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

NVIDIA GeForce GTX 980 4 GB

Joined
Jun 28, 2008
Messages
1,109 (0.19/day)
Location
Greenville, NC
System Name Champ's 1440P Rig
Processor Intel i7-4770K @ 4.6 GHz
Motherboard AsRock Z97 Extreme6
Cooling Corsair H60
Memory Corsair Vengeance 16GB 1600 Mhz 4x4 Blue Ram
Video Card(s) Nvidia 1080 FE
Storage Samsung 840 Evo 256 GB/RAID 0 Western Digital Blue 1 TB HDDs
Display(s) Acer XG270HU
Case Antec P100
Power Supply Corsair CX850M
Mouse Logitech G502
Keyboard TT eSports Poseidon
Software Windows 10
 
Joined
Feb 21, 2008
Messages
4,985 (0.85/day)
Location
Greensboro, NC, USA
System Name Cosmos F1000
Processor i9-9900k
Motherboard Gigabyte Z370XP SLI, BIOS 15a
Cooling Corsair H100i, Panaflo's on case
Memory XPG GAMMIX D30 2x16GB DDR4 3200 CL16
Video Card(s) EVGA RTX 2080 ti
Storage 1TB 960 Pro, 2TB Samsung 850 Pro, 4TB WD Hard Drive
Display(s) ASUS ROG SWIFT PG278Q 27"
Case CM Cosmos 1000
Audio Device(s) logitech 5.1 system (midrange quality)
Power Supply CORSAIR HXi HX1000i 1000watt
Mouse G400s Logitech
Keyboard K65 RGB Corsair Tenkeyless Cherry Red MX
Software Win10 Pro, Win7 x64 Professional
Product progression is one thing. 480 to 580 would be another example. Or how about the 8800GT and its progression. In these examples we still got the full chip and amd/nvidia putting the best chip to market. Had amd not had Hawaii we would have never seen the 780ti and the 780 would be still $650 and Maxwell would still be in the pipeline waiting for 20nm.
Not to mention nvidia has discontiuned the 770/780 and 780ti. The 780/780ti I understand. But since a 770 and a 760 cost the same to produce why not keep the 770 with a price cut?
Bottom line is consumers drive the market and as long as people are willing to rush out and spend flagship money on a mid-range chip it is us the consumers that will be continued to be shortchanged.
Again, if Intel did business this way the 4790k would be the $1k flagship. Kudos to Intel for offering the consumer the best chip reguardless of what the competition is doing.
Instead of defending Nvidia, maybe you should defend your pocket book.

Pricing is created through trying to maximize revenue and dominate the competition(gain market share) with differentiated offerings. Intel, AMD, and Nvidia are just out to make their stockholders the most money. Anything else would be just a figment of your imagination or projection of your own emotions into your analysis. Companies are indifferent to how you feel about their pricing. Public opinion is fickle for the most part. Upgrading from my GTX 680 to the GTX 980 was perceived obsolescence. The GTX 680 suited me just fine but after two generations arrived I felt it was time to buy the best that would fit into my budget. Nvidia gave me a reason to upgrade with the improved efficiency plus better performance at a price that was affordable to me. I was hoping it would offer better performance but it was in the same power envelope as my GTX 680 and noticeably better. That was reason enough.

Intel is losing market share to ARM devices and that is what pushes them to innovate. ARM could catch up to x86 architecture if Intel doesn't continue innovating. Intel has enough money to develop ARM processors but AMD cannot afford what it would take to compete in the ARM market in its current state. ARM might actually be the eventual death of AMD. ATI would have done better separate from AMD if you ask me.


Intel Leap ahead?
 
Joined
Sep 21, 2014
Messages
25 (0.01/day)
So what position do you hold at NVIDIA?

The reason I ask is the only way you could actually know any of what you allege is if you worked in NVIDIA engineering or management.

If you don't, everything you have postulated is nothing more than conspiracy theory and speculation.

NVIDIA MIDRANGE CHIPS/CARDS
GTX 460 = GF 104
GTX 560 = GF 114
GTX 680/660TI/770 =GK 104
GTX 980 GM 204

NVIDIA FLAGSHIP CHIPS/CARDS
GTX 480 = GF 100
GTX 580 = GF 114
GTX 780/780TI/TITAN = GK 110

Notice the pattern? Also check the size of the die.

GTX 980 is a midrange chip, that is a fact!
 
