• Register
  • TOS
  • Privacy
  • @NeoGAF

artist
Banned
(02-25-2013, 09:51 PM)
Via SolidPain;

Originally Posted by SolidPain

Probably posted but oh well Orbis GPU compute, queues and pipelines

MikeE21286
Member
(02-25-2013, 09:52 PM)
MikeE21286's Avatar
Translation-GAF. What does it mean!?!!?!
Freki
Member
(02-25-2013, 09:53 PM)
Freki's Avatar
Could we all please do not derail this thread by silly one liners and memes - thank you!

edit:

as a negative example:

Originally Posted by Tokyo Rain

It means we need 16GB GDDR5 on the next Xbox.

Originally Posted by Medalion

8GB GDDR5 of RAM, it's all that matters...ALL.

Last edited by Freki; 02-25-2013 at 09:56 PM.
Tokyo Rain
Member
(02-25-2013, 09:53 PM)
Tokyo Rain's Avatar

Originally Posted by MikeE21286

Translation-GAF. What does it mean!?!!?!

It means we need 16GB GDDR5 on the next Xbox.
Medalion
Banned
(02-25-2013, 09:54 PM)
Medalion's Avatar

Originally Posted by MikeE21286

Translation-GAF. What does it mean!?!!?!

8GB GDDR5 of RAM, it's all that matters...ALL.
codhand
Member
(02-25-2013, 09:55 PM)
codhand's Avatar

.
weekend_warrior
Junior Member
(02-25-2013, 09:55 PM)
weekend_warrior's Avatar

Originally Posted by MikeE21286

Translation-GAF. What does it mean!?!!?!

It's means it's going to put all that RAM to good use!
artist
Banned
(02-25-2013, 09:56 PM)
Confirms the 8 ACE rumor from earlier today, which is good.
mrklaw
MrArseFace
(02-25-2013, 09:57 PM)
mrklaw's Avatar
It looks like a pretty interesting customisation, would be interested to hear comments from those that can better understand it.

What is VShell, is that like the OS/system? Is it reserving GPU resources, or is the ring just allowing it to hold onto things ready to flip across when you hit the OS button for instance
Perkel
Banned
(02-25-2013, 09:58 PM)
Seriously that RAM talk everywhere but not in ram thread is super annoying. Here we have some info about PS4 GPU and 3 out of 6 post are some shitty GDDR5 mame.

Looks like Cerny was right saying GPU was customized for compute. Exciting stuff if we will have proper physic acceleration in GPU.

Hair cloth particles "here we go !"
shinobi602
(02-25-2013, 09:59 PM)
shinobi602's Avatar
Eh, I only know the basics of hardware. Tech GAF, what do we have here?
Globox_82
Banned
(02-25-2013, 09:59 PM)
Globox_82's Avatar

Originally Posted by artist

Confirms the 8 ACE rumor from earlier today, which is good.

so 8 aces is secret jizz load?
strafer
member
(02-25-2013, 09:59 PM)
strafer's Avatar
lol, there is an actual site named VGleaks, I thought it was something you just wrote in the title.
Kaako
Felium Defensor
(02-25-2013, 10:00 PM)
Kaako's Avatar
Hey developers, how do you feel about this new diagram detailing the pipelines of the Orbis GPU?
Freki
Member
(02-25-2013, 10:01 PM)
Freki's Avatar

Each pipeline has 8 queues of a total of 64
Replaces the 2 compute-only queues and pipelines on R10XX

So more Queues means better load balancing? Am I reading this right?
orientalNoodle
Member
(02-25-2013, 10:02 PM)
orientalNoodle's Avatar
Can some one simplify that diagram down to just a few blocks for easy understanding?
Biggzy
Member
(02-25-2013, 10:02 PM)
Biggzy's Avatar

Originally Posted by Perkel

Seriously that RAM talk everywhere but not in ram thread is super annoying. Here we have some info about PS4 GPU and 3 out of 6 post are some shitty GDDR5 mame.

Looks like Cerny was right saying GPU was customized for compute. Exciting stuff if we will have proper physic acceleration in GPU.

Hair cloth particles "here we go !"

You can quite clearly see it in Knack.
B.O.O.M
Member
(02-25-2013, 10:03 PM)
B.O.O.M's Avatar
Really would appreciate a simple summary of what this means from someone who understands this
artist
Banned
(02-25-2013, 10:03 PM)
This also means that we can finally rest that 14+4 split theory.

Originally Posted by Globox_82

so 8 aces is secret jizz load?

This isnt Durango, so no.
LabouredSubterfuge
Member
(02-25-2013, 10:03 PM)
LabouredSubterfuge's Avatar
Someone sound the Durante horn!!
Kinitari
Black Canada Mafia
(02-25-2013, 10:03 PM)
Kinitari's Avatar
I should really just dedicate a day to understanding 1/10th of what all this stuff means, you know really sit down and learn. Well that's not fair, I understand a lot of what it means, but not enough to really get a full picture.

