• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

NVIDIA Develops Tile-based Multi-GPU Rendering Technique Called CFR

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
39,268 (8.42/day)
Location
Hyderabad, India
Processor AMD Ryzen 7 2700X
Motherboard ASUS ROG Strix B450-E Gaming
Cooling AMD Wraith Prism
Memory 2x 16GB Corsair Vengeance LPX DDR4-3000
Video Card(s) Palit GeForce RTX 2080 SUPER GameRock
Storage Western Digital Black NVMe 512GB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) Creative Sound Blaster Recon3D PCIe
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Microsoft Sidewinder X4
Software Windows 10 Pro
NVIDIA is invested in the development of multi-GPU, specifically SLI over NVLink, and has developed a new multi-GPU rendering technique that appears to be inspired by tile-based rendering. Implemented at a single-GPU level, tile-based rendering has been one of NVIDIA's many secret sauces that improved performance since its "Maxwell" family of GPUs. 3DCenter.org discovered that NVIDIA is working on its multi-GPU avatar, called CFR, which could be short for "checkerboard frame rendering," or "checkered frame rendering." The method is already secretly deployed on current NVIDIA drivers, although not documented for developers to implement.

In CFR, the frame is divided into tiny square tiles, like a checkerboard. Odd-numbered tiles are rendered by one GPU, and even-numbered ones by the other. Unlike AFR (alternate frame rendering), in which each GPU's dedicated memory has a copy of all of the resources needed to render the frame, methods like CFR and SFR (split frame rendering) optimize resource allocation. CFR also purportedly offers lesser micro-stutter than AFR. 3DCenter also detailed the features and requirements of CFR. To begin with, the method is only compatible with DirectX (including DirectX 12, 11, and 10), and not OpenGL or Vulkan. For now it's "Turing" exclusive, since NVLink is required (probably its bandwidth is needed to virtualize the tile buffer). Tools like NVIDIA Profile Inspector allow you to force CFR on provided the other hardware and API requirements are met. It still has many compatibility problems, and remains practically undocumented by NVIDIA.



View at TechPowerUp Main Site
 
Joined
Aug 20, 2007
Messages
13,129 (2.79/day)
System Name Pioneer
Processor Intel i9 9900k
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ 14-14-14-34-2T
Video Card(s) AMD RX 5700 XT (XFX THICC Ultra III)
Storage Mushkin Pilot-E 2TB NVMe SSD w/ EKWB M.2 Heatsink
Display(s) 55" LG 55" B9 OLED 4K Display
Case Thermaltake Core X31
Audio Device(s) VGA HDMI->Panasonic SC-HTB20/Schiit Modi MB/Asgard 2 DAC/Amp to AKG Pro K7712 Headphones
Power Supply SeaSonic Prime 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 Enterprise (yes, it's legit.)
This was explained back when Crossfire and SLI were making their debut, IIRC. It is not exactly new? Or am I missing something.

In all cases I recall, these techniques sucked because they mandated each gpu still had to render the complete scene geometry, and only helped with fill rate.
 

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
39,268 (8.42/day)
Location
Hyderabad, India
Processor AMD Ryzen 7 2700X
Motherboard ASUS ROG Strix B450-E Gaming
Cooling AMD Wraith Prism
Memory 2x 16GB Corsair Vengeance LPX DDR4-3000
Video Card(s) Palit GeForce RTX 2080 SUPER GameRock
Storage Western Digital Black NVMe 512GB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) Creative Sound Blaster Recon3D PCIe
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Microsoft Sidewinder X4
Software Windows 10 Pro
This was explained back when Crossfire and SLI were making their debut, IIRC. It is not exactly new? Or am I missing something.

In all cases I recall, these techniques sucked because they mandated each gpu still had to render the complete scene geometry, and only helped with fill rate.
Yeah, I too had a lot of deja vu writing this, and had a long chat with W1zzard. Maybe it's some kind of TBR extrapolation for multi-GPU which they finally got right.
 
