Corsair Xeneon 27QHD240 OLED monitor review
ASUS Radeon RX 7600 STRIX OC review
Corsair RM1200X SHIFT 1200W PSU Review
Intel NUC 13 Pro (Arena Canyon) review
Endorfy Arx 700 Air chassis review
Beelink SER5 Pro (Ryzen 7 5800H) mini PC review
Crucial T700 PCIe 5.0 NVMe SSD Review - 12GB/s
Sapphire Radeon RX 7600 PULSE review
Gainward GeForce RTX 4060 Ti GHOST review
Radeon RX 7600 review
Possible Galax GeForce RTX 3090 Ti is seen with a 600W PCIe Gen5 power supply.
@wxnod, a known leaker, has posted an alleged picture of Galax's custom GeForce RTX 3090 Ti graphics card with the next-generation 12+4-pin (12VHPWR) PCIe 5.0 auxiliary power connection.
Galax's custom GeForce RTX 3090 Ti graphics card would reportedly feature a triple-wide cooling system and a 12+4-pin (12VHPWR) auxiliary power connector, according to a picture published by @wxnod (note that all other images are of the Galax GeForce RTX 3090 Boomstar from the company's website). Because the new ATX 3.0/PCIe 5.0 power connection may supply between 150W and 600W to an add-in-board (AIB), we can only make educated assumptions regarding the Galax product's power usage.
Galax's Boomstar line is exclusive to China, thus it's unclear whether all of Galax's GeForce RTX 3090 Ti will include the next-generation 12VHPWR power socket or will retain the eight-pin PCIe auxiliary power connector.
That's all there is to show though. Since September 2020, Nvidia has begun shipping premium GeForce RTX 30-series Founders Edition graphics cards with a 12-pin power connection. While the 12-pin power connector is considered a unique technology of Nvidia, the only distinction between it and the industry-standard 12+4-pin (12VHPWR) auxiliary power connector is the absence of four sensing lines. Indeed, Nvidia's Founders Edition boards are fully compatible with next-generation power supplies equipped with auxiliary PCIe 5.0 power connectors. Nvidia is anticipated to unveil its top GeForce RTX 3090 Ti graphics card on March 29 and immediately begin selling it. The new top-of-the-line model is said to be built on the GA102 GPU, which features 10,752 CUDA cores (up from 10,496 on the RTX 3090), and is coupled via a 384-bit interface to 24GB of Micron's GDDR6X memory. With these features, the board is expected to top our list of the best gaming graphics cards in the first half of 2022. The unit's power consumption is predicted to be around 450W.
VideoCardz earns props for bringing attention to thuis spot. Proceed with care, as is common with leaks, until formal confirmation is provided.
Possible entry level Intel Alchemist PCB reveals 6GB VRAM - 09/28/2021 09:34 AM
Vermicelli, a Chiphell user, has posted a snapshot of what appears to be a graphics card from Intel's future Arc Alchemist product line. It looks to become an entry-level desktop variant, and it coul...
Fractal Design Replaces Torrent Fan Hub Due To Possible Short Circuit - 08/30/2021 08:45 AM
The Fractal Design fan hub in its Torrent case can cause a short circuit. Fans should not be used in conjunction with the fan hub, according to the manufacturer, which will provide replacements at no ...
Microsoft releases first Windows 11 ISO making clean install of Windows 11 possible (to Insiders). - 08/20/2021 08:08 AM
Microsoft introduced Windows 11 back in June days after Insiders received the first beta. The developer has provided the first ISO of the new operating system for beta testers to download. This allows...
Possible prototype Z690 motherboard for Intel Alder Lake CPUs Spotted - 08/02/2021 07:35 AM
Images of a potential Intel Z690 motherboard have appeared on a Chinese social media platform. One such motherboard, shared by a Bilibili user, will be utilized with Intel's forthcoming Alder Lake-S ...
Upgrade from Windows 7 to Windows 11 only possible with clean install - 07/08/2021 08:34 AM
So yeah that's not an actual upgrade. Users who wish to upgrade from Windows 7 to Windows 11 will be able to do so only through a clean install. The upgrade will be free, but it will not contain doc...
Krizby
Senior Member
Posts: 2503
Joined: 2005-05-04
Senior Member
Posts: 2503
Joined: 2005-05-04
#6000799 Posted on: 03/14/2022 04:10 PM
you are missing (deliberately?) the point.