Joined
Feb 21, 2008
Messages
4,985 (0.85/day)
Location
Greensboro, NC, USA
System Name Cosmos F1000
Processor i9-9900k
Motherboard Gigabyte Z370XP SLI, BIOS 15a
Cooling Corsair H100i, Panaflo's on case
Memory XPG GAMMIX D30 2x16GB DDR4 3200 CL16
Video Card(s) EVGA RTX 2080 ti
Storage 1TB 960 Pro, 2TB Samsung 850 Pro, 4TB WD Hard Drive
Display(s) ASUS ROG SWIFT PG278Q 27"
Case CM Cosmos 1000
Audio Device(s) logitech 5.1 system (midrange quality)
Power Supply CORSAIR HXi HX1000i 1000watt
Mouse G400s Logitech
Keyboard K65 RGB Corsair Tenkeyless Cherry Red MX
Software Win10 Pro, Win7 x64 Professional
NVIDIA MIDRANGE CHIPS/CARDS
GTX 460 = GF 104
GTX 560 = GF 114
GTX 680/660TI/770 =GK 104
GTX 980 GM 204

NVIDIA FLAGSHIP CHIPS/CARDS
GTX 480 = GF 100
GTX 580 = GF 114
GTX 780/780TI/TITAN = GK 110

Notice the pattern? Also check the size of the die.

GTX 980 is a midrange chip, that is a fact!

Is there a portion of the chip that is not being used? I agree there will be a 980 ti most likely. I don't know what time table it is on though. Will there be a Titan and Titan black successor? idk

I don't know if anybody here can say the gtx 980 is a midrange card as a "fact" unless Nvidia confirms it with you though. Or are you saying you consider it a midrange card and that is your opinion? Fact and opinion are not the same thing. Maybe you have information you are breaking NDA on?

Why do you consider GTX 680 a midrange card? It filled the "high end" single GPU spot in the Nvidia GTX 600 series product lineup.
 
Last edited:
Joined
Sep 7, 2011
Messages
2,785 (0.61/day)
Location
New Zealand
System Name MoneySink
Processor 2600K @ 4.8
Motherboard P8Z77-V
Cooling AC NexXxos XT45 360, RayStorm, D5T+XSPC tank, Tygon R-3603, Bitspower
Memory 16GB Crucial Ballistix DDR3-1600C8
Video Card(s) GTX 780 SLI (EVGA SC ACX + Giga GHz Ed.)
Storage Kingston HyperX SSD (128) OS, WD RE4 (1TB), RE2 (1TB), Cav. Black (2 x 500GB), Red (4TB)
Display(s) Achieva Shimian QH270-IPSMS (2560x1440) S-IPS
Case NZXT Switch 810
Audio Device(s) onboard Realtek yawn edition
Power Supply Seasonic X-1050
Software Win8.1 Pro
Benchmark Scores 3.5 litres of Pale Ale in 18 minutes.
Product progression is one thing. 480 to 580 would be another example. Or how about the 8800GT and its progression. In these examples we still got the full chip and amd/nvidia putting the best chip to market. Had amd not had Hawaii we would have never seen the 780ti and the 780 would be still $650 and Maxwell would still be in the pipeline waiting for 20nm.
Unlikely in the extreme. Nvidia at the very least have an internal cadence they need to continue. HPC and workstation - Nvidia's large dies do double duty, and the largest die is primarily a compute chip. Secondly, the same architecture is now applied to SoC's - so reason two to keep arch cadence, as is OEM requirements - OEM's make up the largest buyers of discrete graphics chips - no new bullet points means people don't upgrade - you can only fool some of the people some of the time with rebrands.....and the primary reason? Shareholders.
Using your reasoning, Intel should have shelved Ivy Bridge/-E, Haswell/-E, and Broadwell...and Skylake for all the competition AMD offer.
Not to mention nvidia has discontiuned the 770/780 and 780ti. The 780/780ti I understand. But since a 770 and a 760 cost the same to produce why not keep the 770 with a price cut?
Because all use 28nm wafers that are finite commodity as far as allocation goes. Why would you spend a second thought about producing old 367mm² GK 104 chips when you need wafers to produce GM 206 and GM 107 ? Likewise, 551mm² GK 110's make the same zero sense when the company need to allocate wafers for 398mm² GM 204 and GM 200 production.