Joined
Aug 20, 2007
Messages
13,129 (2.79/day)
System Name Pioneer
Processor Intel i9 9900k
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ 14-14-14-34-2T
Video Card(s) AMD RX 5700 XT (XFX THICC Ultra III)
Storage Mushkin Pilot-E 2TB NVMe SSD w/ EKWB M.2 Heatsink
Display(s) 55" LG 55" B9 OLED 4K Display
Case Thermaltake Core X31
Audio Device(s) VGA HDMI->Panasonic SC-HTB20/Schiit Modi MB/Asgard 2 DAC/Amp to AKG Pro K7712 Headphones
Power Supply SeaSonic Prime 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 Enterprise (yes, it's legit.)
Yeah, I too had a lot of deja vu writing this, and had a long chat with W1zzard. Maybe it's some kind of TBR extrapolation for multi-GPU which they finally got right.
I sometimes swear they are selling us the same darn tech with new buzzwords...

Maybe the matrix is just glitching again...
 

W1zzard

Administrator
Staff member
Joined
May 14, 2004
Messages
20,635 (3.50/day)
Processor Core i7-4790K
Memory 16 GB
Video Card(s) GTX 1080
Display(s) 30" 2560x1600 + 19" 1280x1024
Software Windows 7
It seems they are leveraging their (single GPU) tiled-rendering hardware in the silicon to split up the image for CFR, possibly with non 50/50 splits that could possibly dynamically change during runtime to spread the load better.
 
Joined
Feb 3, 2017
Messages
2,435 (1.94/day)
Processor i5-8400
Motherboard ASUS ROG STRIX Z370-I GAMING
Cooling Alpenföhn Black Ridge
Memory 2*16GB DDR4-3200 CL16
Video Card(s) Gainward GeForce RTX 2080 Phoenix
Storage 1TB Samsung 970 Pro, 2TB Intel 660p
Display(s) ASUS PG279Q, Eizo EV2736W
Case Dan Cases A4-SFX
Power Supply Corsair SF600
Mouse Logitech G700
Keyboard Corsair K60
Did either AMD or Nvidia manage to get dynamic splitting to work reliably? As far as I remember all the attempts were eventually ended because solutions came with their own set of problems primarily around uneven frame times and stuttering.

Single-GPU tiled-rendering hardware would be tiles of static size but playing around with the tile count per GPU might work?
 
Joined
Nov 20, 2013
Messages
4,306 (1.77/day)
Location
Kiev, Ukraine
System Name WS#1337
Processor Ryzen 5 1600X
Motherboard Gigabyte x470 AORUS Ultra Gamin
Cooling Xigmatek Scylla 240 AIO
Memory 2x8GB Team T-Force Vulkan DDR4-3000
Video Card(s) MSI RTX 2060 Super Armor OC
Storage Adata SX8200 Pro 1TB
Display(s) Samsung U24E590D (4K/UHD)
Case Chieftec AL-01B-OP
Audio Device(s) ALC1220
Power Supply SeaSonic SSR-550FX (80+ GOLD)
Mouse Logitech G603
Keyboard Zalman K500 modded (Gateron brown)
Software Windows 10, Ubuntu 18.04 LTS
I'm wondering if that new tile-based technique will introduce artifacts in the picture, just like with tearing in SFR?
 
Joined
Jun 28, 2016
Messages
3,595 (2.44/day)
I'm wondering if that new tile-based technique will introduce artifacts in the picture, just like with tearing in SFR?
Not when doing RTRT, which is likely the reason they're developing this (and mostly for game streaming services, not local GPUs).
Did either AMD or Nvidia manage to get dynamic splitting to work reliably? As far as I remember all the attempts were eventually ended because solutions came with their own set of problems primarily around uneven frame times and stuttering.
Well, actually this is a problem that RTRT solves automatically.
In legacy game rendering techniques the input consists of instructions that must be run. There's little control over time - GPU has to complete (almost) everything or there's no image at all.
So the rendering time is a result (not a parameter) and each frame has to wait for the last tile.