GA100 is a monolithic die.
@ 7nm one chiplet (from Ryzen in this case - the only on the market mcm as we speak) has vastly greater yield than GA100
at over 6:1
Huh? Since when did I mention that Nvidia is going to compete with RDNA3 with MCM design?
Yes the point behind MCM is that by utilizing smaller dies with good yield (like 90% yield rate with 350mm2 die), AMD can make more halo product from a single wafer.
Let say Navi33 is 350mm2, with 90% yield rate there are 166 perfect die from a single wafer, that means AMD can make 83 MCM from a wafer and sell them 1200usd a pop, making 99.6k USD revenue from a single wafer.
Meanwhile Nvidia can make 92 AD102 chip from a wafer (~600mm2), but only 45 of them are 4090 (50% yield) and 47 defective chips are salvaged as 4080, selling 4090 @ 1500usd and 4080@700usd would net Nvidia 100.4k usd from a wafer.
For midrange GPU, MCM is pointless as 350mm2 and smaller die get 90% yield anyways, no point coupling 2x 200mm2 die then spend extra for the Infinity Cache/ IO chiplet. Here Nvidia definitely has the edge from superior uarch.
you are missing (deliberately?) the point.
GA100 is a monolithic die.
@ 7nm one chiplet (from Ryzen in this case - the only on the market mcm as we speak) has vastly greater yield than GA100
at over 6:1
Huh? Since when did I mention that Nvidia is going to compete with RDNA3 with MCM design?
Yes the point behind MCM is that by utilizing smaller dies with good yield (like 90% yield rate with 350mm2 die), AMD can make more halo product from a single wafer.
Let say Navi33 is 350mm2, with 90% yield rate there are 166 perfect die from a single wafer, that means AMD can make 83 MCM from a wafer and sell them 1200usd a pop, making 99.6k USD revenue from a single wafer.
Meanwhile Nvidia can make 92 AD102 chip from a wafer (~600mm2), but only 45 of them are 4090 (50% yield) and 47 defective chips are salvaged as 4080, selling 4090 @ 1500usd and 4080@700usd would net Nvidia 100.4k usd from a wafer.
For midrange GPU, MCM is pointless as 350mm2 and smaller die get 90% yield anyways, no point coupling 2x 200mm2 die then spend extra for the Infinity Cache/ IO chiplet. Here Nvidia definitely has the edge from superior uarch.
tunejunky
Senior Member
Posts: 3470
Joined: 2017-08-18
Senior Member
Posts: 3470
Joined: 2017-08-18
#6000859 Posted on: 03/14/2022 08:02 PM
Huh? Since when did I mention that Nvidia is going to compete with RDNA3 with MCM design?
Yes the point behind MCM is that by utilizing smaller dies with good yield (like 90% yield rate with 350mm2 die), AMD can make more halo product from a single wafer.
Let say Navi33 is 350mm2, with 90% yield rate there are 166 perfect die from a single wafer, that means AMD can make 83 MCM from a wafer and sell them 1200usd a pop, making 99.6k USD revenue from a single wafer.
Meanwhile Nvidia can make 92 AD102 chip from a wafer (~600mm2), but only 45 of them are 4090 (50% yield) and 47 defective chips are salvaged as 4080, selling 4090 @ 1500usd and 4080@700usd would net Nvidia 100.4k usd from a wafer.
For midrange GPU, MCM is pointless as 350mm2 and smaller die get 90% yield anyways, no point coupling 2x 200mm2 die then spend extra for the Infinity Cache/ IO chiplet. Here Nvidia definitely has the edge from superior uarch.
1) agreed Nvidia is the King of (gpu) uArch
2) in all forms of uArch, due to the realities of manufacturing the larger the die the lower the yield as you agreed.
3) you supposed Nvidia Lovelace 3090ti replacement with a mcm.
salvaging gpus is something all do. i even made the point the other day about Nvidia potentially peeing on AMD's RDNA 3 launch with cut-downs.
and your math on the yields is not even guessing and it's presented as an argument.
which it is not, it is an illustration and i get your point.
i do know the ballpark of the yields and you are off.
what i will say is this - higher yields are always better not least because Fab prices Are Not Equal and never have been.
