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

TSMC to Bring 3D Stacked Wafers to Complex Silicon Designs, Such as GPUs

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,297 (7.53/day)
Location
Hyderabad, India
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard ASUS ROG Strix B450-E Gaming
Cooling DeepCool Gammax L240 V2
Memory 2x 8GB G.Skill Sniper X
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) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
TSMC is close to adapt 3D stacked silicon wafers to complex silicon designs, such as graphics processors, using its new proprietary Wafer-on-Wafer (WoW) Advanced Packaging technology, which will be introduced with its 7 nm+ and 5 nm nodes. 3D stacked silicon fabrication is currently only implemented on "less complex" silicon designs, such as NAND flash, which don't run anywhere near as hot as complex designs ASIC designs, such as GPUs or CPUs. In its current form, TSMC achieved 2-layer stacks, in which two silicon layers that are "mirror images" of each other (for perfect alignment), sandwich bonding layers, through which pins for the upper layer pass through.

The bonding of the two layers is where the bulk of TSMC's innovations and "secret sauces" lie. For 3D NAND flash, multiple pancaked dies are wired out through their edges. You don't need as many pins to talk to a NAND flash die, as say a GPU die. For complex dies, designers have to pass thousands of pins through the "bottom layer," the connecting substrate, and eventually to the "top layer." The bottom layer hence is bumped out on both ends, one side interfacing with the package substrate for both dies, and the top side serving as a sort of substrate for the top die. This innovation is what TSMC calls "thru-silicon-vias" or TSVs.



WoW (wafer on wafer) is different from package-on-package or PoP (the way SoCs and DRAM packages are mated inside cellphones), in which two complete packages are wired out either concentrically on the PCB, or with pins on top of the SoC package interfacing with the DRAM package. The DRAM package needs fewer pins than the SoC, so it's more convenient having that on top. A WoW die sits inside a single package, and offers double the die area of a planar single-layer die. The bonding layers, the other key innovation of TSMC, not only helps mate the two packages, but also helps with thermal conductivity. There's division of labor between the two dies. The bottom layer has to bear the wiring of both dies, while the top layer has to dissipate heat from both dies. In this regard, the top layer gets some help from the fact that it has blank areas (where the bottom layer would normally have bumps to the package substrate).

View at TechPowerUp Main Site
 
Joined
Sep 17, 2014
Messages
22,666 (6.05/day)
Location
The Washing Machine
System Name Tiny the White Yeti
Processor 7800X3D
Motherboard MSI MAG Mortar b650m wifi
Cooling CPU: Thermalright Peerless Assassin / Case: Phanteks T30-120 x3
Memory 32GB Corsair Vengeance 30CL6000
Video Card(s) ASRock RX7900XT Phantom Gaming
Storage Lexar NM790 4TB + Samsung 850 EVO 1TB + Samsung 980 1TB + Crucial BX100 250GB
Display(s) Gigabyte G34QWC (3440x1440)
Case Lian Li A3 mATX White
Audio Device(s) Harman Kardon AVR137 + 2.1
Power Supply EVGA Supernova G2 750W
Mouse Steelseries Aerox 5
Keyboard Lenovo Thinkpad Trackpoint II
VR HMD HD 420 - Green Edition ;)
Software W11 IoT Enterprise LTSC
Benchmark Scores Over 9000
Interesting, very curious how these will handle the heat in the end and whether any form of overclocking is still going to be in the cards. Getting the idea that the TDP allowance is going to lose a lot of headroom...
 
Joined
Feb 8, 2012
Messages
3,014 (0.64/day)
Location
Zagreb, Croatia
System Name Windows 10 64-bit Core i7 6700
Processor Intel Core i7 6700
Motherboard Asus Z170M-PLUS
Cooling Corsair AIO
Memory 2 x 8 GB Kingston DDR4 2666
Video Card(s) Gigabyte NVIDIA GeForce GTX 1060 6GB
Storage Western Digital Caviar Blue 1 TB, Seagate Baracuda 1 TB
Display(s) Dell P2414H
Case Corsair Carbide Air 540
Audio Device(s) Realtek HD Audio
Power Supply Corsair TX v2 650W
Mouse Steelseries Sensei
Keyboard CM Storm Quickfire Pro, Cherry MX Reds
Software MS Windows 10 Pro 64-bit
Interesting, very curious how these will handle the heat in the end and whether any form of overclocking is still going to be in the cards. Getting the idea that the TDP allowance is going to lose a lot of headroom...
Fill the whole bottom floor with cache, and put the rest of the cpu on top? ... or with gpus, memory controllers, rops and cache on the bottom floor, shader cores on the top
 
Last edited:

blindwrite

New Member
Joined
May 3, 2018
Messages
1 (0.00/day)
It looks more like Hybrid Bonding and TSV combined (both already largely proven). Nice to see support form EDA vendors
 
Joined
Jul 13, 2016
Messages
3,329 (1.08/day)
Processor Ryzen 7800X3D
Motherboard ASRock X670E Taichi
Cooling Noctua NH-D15 Chromax
Memory 32GB DDR5 6000 CL30
Video Card(s) MSI RTX 4090 Trio
Storage Too much
Display(s) Acer Predator XB3 27" 240 Hz
Case Thermaltake Core X9
Audio Device(s) Topping DX5, DCA Aeon II
Power Supply Seasonic Prime Titanium 850w
Mouse G305
Keyboard Wooting HE60
VR HMD Valve Index
Software Win 10
Fill the whole bottom floor with cache, and put the rest of the cpu on top? ... or with gpus, memory controllers, rops and cache on the bottom floor, shader cores on the top

Latency is an issue. You cannot put cache on a separate die, which requires extremely low latency. AMD experiences up to 250ns of latency die to die. For something as commenly used as cache, putting it on a seperate die would completely destroy performance. There is a reason cache is right next to the CPU. Ditto goes for GPUs as well.
 