In RTRT frame rendering time (i.e. number of rays) is the primary input parameter. It's not relevant how you split the frame. This is perfectly fine:

1574328651433.png
 
Joined
Dec 3, 2012
Messages
406 (0.15/day)
Processor Intel i9 9900K @5Ghz 1.33vlts
Motherboard Gigabyte Z390 Aorus Pro Wi-Fi
Cooling BeQuiet Dark Rock 4
Memory 32GB Corsair Vengeance Pro DDR4 3200Mhz
Video Card(s) EVGA RTX 2080
Storage 512GB Gigabyte Aorus NVMe (Boot) 1Tb Crucial NVMe (Games)
Display(s) LG UK850 27in 4K Freesync/G-Sync/HDR 450
Case Fractal Design Meshify C Windowed (Dark Tint)
Audio Device(s) Corsair HS70 Special Edition Wireless Headphones & 7.1 Sound
Power Supply Corsair RMx 850w Gold
Mouse Corsair Glaive RGB
Keyboard HyperX Alloy Elite Mechanical RGB (Cherry Red)
Software Windows 10 Home
So, Nvidia are now using the technique that UK based PowerVR developed, a company that Nvidia effectively forced out of the PC GPU market with their dirty tricks, in the early 2000's... :rolleyes:
 
Joined
Jun 28, 2016
Messages
3,595 (2.44/day)
So, Nvidia are now using the technique that UK based PowerVR developed, a company that Nvidia effectively forced out of the PC GPU market with their dirty tricks, in the early 2000's... :rolleyes:
Tile-based rendering is a straightforward, natural approach. It's commonly used in non-gaming rendering engines (you see it happening in Cinebench). PowerVR didn't invent it. They may have just been the first to implement it in hardware.
 
Joined
Jul 15, 2006
Messages
784 (0.15/day)
Location
Malaysia
Processor Ryzen 5 3600
Motherboard Gigabyte B450M-S2H
Cooling AMD Wraith Stealth
Memory 2x8GB Samsung OEM B-die @ 3600 17-19-18-36
Video Card(s) Galax GTX 1070 Katana
Storage 120GB Samsung Evo 840 SSD + 2TB Seagate Surveillance 5900rpm
Display(s) 24" LG 24MP59G
Case Mars Gaming MCX Midtower
Audio Device(s) Creative X-Fi Titanium HD + Kurtzweil KS-40A bookshelf
Power Supply Corsair CX750M
Mouse Logitech G402 Hyperion Fury
Keyboard CM Storm QuickFire Pro Cherry MX Black
Software Windows 10 Pro x64
ATi implement Crossfire mode called Super Tiling back in early X800/X850 days. Though it requires a 'Master' card with dedicated compositing engine to combine the input of two cards, plus a dongle.


 
Joined
Jun 3, 2010
Messages
1,067 (0.29/day)
Don't overthink it. We needed SLI in Directx 12, now we have it. The trick is running render targets seperately despite having to run equal postprocess weights throughout the screen therefore it has been difficult to scale up SFR performance. Since there is no unified dynamic lighting load in RTX mode, this might work.
 
Joined
Jun 2, 2017
Messages
2,542 (2.24/day)
System Name Best AMD Computer
Processor AMD TR4 1920X
Motherboard MSI X399 SLI Plus
Cooling Alphacool Eisbaer 420 x2 Noctua XPX Pro TR4 block
Memory Gskill RIpjaws 4 3000MHZ 48GB
Video Card(s) Sapphire Vega 64 Nitro, Gigabyte Vega 64 Gaming OC
Storage 6 x NVME 480 GB, 2 x SSD 2TB, 5TB HDD, 2 TB HDD, 2x 2TB SSHD
Display(s) Acer 49BQ0k 4K monitor
Case Thermaltake Core X9
Audio Device(s) Corsair Void Pro, Logitch Z523 5.1
Power Supply Corsair HX1200!
Mouse Logitech g7 gaming mouse
Keyboard Logitech G510
Software Windows 10 Pro 64 Steam. GOG, Uplay, Origin
Benchmark Scores Firestrike: 24955 Time Spy: 13500
A question for the community; Would a VBIOS update be enough to enable crossfire on the 5700 cards?
 