AMD has a lower cost of fabrication than Nvidia by contract through next year and will until Intel grabs that spot in '24
AMD knows this, although they hoped Intel wouldn't be aggressive
Huh? Since when did I mention that Nvidia is going to compete with RDNA3 with MCM design?
Yes the point behind MCM is that by utilizing smaller dies with good yield (like 90% yield rate with 350mm2 die), AMD can make more halo product from a single wafer.
Let say Navi33 is 350mm2, with 90% yield rate there are 166 perfect die from a single wafer, that means AMD can make 83 MCM from a wafer and sell them 1200usd a pop, making 99.6k USD revenue from a single wafer.
Meanwhile Nvidia can make 92 AD102 chip from a wafer (~600mm2), but only 45 of them are 4090 (50% yield) and 47 defective chips are salvaged as 4080, selling 4090 @ 1500usd and 4080@700usd would net Nvidia 100.4k usd from a wafer.
For midrange GPU, MCM is pointless as 350mm2 and smaller die get 90% yield anyways, no point coupling 2x 200mm2 die then spend extra for the Infinity Cache/ IO chiplet. Here Nvidia definitely has the edge from superior uarch.
1) agreed Nvidia is the King of (gpu) uArch
2) in all forms of uArch, due to the realities of manufacturing the larger the die the lower the yield as you agreed.
3) you supposed Nvidia Lovelace 3090ti replacement with a mcm.
salvaging gpus is something all do. i even made the point the other day about Nvidia potentially peeing on AMD's RDNA 3 launch with cut-downs.
and your math on the yields is not even guessing and it's presented as an argument.
which it is not, it is an illustration and i get your point.
i do know the ballpark of the yields and you are off.
what i will say is this - higher yields are always better not least because Fab prices Are Not Equal and never have been.
AMD has a lower cost of fabrication than Nvidia by contract through next year and will until Intel grabs that spot in '24
AMD knows this, although they hoped Intel wouldn't be aggressive
Aura89
Senior Member
Posts: 8408
Joined: 2008-07-31
Senior Member
Posts: 8408
Joined: 2008-07-31
#6000914 Posted on: 03/15/2022 12:40 AM
Right? Can't for the life of me understand why anyone would want to stick to the previous connectors...
I'll take one single cable vs 3 separate 8x pins
Right? Can't for the life of me understand why anyone would want to stick to the previous connectors...
Falkentyne
Senior Member
Posts: 538
Joined: 2001-02-27
Senior Member
Posts: 538
Joined: 2001-02-27
#6000959 Posted on: 03/15/2022 05:13 AM
All the people who bought a 3090 at MSRP for gaming are laughing at you right now.
Hold my beer.
The 3090Ti is a Titan-level card. Why are people discussing it as if it were a mainstream product? It isn't. It's meant for those with more money than common sense. Gamers don't need a 3090Ti. They don't need a 3090. Heck, most don't need a 3080, but at least that one makes sense for gaming. If you're an enthusiast, then this is your hobby, and you can easily afford one. If you aren't, then what do you care about an insanely overpriced and power-hungry contraption? The people that will buy them already own a cottage, two luxury cars and are probably eyeing a Cessna.
All the people who bought a 3090 at MSRP for gaming are laughing at you right now.
Hold my beer.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 14092
Joined: 2004-05-16
Laugh all you want - name ONE fabrication plant that Nvidia has owned or operated.
this is true and correct.
just because Nvidia is freaking amazing at uArch does not translate to manufacturing just as a Physics teacher is out of place at a nuclear power plant.
I don't believe that matters - companies hire manufacturing process engineers with experience. It's not like owning a fabrication plant suddenly imbues everyone in the company with the knowledge of the process there - you have specialized people for that and when those people leave (foundry splits off) they take most of that experience with them. If Nvidia poached every top engineer from TSMC, I don't think we'd be sitting here saying AMD has more knowledge because they onced owned a fab a decade ago.
I think a better argument for AMD would be all the cutting edge process technology they work on - HBM/3DCache (silicon vias work)/MCM/Semi-Custom/etc. They clearly spend a large chunk of their R&D budget on gambles in fabrication in order to maintain a competitive edge and you'd presume this would continue - but I don't think this has to do with them once owning a fab plant, I think it's them choosing to allocate R&D expenses on fabrication vs Nvidia who's R&D is heavily spent on software development.