Again, if Intel did business this way the 4790k would be the $1k flagship. Kudos to Intel for offering the consumer the best chip regardless of what the competition is doing.
Some people might say that that is rubbish. Intel innovate just enough to keep people upgrading. You really think "best chip regardless" philosophy covers decreasing the PCI-E lanes available to the 5930K ? or deliberately keeping separation between mainstream platforms and HEDT ? The 4790K is the price it is because of the product stack above it, and the number of people who buy $1K processors aren't by any means the majority of users.
Instead of defending Nvidia, maybe you should defend your pocket book.
Sorry if the logic of the situation and business in general is unpalatable to you....
Meanwhile a $339 GTX 970 basically equals the gaming performance of a $450 R9 290X - does that class as defending my pocket book?
I don't know if anybody here can say the gtx 980 is a midrange card as a "fact" unless Nvidia confirms it with you though.
Within Nvidia's GPU hierarchy, GM 204 is indeed a mid range (second tier) chip. GM 200 (or GM 210 as some people are calling it) is the high end. What frdmftr isn't considering is that Tahiti's successor (Bermuda) will also be a midrange chip, since Fiji will be their large die compute chip.
What frdmftr is highlighting about Nvidia's lineup is exactly what AMD are now in the process of doing. Fiji has no analogue in AMD's current lineup. The big chip of each (GM 200 and Fiji) will be heavily compute orientated - IIRC both are likely to feature 1:2 FP64, while the midrange (and lower) starting with GM 204 and Bermuda (the chip associated with the R9 390X) feature die space area-ruled for gaming workloads. frdmftr can pillory Nvidia to his hearts content, but the fact remains that AMD are following their example because bifurcating the product line is the most effective use of expensive silicon production.
 
Last edited:
Joined
Sep 21, 2014
Messages
25 (0.01/day)
Unlikely in the extreme. Nvidia at the very least have an internal cadence they need to continue. HPC and workstation - Nvidia's large dies do double duty, and the largest die is primarily a compute chip. Secondly, the same architecture is now applied to SoC's - so reason two to keep arch cadence, as is OEM requirements - OEM's make up the largest buyers of discrete graphics chips - no new bullet points means people don't upgrade - you can only fool some of the people some of the time with rebrands.....and the primary reason? Shareholders.
Using your reasoning, Intel should have shelved Ivy Bridge/-E, Haswell/-E, and Broadwell...and Skylake for all the competition AMD offer.

Because all use 28nm wafers that are finite commodity as far as allocation goes. Why would you spend a second thought about producing old 367mm² GK 104 chips when you need wafers to produce GM 206 and GM 107 ? Likewise, 551mm² GK 110's make the same zero sense when the company need to allocate wafers for 398mm² GM 204 and GM 200 production.


Some people might say that that is rubbish. Intel innovate just enough to keep people upgrading. You really think "best chip regardless" philosophy covers decreasing the PCI-E lanes available to the 5930K ? or deliberately keeping separation between mainstream platforms and HEDT ? The 4790K is the price it is because of the product stack above it, and the number of people who buy $1K processors aren't by any means the majority of users.

Sorry if the logic of the situation and business in general is unpalatable to you....
Meanwhile a $339 GTX 970 basically equals the gaming performance of a $450 R9 290X - does that class as defending my pocket book?

Within Nvidia's GPU hierarchy, GM 204 is indeed a mid range (second tier) chip. GM 200 (or GM 210 as some people are calling it) is the high end. What frdmftr isn't considering is that Tahiti's successor (Bermuda) will also be a midrange chip, since Fiji will be their large die compute chip.
What frdmftr is highlighting about Nvidia's lineup is exactly what AMD are now in the process of doing. Fiji has no analogue in AMD's current lineup. The big chip of each (GM 200 and Fiji) will be heavily compute orientated - IIRC both are likely to feature 1:2 FP64, while the midrange (and lower) starting with GM 204 and Bermuda (the chip associated with the R9 390X) feature die space area-ruled for gaming workloads. frdmftr can pillory Nvidia to his hearts content, but the fact remains that AMD are following their example because bifurcating the product line is the most effective use of expensive silicon production.


The 760 and the 770 use the exact same chip. Nvidia diaables a portion of the chip to make the 760. That being said why keep a $220 GTX 760 and not go to $250 on the 770? Again just Nvidia protecting its product stack.

I am not a socialist and do not think Nvidia should be a chairty. However, how long had the Titan been around before we saw the 780? Even the Titan remained unchanged until after the 290x. They were shipping the chips anyway. once yeilds improved they could have fully enabled the Titan long ago. Instead they disable a portion of the chip?

No arguement here about the 970. Again a little spendy for a second tier chip but it really delivers on the preformance.

As I have been saying all along the GM 204 is a mid range chip and at $550 that is a top tier price.
 