Joined
Jun 5, 2009
Messages
181 (0.04/day)
Location
Germany
System Name Clevo W650KK1 | Nokia 7 Plus
Processor i5-8400 uVolted | Snapdagon 660
Motherboard Clevo H170 | -
Cooling Stock w/ AC MX-2 | -
Memory 16GB DDR4 2400 | 4GB LPDDR4
Video Card(s) GTX1050Ti uVolted | Adreno 512
Storage 275GB SSD + 500GB SSHD | 64GB int. + 128GB uSD
Display(s) 15.6" 100Hz + LG 34" 75Hz | 6" 18:9 1080p
Case Clevo W650 | Nokia 7 Plus
Power Supply 180W Delta Electronics | 3800mAh Battery
Mouse Fujitsu LX901 Wireless | -
Keyboard Fujitsu LX901 Wireless | GBoard
Software W10 Pro x64 | Android 10
Here's a crazy idea: Why not work with M$/AMD to optimize DX12/Vulkan? Hell Vulkan has an open source SDK, it does not even need special cooperations with anyone.
Also, back when DX12 was launched there was a lot of hype on how good it would perform with multi-GPU setups using async technologies (indipendent chips & manufacturers) https://wccftech.com/dx12-nvidia-amd-asynchronous-multigpu/
Seems like everyone forgot about it...
 
Joined
Nov 6, 2016
Messages
415 (0.31/day)
Location
NJ, USA
System Name Lightbringer
Processor Ryzen 7 2700X
Motherboard Asus ROG Strix X470-F Gaming
Cooling Enermax Liqmax Iii 360mm AIO
Memory G.Skill Trident Z RGB 32GB (8GBx4) 3200Mhz CL 14
Video Card(s) Sapphire RX 5700XT Nitro+
Storage Hp EX950 2TB NVMe M.2, HP EX950 1TB NVMe M.2, Samsung 860 EVO 2TB
Display(s) LG 34BK95U-W 34" 5120 x 2160
Case Lian Li PC-O11 Dynamic (White)
Power Supply BeQuiet Straight Power 11 850w Gold Rated PSU
Mouse Glorious Model O (Matte White)
Keyboard Royal Kludge RK71
Software Windows 10
Would this have anything to do with MCM GPUs? I hope AMD beats Nvidia to an MCM (multiple GPU Chipley, not just a GPU and HBM) GPU, I'm not an AMD fanboy in the least, I just dislike Nvidia and want them to get cut down to size like Intel has been solely due to the fact that Intel getting their ass whooped has benefitted consumers and the same happening to Nvidia would probably benefit us all.
 
Joined
Nov 11, 2004
Messages
6,252 (1.09/day)
Location
Formosa
System Name Overlord Mk MXVI
Processor AMD Ryzen 7 3800X
Motherboard Gigabyte X570 Aorus Master
Cooling Corsair H115i Pro
Memory 32GB Viper Steel 3600 DDR4 @ 3800MHz 16-19-16-19-36
Video Card(s) Gigabyte RTX 2080 Gaming OC 8G
Storage 1TB WD Black NVMe (2018), 2TB Viper VPN100, 1TB WD Blue 3D NAND
Display(s) Asus PG27AQ
Case Corsair Carbide 275Q
Audio Device(s) Corsair Virtuoso SE
Power Supply Corsair RM750
Mouse Logitech G500s
Keyboard Wooting Two
Software Windows 10 Pro
Benchmark Scores https://valid.x86.fr/33u9si
So, Nvidia are now using the technique that UK based PowerVR developed, a company that Nvidia effectively forced out of the PC GPU market with their dirty tricks, in the early 2000's... :rolleyes:
Wow, I thought people had forgotten about them. Nvidia was also trashing them back then and saying tile based rendering sucked...
 
