px) Image search: [Google]

628KB, 516x402px

>>62060873
WHERE THE FUCK ARE THE DRIVERS RAJA

YOU SAID THERE WOULD BE DRIVERS

>>62065982
DRIVERS? WHAT DRIVERS?
YOU SAW NOTHING.
BUT RADEON PRO SSG.

How many people in amd driver team

>>62066037
Enough to launch one working branch in time.
Well it's a shame it was a Pro branch.

>>62066052
how it compare to Nvidia

>>62066092
RTG is like 1/3 the size of NVIDIA, so their driver team is also probably a third of NVIDIA's.

>>62064616
Soooppaaaaaa

>>62064047
>They're just not going to fuck with architecture specific programming
Yeah, instead they'll just waste their time on Nvidia gameworks instead.

File: 1502746412084.jpg (113KB, 646x1000px) Image search: [Google]

113KB, 646x1000px

AMD has no drivers!

This is not a meme, but a fact!

>>62066859
considering how it's just slapped to engine most of the time without any game integration or QA, they don't waste any time

>>62065571
Less bottleneck. More performance. A year and a half too late.

>>62065293
nevertheless, nvidia tries to implement goyworks to vulkan.

>>62066859
>>62066994
Even better. Nvidia sends out software engineers onsite to help them integrate the engines so 99% of the work is done for the sake of making sure studios keep using it

>>62067202
kek, vega handles gameworks, what are they gonna gimp? if they bait bandwith bottleneck their ass is going on the ground

>>62067274
>what are they gonna gimp?
I really don't know. but it seems they found something.

>>62063128
Underrated