Joined
Sep 7, 2011
Messages
2,785 (0.61/day)
Location
New Zealand
System Name MoneySink
Processor 2600K @ 4.8
Motherboard P8Z77-V
Cooling AC NexXxos XT45 360, RayStorm, D5T+XSPC tank, Tygon R-3603, Bitspower
Memory 16GB Crucial Ballistix DDR3-1600C8
Video Card(s) GTX 780 SLI (EVGA SC ACX + Giga GHz Ed.)
Storage Kingston HyperX SSD (128) OS, WD RE4 (1TB), RE2 (1TB), Cav. Black (2 x 500GB), Red (4TB)
Display(s) Achieva Shimian QH270-IPSMS (2560x1440) S-IPS
Case NZXT Switch 810
Audio Device(s) onboard Realtek yawn edition
Power Supply Seasonic X-1050
Software Win8.1 Pro
Benchmark Scores 3.5 litres of Pale Ale in 18 minutes.
The 760 and the 770 use the exact same chip. Nvidia diaables a portion of the chip to make the 760. That being said why keep a $220 GTX 760 and not go to $250 on the 770? Again just Nvidia protecting its product stack.
Honestly I don't know how to make it any clearer. Nvidia is drawing a line under Kepler (GK 204, GK 110) production in favour of Maxwell production (GM 107, GM 204, GM 200) where wafer starts are a limited commodity. Why would Nvidia continue producing a $250 770, when they have a stack of salvage GM 204's ready to go as the GTX 960 next month? You think that a $250 GTX 770 makes more sense than a likely faster GTX 960 at the same (or lower) price point?
I am not a socialist and do not think Nvidia should be a chairty. However, how long had the Titan been around before we saw the 780?
Different argument entirely. The Titan -> GTX 780 -> 780 Ti -> Titan Black is generally accepted as marketing strategy - no question, and I wouldn't argue otherwise.
Even the Titan remained unchanged until after the 290x. They were shipping the chips anyway. once yeilds improved they could have fully enabled the Titan long ago.
That smells suspiciously like your opinion dressed up as fact- and unfortunately for you it is wrong. The fact is that the fully enabled GTX 780 Ti and Titan Black are both revised B1 silicon. Titan and the GTX 780 - not fully enabled - are A1 silicon. Easy reference: B1 silicon is specced for 7GHz (effective) memory, A1 is specced for 6GHz.
 
Joined
Nov 7, 2007
Messages
32 (0.01/day)
As I have been saying all along the GM 204 is a mid range chip and at $550 that is a top tier price.

You're working really hard to make it look like NVIDIA is somehow "cheating" people by giving us the top single GPU performance for $550 and beating their competitors $500 card on all fronts for $339.. DARN them for selling people products that are superior on all fronts for $160 less!

On the rest of your theories:

Yes the GTX980 may well not be the largest, most powerful chip based on the Maxwell arch. Doesn't mean larger chips on the Maxwell arch are done now, or could even be produced at 28nm.

So for right now, the GTX980 "is" the high end on PC gaming because there's no other single GPU that competes. (and AMD/NVIDIA is starting to look a lot like AMD/intel- just a beat down, even on the same process node- pretty amazing)

Also, while $550 may be a "top card" price for a second tier vendor like AMD, NVIDIA can (and does) charge more than that for their top card with fair regularity. Their "big" Maxwell chip will likely cost $1000..
 
Joined
Oct 29, 2013
Messages
69 (0.02/day)
Location
Switzerland
System Name Double Overseer
Processor i7 3820 / FX-8350
Motherboard Asus P9X79 / MSI 990FXA-GD65
Cooling Air
Memory Kingston 16 GB RAM 1600 / Corsair 8 GB RAM 1866 (2000)
Video Card(s) PCS+ 7950 Crossfire / Club3d 7950 13 Series / Hauppauge 5500
Storage 240 Kingston HyperX 3K / Crucial MX100 256 GB / 1+3 TB Seagate
Display(s) S240HL Acer / S242HL Acer x2
Case 2x Thermaltake Overseer
Audio Device(s) Onkyo TX-SR309 / 5.1 Canton
Power Supply Fractal Design Newton R3 800 / Seasonic SS-660KM Active
Mouse 5 Euro one
Keyboard Logitech K120
Software Windows 7 64-Bit / Windows 10 64-Bit
Benchmark Scores Firestrike 10400 3DMark11 13400 / triple crossfire Firestrike 12500 3DMark11 15600
Buying two of these 970 cards that would be my style, because of the 4gb high ram size and the cheaper price than the 980 card. I like the double card setting and the low powerconsumption due to the lower noise. NVIDIA wants me to buy. But then again, I'll wait AMD's turn and buy some similar cards for 100$ less. Or I even skip this generation for no need.