Joined
Oct 4, 2017
Messages
448 (0.44/day)
Location
France
System Name White Rose ( https://imgur.com/gallery/l7Lg4Wj )
Processor RYZEN 7 2700
Motherboard ROG STRIX B450-i
Cooling NOCTUA NH-L12S
Memory Patriot Viper Steel DDR4 4000Mhz 16Go PVS416G400C9K
Video Card(s) ASUS STRIX 1080Ti OC
Storage XPG SX8200 Pro 512 go NVMe + SAMSUNG 850 EVO 500GB
Display(s) SAMSUNG U28D590D 4K 28''
Case Nouvolo Steck
Power Supply CORSAIR SF600
Mouse Logitech G203 Prodigy
Keyboard Ajazz ak33
Software Windows 10 1909
Would this have anything to do with MCM GPUs?
That's exactly what i though ! I don't see them revamping SLI after killing it , to me this has more to do with future MCM designs and might be a good indication that MCM design based gaming GPU from Nvidia is closer than what most of us believe .
 
Joined
Feb 3, 2017
Messages
2,435 (1.94/day)
Processor i5-8400
Motherboard ASUS ROG STRIX Z370-I GAMING
Cooling Alpenföhn Black Ridge
Memory 2*16GB DDR4-3200 CL16
Video Card(s) Gainward GeForce RTX 2080 Phoenix
Storage 1TB Samsung 970 Pro, 2TB Intel 660p
Display(s) ASUS PG279Q, Eizo EV2736W
Case Dan Cases A4-SFX
Power Supply Corsair SF600
Mouse Logitech G700
Keyboard Corsair K60
Nvidia was also trashing them back then and saying tile based rendering sucked...
:)

Edit:
For a bit of background, this was a presentation to OEMs.
Kyro was technically new and interesting but as an actual gaming GPU on desktop cards, it sucked both due to spotty support as well as lackluster performance. It definitely had its bright moments but they were too few and far between. PowerVR could not develop their tech fast enough to compete with Nvidia an ATi at the time.
PowerVR itself went along just fine, the same architecture series was (or is) a strong contender in mobile GPUs.
 
Last edited:
Joined
Mar 13, 2014
Messages
4,481 (1.94/day)
Processor i7 7700k
Motherboard MSI Z270 SLI Plus
Cooling CM Hyper 212 EVO
Memory 2 x 8 GB Corsair Vengeance
Video Card(s) MSI RTX 2070 Super
Storage Samsung 850 EVO 250 GB and WD Black 4TB
Display(s) Dell 27 inch 1440p 144 Hz
Case Corsair Obsidian 750D Airflow Edition
Audio Device(s) Onboard
Power Supply EVGA SuperNova 850 W Gold
Mouse Logitech G502
Keyboard Logitech G105
Software Windows 10
I see MCM as the way forward and not just another version of SLI. For one thing the cost of buying 2 cards must be more expensive than a single card with MCM that could rival the performance of multi-GPU. Granted the MCM will cost more than a regular GPU but with SLI you have to buy 2 of everything. 2 PCBs, 2 GPUs, 2 sets of VRAM, 2 of all the components on the PCB, 2 Shrouds, 2 coolers, 2 boxes, etc
 
