New AMD Radeon RX Vega Details Surface In Linux Patch - 4096 Shader procs

Published by

Click here to post a comment for New AMD Radeon RX Vega Details Surface In Linux Patch - 4096 Shader procs on our message forum
https://forums.guru3d.com/data/avatars/m/262/262239.jpg
That doesnt look like its going to beat a 1080ti sadly 🙁 I still hope it can but these specs feel underwhelming at first glance 🙁
https://forums.guru3d.com/data/avatars/m/198/198862.jpg
That doesnt look like its going to beat a 1080ti sadly 🙁 I still hope it can but these specs feel underwhelming at first glance 🙁
It does not need to beat 1080ti. It needs to offer similiar performance at lower price.
https://forums.guru3d.com/data/avatars/m/270/270041.jpg
Looking at that spec sheet, it is like a sli 570 XD Might cry a little if this ends up being the case, i highly doubt it. but it would be funny for us to wait so long for a duo card
data/avatar/default/avatar02.webp
That doesnt look like its going to beat a 1080ti sadly 🙁 I still hope it can but these specs feel underwhelming at first glance 🙁
12.5 Tflops, HBM, double the amount of pretty much everything, ~1.5ghz, over 1/2 a TERAbyte of memory bandwidth! Sounds pretty good to me, hopefully it is priced nicely. If it is, it'll likely replace these two 970's.
data/avatar/default/avatar27.webp
So it has the same graphic computational resource as Fiji, suppose it still retain the same arch in essence. If only we have clockspeed and memory config it carries any well informed would gives better guesstimate. But at this point, I dare guess it'll be somewhere at 1070 level considering.
https://forums.guru3d.com/data/avatars/m/80/80129.jpg
So it has the same graphic computational resource as Fiji, suppose it still retain the same arch in essence. If only we have clockspeed and memory config it carries any well informed would gives better guesstimate. But at this point, I dare guess it'll be somewhere at 1070 level considering.
Why 1070 level? It's 12.5 Tflops, which puts it's theoretical maximum slightly above a Titan XP. I doubt AMD will get everything out of it, especially in DX11 - but it will almost definitely trade blows with the Ti/XP in DX12 and may take some titles in DX11 too. I also think it's going to be priced at $650. There are already Ti's selling for $680 - I expect those prices to drop even further after Vega launches.
https://forums.guru3d.com/data/avatars/m/244/244337.jpg
That doesnt look like its going to beat a 1080ti sadly 🙁 I still hope it can but these specs feel underwhelming at first glance 🙁
You must have been living in a dream world if You expecrted it to beat 1080ti... It will be bit faster than 1080 in dx11 but in DX12 well that where Vega should shine since Pascal is not a dx12 card 🙂 All depends if AMD wont go STUPID with pricinf like they dis with Fury X...
https://forums.guru3d.com/data/avatars/m/80/80129.jpg
You must have been living in a dream world if You expecrted it to beat 1080ti... It will be bit faster than 1080 in dx11 but in DX12 well that where Vega should shine since Pascal is not a dx12 card 🙂 All depends if AMD wont go STUPID with pricinf like they dis with Fury X...
Weird considering I play a number of DX12 games on my Pascal card.
https://forums.guru3d.com/data/avatars/m/164/164033.jpg
Weird considering I play a number of DX12 games on my Pascal card.
Must be that nvidia drivers are emulating AMD card via drivers surely! Well if the clock speeds are on point for this it should be quite a bit faster then Fury X was. I have no clue where people get 1070 level. Considering Fury X is around that level especially in dx12 and so on.
https://forums.guru3d.com/data/avatars/m/198/198862.jpg
Weird considering I play a number of DX12 games on my Pascal card.
Its only an emulation, haha. Sorry i know you hate that word. 😀
https://forums.guru3d.com/data/avatars/m/259/259654.jpg
You must have been living in a dream world if You expecrted it to beat 1080ti...