Joined
Feb 8, 2012
Messages
3,014 (0.64/day)
Location
Zagreb, Croatia
System Name Windows 10 64-bit Core i7 6700
Processor Intel Core i7 6700
Motherboard Asus Z170M-PLUS
Cooling Corsair AIO
Memory 2 x 8 GB Kingston DDR4 2666
Video Card(s) Gigabyte NVIDIA GeForce GTX 1060 6GB
Storage Western Digital Caviar Blue 1 TB, Seagate Baracuda 1 TB
Display(s) Dell P2414H
Case Corsair Carbide Air 540
Audio Device(s) Realtek HD Audio
Power Supply Corsair TX v2 650W
Mouse Steelseries Sensei
Keyboard CM Storm Quickfire Pro, Cherry MX Reds
Software MS Windows 10 Pro 64-bit
Latency is an issue. You cannot put cache on a separate die, which requires extremely low latency. AMD experiences up to 250ns of latency die to die. For something as commenly used as cache, putting it on a seperate die would completely destroy performance. There is a reason cache is right next to the CPU. Ditto goes for GPUs as well.
That high? ... What's the point then ... what wouldn't suffer from 250ns of latency ... RAM access from separate NUMA node is in range of 100ns
 
Joined
Sep 17, 2014
Messages
22,666 (6.05/day)
Location
The Washing Machine
System Name Tiny the White Yeti
Processor 7800X3D
Motherboard MSI MAG Mortar b650m wifi
Cooling CPU: Thermalright Peerless Assassin / Case: Phanteks T30-120 x3
Memory 32GB Corsair Vengeance 30CL6000
Video Card(s) ASRock RX7900XT Phantom Gaming
Storage Lexar NM790 4TB + Samsung 850 EVO 1TB + Samsung 980 1TB + Crucial BX100 250GB
Display(s) Gigabyte G34QWC (3440x1440)
Case Lian Li A3 mATX White
Audio Device(s) Harman Kardon AVR137 + 2.1
Power Supply EVGA Supernova G2 750W
Mouse Steelseries Aerox 5
Keyboard Lenovo Thinkpad Trackpoint II
VR HMD HD 420 - Green Edition ;)
Software W11 IoT Enterprise LTSC
Benchmark Scores Over 9000
Fill the whole bottom floor with cache, and put the rest of the cpu on top? ... or with gpus, memory controllers, rops and cache on the bottom floor, shader cores on the top

That's why I'm intrigued, this will vastly complicate any kind of overclocking, its no longer a flat surface that gets direct cooling, but temps will vary wildly throughout the chip and you only need one bit to limit potential of the entire thing.
 
Joined
Sep 15, 2007
Messages
3,946 (0.63/day)
Location
Police/Nanny State of America
Processor OCed 5800X3D
Motherboard Asucks C6H
Cooling Air
Memory 32GB
Video Card(s) OCed 6800XT
Storage NVMees
Display(s) 32" Dull curved 1440
Case Freebie glass idk
Audio Device(s) Sennheiser
Power Supply Don't even remember
That's why I'm intrigued, this will vastly complicate any kind of overclocking, its no longer a flat surface that gets direct cooling, but temps will vary wildly throughout the chip and you only need one bit to limit potential of the entire thing.

Yeah, I doubt this can work for anything over 50 watts.
 
Joined
Jul 13, 2010
Messages
62 (0.01/day)
Location
Slovakia
System Name Pap1er
Processor AMD Ryzen 7 5800X3D
Motherboard MSI B450 GAMING PRO CARBON AC
Cooling ARCTIC Freezer 33 eSport One - Red
Memory G.SKILL 16 GB KIT DDR4 4000 MHz CL15 Ripjaws V
Video Card(s) Sapphire NITRO+ AMD Radeon™ RX 7800 XT
Storage ADATA XPG GAMMIX S50 CORE/1TB/SSD/M.2 NVMe
Display(s) LG 29UC88 Curved UltraWide Monitor
Case Corsair 230T Graphite Series - Orange
Audio Device(s) OnBoard
Power Supply Corsair CX750M
Mouse Creative Sound BlasterX Siege M04 Gaming mouse
Software Windows 11 Pro x64
Yeah, I doubt this can work for anything over 50 watts.

I assume that making matrix of few smaller chips with small power dissipation would make sense. Also cooling of chip grid might be easier due to larger dissipation area.
You know, like AMD already did with it's latest CPUs...
 
Top