What if AMD is going to fail with its next cards? Then you should buy these cards now or they even get more expensive. Nice cards anyway. :lovetpu:
 
Joined
Oct 15, 2010
Messages
951 (0.19/day)
System Name Little Boy / New Guy
Processor AMD Ryzen 9 5900X / Intel Core I5 10400F
Motherboard Asrock X470 Taichi Ultimate / Asus H410M Prime
Cooling ARCTIC Liquid Freezer II 280 A-RGB / ARCTIC Freezer 34 eSports DUO
Memory TeamGroup Zeus 2x16GB 3200Mhz CL16 / Teamgroup 1x16GB 3000Mhz CL18
Video Card(s) Asrock Phantom RX 6800 XT 16GB / Asus RTX 3060 Ti 8GB DUAL Mini V2
Storage Patriot Viper VPN100 Nvme 1TB / OCZ Vertex 4 256GB Sata / Ultrastar 2TB / IronWolf 4TB / WD Red 8TB
Display(s) Compumax MF32C 144Hz QHD / ViewSonic OMNI 27 144Hz QHD
Case Phanteks Eclipse P400A / Montech X3 Mesh
Power Supply Aresgame 850W 80+ Gold / Aerocool 850W Plus bronze
Mouse Gigabyte Force M7 Thor
Keyboard Gigabyte Aivia K8100
Software Windows 10 Pro 64 Bits
(and AMD/NVIDIA is starting to look a lot like AMD/intel- just a beat down, even on the same process node- pretty amazing)

As far as i have memory about gpus, they are ALWAYS trading blows. And i don't know if i'm understanding people the wrong way here, they seem to be so exited about nvidia beating amd or the other way around, but don't you people see that if one side singlehandedly beats the other out of competition, WE are the ones SCREWED!?
 
Joined
Nov 7, 2007
Messages
32 (0.01/day)
As far as i have memory about gpus, they are ALWAYS trading blows. And i don't know if i'm understanding people the wrong way here, they seem to be so exited about nvidia beating amd or the other way around, but don't you people see that if one side singlehandedly beats the other out of competition, WE are the ones SCREWED!?
Personally I'm just excited to see products this good this cheap.

The GK series chips were great, but fairly costly at first. (pre-GTX780 launch)

The R290X was a face plant launch. Sure, it competed, but the OEM design was a hairdryer.

I disagree on the one company winning harms us.

Intel has had no competition for many years, but they have to sell us better parts at a price we'll pay to keep the doors open.

Unless you think they're saying "Gee fellas if we DON'T sell our bada$$ chips for $300, people will buy FX-8350s!"? LOL- like that would happen.
 
Joined
Sep 21, 2014
Messages
25 (0.01/day)
You're working really hard to make it look like NVIDIA is somehow "cheating" people by giving us the top single GPU performance for $550 and beating their competitors $500 card on all fronts for $339.. DARN them for selling people products that are superior on all fronts for $160 less!

On the rest of your theories:

Yes the GTX980 may well not be the largest, most powerful chip based on the Maxwell arch. Doesn't mean larger chips on the Maxwell arch are done now, or could even be produced at 28nm.

So for right now, the GTX980 "is" the high end on PC gaming because there's no other single GPU that competes. (and AMD/NVIDIA is starting to look a lot like AMD/intel- just a beat down, even on the same process node- pretty amazing)

Also, while $550 may be a "top card" price for a second tier vendor like AMD, NVIDIA can (and does) charge more than that for their top card with fair regularity. Their "big" Maxwell chip will likely cost $1000..


The cost difference comes into play based on die size. Given the size of the die used in the 980 and the fact that it has a 204 at the end tells us the simple FACT this is a mid-range, second tier chip, period. Now, this chip was supposed to have been on the 20nm process and since they went withn 28nm the die is a little bigger than the GK 104 it replaced but not the size of the GK 110. The 110 is the flagship chip. The 980 will cost less to produce than the 780, yet is priced higher.
Yes it is impressive for its size but it is not the "full monte"

Everyone wants to bring the 970 into the conversation. That is not what we are taking about. I am specifically referring to the 980. You can talk about price/preformance all you want. Anyone can make a Kia as fast as a BMW that doesn't make it worth the price of a BMW. The 204 chip is an ecomomy class, just because of techinacal advancements it does not make it worth luxury prices. Think about that next time you buy a TV. year after year they get cheaper and bigger. And since Kepler Nvidia has been offering less silicon for more and more dollars.
 