Why? The way it looks it probably be very close. In AMD-friendly titles it most likely will. The die size is also interesting, a tiny bit larger than the 1080Ti. I wonder what that means for the future.
data/avatar/default/avatar14.webp
At least it is good to see that the prediction for Vega10 have been spot on, with the 4096 shader processors and 8GB memory, really it should be good if they can keep the clocks high enough and the leakage low.
Preach Hilbert! Ppl need to understand that the only reason why Nvidia can clocks the bejesus out of the Pascal is the low leakage and optimized perf/Watt onchip operations. That is the reason behind the "clock gap". I can already hear them. - Oh but we don't care about our power-bill. - Physics care, u bozo 😀
data/avatar/default/avatar04.webp
I really think AMD bottleneck their own cards with low amount of ROPS with too many TMU there need to be a better balance, or they really betting hard on DX12 and Async to make up for it. I Thought the big boy would have atleast 6144 shaders and 128ROPS +320TMU now that would be a 1080TI killer...
https://forums.guru3d.com/data/avatars/m/259/259654.jpg
I really think AMD bottleneck their own cards with low amount of ROPS with too many TMU there need to be a better balance, or they really betting hard on DX12 and Async to make up for it.
It's really triangle throughput and single-threaded submitted draw calls that are bottlenecking AMD cards. Polaris has almost fixed the triangle part, Vega will do even more for that. My personal question is about the new memory controller and command processor. If it manages to feed the more flexible SIMDs properly, we might even have an efficiency surprise in our hands. I still believe that the initial benchmarks will disappoint, but this will end up to be the card to get, as is tradition.
data/avatar/default/avatar30.webp
I really think AMD bottleneck their own cards with low amount of ROPS with too many TMU there need to be a better balance, or they really betting hard on DX12 and Async to make up for it.
Nope. AMD knows their ****. You think these guys are that clueless? To make a utterly unbalanced product. Polaris does show some dips compared to Hawaii at higher res, but its minimal really. And could easily be explained by Polaris bandwidth deficit.
https://forums.guru3d.com/data/avatars/m/242/242395.jpg
sli 570 XD
What does this mean? That's a card name?
data/avatar/default/avatar21.webp
Just because it has a same arrangement of shaders, TMU and ROP units it doesn't mean that VEGA = FIJI It's also not just Fiji with higher clock and smaller node. Vega has a new scheduler, new pixel and vertex engine, tile based rasterizer, new more flexible compute unit, new memory controller... That's about the same absurd as saying Volkswagen Up! with 1.0 engine is the same as Mitsubishi Lancer Evo X with a 2.0 Turbo engine, just because they both have 4 cylinders.
https://forums.guru3d.com/data/avatars/m/54/54823.jpg
You must have been living in a dream world if You expecrted it to beat 1080ti... It will be bit faster than 1080 in dx11 but in DX12 well that where Vega should shine since Pascal is not a dx12 card 🙂 All depends if AMD wont go STUPID with pricinf like they dis with Fury X...
AMD gains a a bit from async compute, more than nVIDIA in most titles. The only software where nVIDIA's gains are large is TimeSpy. Which is why that benchmark is a write-off to me. AMD was honest about its comparison even to maxwell cards, when it came to DX12, neither cards support all the APIs features.
https://forums.guru3d.com/data/avatars/m/130/130124.jpg
Judging by the specs it should knock the f*ck out the 1080ti. If that's not the case then i ****ing pity AMD with their GPU lineup. Why would you invest this time and money into a GPU that's as fast as rx480 crossfire.:bang::bang:
data/avatar/default/avatar26.webp
Judging by the specs it should knock the f*ck out the 1080ti. If that's not the case then i ****ing pity AMD with their GPU lineup. Why would you invest this time and money into a GPU that's as fast as a dual rx580.:bang::bang:
Well its still pretty sad, that it takes them 1 year after the release of the 1080 just to match it as well.