Last edited:

eidairaman1

The Exiled Airman
Joined
Jul 2, 2007
Messages
30,443 (6.40/day)
Location
Republic of Texas (True Patriot)
System Name PCGOD
Processor AMD FX 8350@ 5.0GHz
Motherboard Asus TUF 990FX Sabertooth R2 2901 Bios
Cooling Scythe Ashura, 2×BitFenix 230mm Spectre Pro LED (Blue,Green), 2x BitFenix 140mm Spectre Pro LED
Memory 16 GB Gskill Ripjaws X 2133 (2400 OC, 10-10-12-20-20, 1T, 1.65V)
Video Card(s) AMD Radeon 290 Sapphire Vapor-X
Storage Samsung 840 Pro 256GB, WD Velociraptor 1TB
Display(s) NEC Multisync LCD 1700V (Display Port Adapter)
Case AeroCool Xpredator Evil Blue Edition
Audio Device(s) Creative Labs Sound Blaster ZxR
Power Supply Seasonic 1250 XM2 Series (XP3)
Mouse Roccat Kone XTD
Keyboard Roccat Ryos MK Pro
Software Windows 7 Pro 64
They are trying to justify the rtx lineup lol
 
Joined
Apr 8, 2010
Messages
563 (0.15/day)
Processor Intel Core i5 8400
Motherboard Gigabyte Z370N-Wifi
Cooling Silverstone AR05
Memory Micron Crucial 16GB DDR4-2400
Video Card(s) Gigabyte GTX1080 G1 Gaming 8G
Storage Micron Crucial MX300 275GB
Display(s) Dell U2415
Case Silverstone RVZ02B
Power Supply Silverstone SSR-SX550
Keyboard Ducky One Red Switch
Software Windows 10 Pro 1909
Also, back when DX12 was launched there was a lot of hype on how good it would perform with multi-GPU setups using async technologies (indipendent chips & manufacturers) https://wccftech.com/dx12-nvidia-amd-asynchronous-multigpu/
Seems like everyone forgot about it...
With good reason. In order for it to really work, the programmer would need to optimize every time for a specific system. If I am writing some GPGPU software for a solution that I'm selling bundled with a computer (which hardware I get to specify), it could be worth the effort. For games that can have any combination of rendering hardware? Eh, no thanks. The world is just much simpler when we just have to think about 2 exact same gpu to balance the workload equally. Even then we get cans of worms thrown at our faces from time to time.
 
Joined
Nov 4, 2005
Messages
10,551 (1.97/day)
System Name MoFo 2
Processor AMD PhenomII 1100T @ 4.2Ghz
Motherboard Asus Crosshair IV
Cooling Swiftec 655 pump, Apogee GT,, MCR360mm Rad, 1/2 loop.
Memory 8GB DDR3-2133 @ 1900 8.9.9.24 1T
Video Card(s) HD7970 1250/1750
Storage Agility 3 SSD 6TB RAID 0 on RAID Card
Display(s) 46" 1080P Toshiba LCD
Case Rosewill R6A34-BK modded (thanks to MKmods)
Audio Device(s) ATI HDMI
Power Supply 750W PC Power & Cooling modded (thanks to MKmods)
Software A lot.
Benchmark Scores Its fast. Enough.
It seems they are leveraging their (single GPU) tiled-rendering hardware in the silicon to split up the image for CFR, possibly with non 50/50 splits that could possibly dynamically change during runtime to spread the load better.

A good idea with complexity, how is full screen AA processed if only half the resources are on each card?

Or could this possibly be a Zen like chiplet design to save money and loss on the newest node?

NVlink as the fabric for communication, if only half the resources are actually required maybe I'm out in left field but put 12GB or 6GB for each chiplet and interleave the memory.
 
Joined
Feb 3, 2017
Messages
2,435 (1.94/day)
Processor i5-8400
Motherboard ASUS ROG STRIX Z370-I GAMING
Cooling Alpenföhn Black Ridge
Memory 2*16GB DDR4-3200 CL16
Video Card(s) Gainward GeForce RTX 2080 Phoenix
Storage 1TB Samsung 970 Pro, 2TB Intel 660p
Display(s) ASUS PG279Q, Eizo EV2736W
Case Dan Cases A4-SFX
Power Supply Corsair SF600
Mouse Logitech G700
Keyboard Corsair K60
A good idea with complexity, how is full screen AA processed if only half the resources are on each card?
Or could this possibly be a Zen like chiplet design to save money and loss on the newest node?
NVlink as the fabric for communication, if only half the resources are actually required maybe I'm out in left field but put 12GB or 6GB for each chiplet and interleave the memory.
AA would probably be one of the postprocessing methods done at the end of rendering a frame.