One day.
demolitio
Member
(02-25-2013, 10:04 PM)
demolitio's Avatar
I'm just excited to see the evolution of physics. I'm going to have a hard time not destroying shit in games that have good physics. :D
Kenka
Member
(02-25-2013, 10:04 PM)
Kenka's Avatar
I summon brain_stew, blu, Durante and Thraktor.

Last edited by Kenka; 02-25-2013 at 10:06 PM.
gofreak
GAF's Bob Woodward
(02-25-2013, 10:04 PM)
gofreak's Avatar
This is so low level... it is a much more detailed view of the ACE stuff rumoured before though. I think 'better/easier utilisation during mixed compute/graphics work' is still the 20,000ft version here.
GoldPunch
Junior Member
(02-25-2013, 10:04 PM)
GoldPunch's Avatar
Still orbis?

It's playstation 4:(
Biggzy
Member
(02-25-2013, 10:05 PM)
Biggzy's Avatar

Originally Posted by demolitio

I'm just excited to see the evolution of physics. I'm going to have a hard time not destroying shit in games that have good physics. :D

Destruction in Battlefield 4 think about it.
darkwing
Member
(02-25-2013, 10:05 PM)
darkwing's Avatar

Originally Posted by Biggzy

You can quite clearly see it in Knack.

you can see it too in the Havok demo
Perkel
Banned
(02-25-2013, 10:05 PM)

Originally Posted by Biggzy

You can quite clearly see it in Knack.

With all due respect to Knack it didn't push that much particles on screen with physic in trailer nor it had cloth or hair physic.
sangreal
Member
(02-25-2013, 10:06 PM)
sangreal's Avatar

Originally Posted by artist

This also means that we can finally rest that 14+4 split theory.

While it would seem so, that also came from VGLeaks (and Eurogamer). Anyways, besides the official specs and this article, ERP also shit on that idea a few days ago
Biggzy
Member
(02-25-2013, 10:06 PM)
Biggzy's Avatar

Originally Posted by darkwing

you can see it too in the Havok demo

I used Knack as an example because it is an actual game.

Originally Posted by Perkel

With all due respect to Knack it didn't push that much particles on screen with physic in trailer not it had cloth or hair physic.

No. But the way the character dissembled and resembled all his pieces was definitely influenced by the GPU. Of course we can expect more down the line, but for a taster it isn't a bad start.
Last edited by Biggzy; 02-25-2013 at 10:08 PM.
Osiris
Member
(02-25-2013, 10:06 PM)
Osiris's Avatar

Originally Posted by Freki

So more Queues means better load balancing? Am I reading this right?

Pretty much, these don't add performance directly, they make your use of resources more efficient by reducing stalls, keeping the CU's fed and speeding up context switching between general compute / gfx workloads.
SirIgbyCeaser
Banned
(02-25-2013, 10:06 PM)
SirIgbyCeaser's Avatar

- High Priority Graphics (HP3D) ring and pipeline

New for Liverpool
Same as GFX pipeline except no compute capabilities
For exclusive use by VShell

Is this AMD's hardware solution for 3D/stereoscopic gaming?
Kaako
Felium Defensor
(02-25-2013, 10:06 PM)
Kaako's Avatar

Originally Posted by Biggzy

Destruction in Battlefield 4 think about it.

I will level everywhere I set my foot on. Belieee that.
sangreal
Member
(02-25-2013, 10:08 PM)
sangreal's Avatar

Originally Posted by SirIgbyCeaser

Is this AMD's hardware solution for 3D/stereoscopic gaming?

It sounded to me like something for the OS, etc to render without having to wait for the game but I don't know shit. So basically if there was something in the HP DRAW and the GFX DRAW queues, the "Arbitration" would give priority to the HP DRAW
benny_a
extra source of jiggaflops
(02-25-2013, 10:09 PM)
benny_a's Avatar

Originally Posted by Osiris

Pretty much, these don't add performance directly, they make your use of resources more efficient by reducing stalls, keeping the CU's fed and speeding up context switching between general compute / gfx workloads.

There was talk about 100% efficiency GPU. Can anyone describe that this leak means in that context and what 100% efficiency means?

I assume it has something to do with memory bandwidth and FLOPs and having these things be adjusted so that neither part has an obvious bottle neck?
artist
Banned
(02-25-2013, 10:09 PM)
In simpler terms, the CPU is dividing the calls based on the type (graphics vs compute) and feeding the GPU accordingly. The compute tasks get further funneled to the units that are idle and get better utilization. 8x8 granularity is a lot better versus 2x2 approach of GCN.

The graphics pipeline is obviously higher priority and doesnt need the scheduling of ACEs to distribute the load.

edit: It also looks like each ACE can also interface with the DMA directly.
Last edited by artist; 02-25-2013 at 10:12 PM.
Sentry
Still Alive
(02-25-2013, 10:09 PM)
Sentry's Avatar

Originally Posted by gofreak

This is so low level... it is a much more detailed view of the ACE stuff rumoured before though. I think 'better/easier utilisation during mixed compute/graphics work' is still the 20,000ft version here.