You can't get off with shared memory like that. You are still going to need a sizable part of assets accessible by both/all GPUs. Any memory far away from GPU is evil and even a fast interconnect like NVLink won't replace local memory. GPUs are very bandwidth-constrained so sharing memory access through something like Zen2's IO die is not likely to work on GPUs at this time. With big HBM cache for each GPU, maybe, but that is effectively still each GPU having its own VRAM :)

Chiplet design has been the end goal for a while and all the GPU makers have been trying their hand on this. So far, unsuccessfully. As @Apocalypsee already noted - even tiled distribution of work is not new.
 
Joined
Nov 11, 2004
Messages
6,252 (1.09/day)
Location
Formosa
System Name Overlord Mk MXVI
Processor AMD Ryzen 7 3800X
Motherboard Gigabyte X570 Aorus Master
Cooling Corsair H115i Pro
Memory 32GB Viper Steel 3600 DDR4 @ 3800MHz 16-19-16-19-36
Video Card(s) Gigabyte RTX 2080 Gaming OC 8G
Storage 1TB WD Black NVMe (2018), 2TB Viper VPN100, 1TB WD Blue 3D NAND
Display(s) Asus PG27AQ
Case Corsair Carbide 275Q
Audio Device(s) Corsair Virtuoso SE
Power Supply Corsair RM750
Mouse Logitech G500s
Keyboard Wooting Two
Software Windows 10 Pro
Benchmark Scores https://valid.x86.fr/33u9si
:)

Edit:
For a bit of background, this was a presentation to OEMs.
Kyro was technically new and interesting but as an actual gaming GPU on desktop cards, it sucked both due to spotty support as well as lackluster performance. It definitely had its bright moments but they were too few and far between. PowerVR could not develop their tech fast enough to compete with Nvidia an ATi at the time.
PowerVR itself went along just fine, the same architecture series was (or is) a strong contender in mobile GPUs.
It wasn't that bad, I tested the cards myself at the time, in fact, I'm still on good terms with Imagination Technologies PR director, who at the time used to come by the office with things to test. But yes, they did have drivers issues, which was one of the big flaws, but performance wasn't as terrible as that old Nvidia presentation makes it out to be.
 

eidairaman1

The Exiled Airman
Joined
Jul 2, 2007
Messages
30,443 (6.40/day)
Location
Republic of Texas (True Patriot)
System Name PCGOD
Processor AMD FX 8350@ 5.0GHz
Motherboard Asus TUF 990FX Sabertooth R2 2901 Bios
Cooling Scythe Ashura, 2×BitFenix 230mm Spectre Pro LED (Blue,Green), 2x BitFenix 140mm Spectre Pro LED
Memory 16 GB Gskill Ripjaws X 2133 (2400 OC, 10-10-12-20-20, 1T, 1.65V)
Video Card(s) AMD Radeon 290 Sapphire Vapor-X
Storage Samsung 840 Pro 256GB, WD Velociraptor 1TB
Display(s) NEC Multisync LCD 1700V (Display Port Adapter)
Case AeroCool Xpredator Evil Blue Edition
Audio Device(s) Creative Labs Sound Blaster ZxR
Power Supply Seasonic 1250 XM2 Series (XP3)
Mouse Roccat Kone XTD
Keyboard Roccat Ryos MK Pro
Software Windows 7 Pro 64
It wasn't that bad, I tested the cards myself at the time, in fact, I'm still on good terms with Imagination Technologies PR director, who at the time used to come by the office with things to test. But yes, they did have drivers issues, which was one of the big flaws, but performance wasn't as terrible as that old Nvidia presentation makes it out to be.
Of course nv will commit libel just like intel.
 
Top