AgentP
Banned
(02-25-2013, 10:09 PM)
It is kind of hard to do a 1:1 with the two flow charts. I hope someone can make heads or tails from these.
Biggzy
Member
(02-25-2013, 10:11 PM)
Biggzy's Avatar

Originally Posted by benny_a

There was talk about 100% efficiency GPU. Can anyone describe that this leak means in that context and what 100% efficiency means?

I assume it has something to do with memory bandwidth and FLOPs and having these things be adjusted so that neither part has an obvious bottle neck?

Think of it as the GPU is able to reach it's full potential.
Lovely Salsa
Banned
(02-25-2013, 10:11 PM)
IS the GPU equal to 7870? Or is it close to it?
Biggzy
Member
(02-25-2013, 10:12 PM)
Biggzy's Avatar

Originally Posted by Lovely Salsa

IS the GPU equal to 7870? Or is it close to it?

Somewhere between a 7850 and a 7870, closer to a 7850 though I would say.
demolitio
Member
(02-25-2013, 10:12 PM)
demolitio's Avatar

Originally Posted by Biggzy

Destruction in Battlefield 4 think about it.

Yea, that's actually one of the reasons I want BF5 to return to WWII. True destruction in a war that was pretty much all about destruction would be epic, especially if they brought naval battles back. Imagine a destroyer shelling a village along the coast with all of its weapons...MMMmmmm.

I hope more MP games are willing to take the risk on destruction and realize the potential instead of just thinking it would ruin the flow of a map.
tipoo
Banned
(02-25-2013, 10:12 PM)
Do we really have to make the RAM thing the next Cell meme?

So it doesn't look exactly like the GCN architecture, a few enhancements in there. I wonder if we're looking at a preview of the GCN 2.0? Like how the 360 GPU had some HD2000 series features.
Elios83
Member
(02-25-2013, 10:14 PM)
These things are really advanced and specific, but basically it confirms that there are specific customizations to the standard GCN cores aimed at balancing the workload so that everything is more efficient.
Nirolak
Mrgrgr
(02-25-2013, 10:15 PM)
Nirolak's Avatar

Originally Posted by Sentry

If you're running both compute work (physics, animation, etc) and graphics work (rendering, etc) at the same time, this helps that not get bogged down with each other since they're not exactly the same type of workload.
gofreak
GAF's Bob Woodward
(02-25-2013, 10:15 PM)
gofreak's Avatar

Originally Posted by benny_a

There was talk about 100% efficiency GPU. Can anyone describe that this leak means in that context and what 100% efficiency means?

There's no such thing.

Or no such one thing. And you can verge into semantics here. For example, an algorithm might be considered by some to be '100% efficient' when it's as optimised as it can be, though if you were looking at compute resources its executing on, it may not be firing all cylinders all of the time.

So it depends what you're measuring by.

What 'improved efficiency' means in relation to this is, that by having more threads ready, the gpu can switch faster to another thread if the current one stalls, and switch more readily between graphics and compute threads. Apparently with regular GCN there was a certain non-negligible penalty in doing that kind of switching between different workloads. So much so that AMD recommended doing compute and graphics on separate chips inside a system where available.

Or at least that's one takeaway, I think. It doesn't mean '100% efficiency' though. It's 'just' another tool for potentially improving utilisation and thus helping code thrown at the GPU finish faster.
benny_a
extra source of jiggaflops
(02-25-2013, 10:16 PM)
benny_a's Avatar

Originally Posted by Biggzy

Think of it as the GPU is able to reach it's full potential.

I was hoping for more insight in how that is calculated because I think 100% efficiency is obvious, but how one gets to make that statement is not.

Originally Posted by gofreak

There's no such thing.

It came up with the Durango GPU. It's at ~1.2Tflops but 100% efficiency and the 360 was rated at 60% efficiency.
Durante
I'm taking it FROM here, so says Mr. Stewart
(02-25-2013, 10:16 PM)
Durante's Avatar
This is really interesting, probably the most interesting thing on VGLeaks so far.
It should allow better GPU utilization, especially with mixed graphics/compute workloads. What I don't understand yet is how the load balancing between the individual queues/pipelines will be performed or controlled.

Originally Posted by SirIgbyCeaser

Is this AMD's hardware solution for 3D/stereoscopic gaming?

Nah, it has nothing to do with that. It appears to allow the OS higher priority access to the GPU.
Lovely Salsa
Banned
(02-25-2013, 10:17 PM)

Originally Posted by Biggzy

Somewhere between a 7850 and a 7870, closer to a 7850 though I would say.

Whats the best GPU a console manufacturer could use for a fall 2013 release? Would 7950 be possible?
Biggzy
Member
(02-25-2013, 10:18 PM)
Biggzy's Avatar

Originally Posted by benny_a

I was hoping for more insight in how that is calculated because I think 100% efficiency is obvious, but how one gets to make that statement is not.

I am no tech expert, but making sure the GPU is not stalling and doing nothing for a number of cycles is probably one way of increasing efficiency. I am sure someone will be able to give you a far better answer than that.

Thread Tools