Joined
Sep 7, 2011
Messages
2,785 (0.61/day)
Location
New Zealand
System Name MoneySink
Processor 2600K @ 4.8
Motherboard P8Z77-V
Cooling AC NexXxos XT45 360, RayStorm, D5T+XSPC tank, Tygon R-3603, Bitspower
Memory 16GB Crucial Ballistix DDR3-1600C8
Video Card(s) GTX 780 SLI (EVGA SC ACX + Giga GHz Ed.)
Storage Kingston HyperX SSD (128) OS, WD RE4 (1TB), RE2 (1TB), Cav. Black (2 x 500GB), Red (4TB)
Display(s) Achieva Shimian QH270-IPSMS (2560x1440) S-IPS
Case NZXT Switch 810
Audio Device(s) onboard Realtek yawn edition
Power Supply Seasonic X-1050
Software Win8.1 Pro
Benchmark Scores 3.5 litres of Pale Ale in 18 minutes.
I disagree on the one company winning harms us.
Intel has had no competition for many years, but they have to sell us better parts at a price we'll pay to keep the doors open.
Unless you think they're saying "Gee fellas if we DON'T sell our bada$$ chips for $300, people will buy FX-8350s!"? LOL- like that would happen.
A different situation with graphics since hardware, features, and end product (games and apps) have a greater interdependency.
If Nvidia were left as the sole discrete GPU supplier, OpenCL would suffer and game developers would likely become more dependant upon the company. If AMD were the sole GPU supplier, they would immediately divert funds/R&D from their graphics program to bolster the processor division as is already apparent.
Competition between architectures and gaming programs serves to keep innovation and development at a somewhat reasonable pace in comparison to what we would have without it.
 
Last edited:
Joined
Nov 7, 2007
Messages
32 (0.01/day)
The 204 chip is an ecomomy class, just because of techinacal advancements it does not make it worth luxury prices.

Pretty harsh assessment frdmftr.

As you think the 980 at $550 is an "economy class chip" and a "Kia", what do you think of the 290X?

High school science project? Tobacco Row part?

After all, the 980 pretty much embarrasses the 290X on every relevant performance, engineering, and efficiency metric.

AMD has become synonymous with slow, hot, loud, and inefficient in all markets they compete in. Not having any money in the tech world is like having one foot in the grave, the other sliding off the edge, and the rain starting to fall....hard.
 
Joined
Sep 7, 2011
Messages
2,785 (0.61/day)
Location
New Zealand
System Name MoneySink
Processor 2600K @ 4.8
Motherboard P8Z77-V
Cooling AC NexXxos XT45 360, RayStorm, D5T+XSPC tank, Tygon R-3603, Bitspower
Memory 16GB Crucial Ballistix DDR3-1600C8
Video Card(s) GTX 780 SLI (EVGA SC ACX + Giga GHz Ed.)
Storage Kingston HyperX SSD (128) OS, WD RE4 (1TB), RE2 (1TB), Cav. Black (2 x 500GB), Red (4TB)
Display(s) Achieva Shimian QH270-IPSMS (2560x1440) S-IPS
Case NZXT Switch 810
Audio Device(s) onboard Realtek yawn edition
Power Supply Seasonic X-1050
Software Win8.1 Pro
Benchmark Scores 3.5 litres of Pale Ale in 18 minutes.
The 980 will cost less to produce than the 780, yet is priced higher.
Oh, ffs, the GTX 980 is a fully functional GPU. The GTX 780 is a third tier salvage part. :shadedshu: Why don't you compare pricing for fully functional GPU vs. fully functional GPU - the top GM 204 part is the GTX 980, the top single GK 110 part is the GTX Titan Black (which hasn't been EOL'd)
And since Kepler Nvidia has been offering less silicon for more and more dollars.
Paraphrase : GM 204 is bigger than GK 104 but I won't compare any further back than the last GPU because the argument doesn't hold up. You just admitted:
Given the size of the die used in the 980 and the fact that it has a 204 at the end tells us the simple FACT this is a mid-range, second tier chip, period.
Yet continue to base pricing across two distinct segments in the hierarchy. Die sizes for the second tier GPU have been rising as a general trend - picking out a relative outlier in GK 104 says more about your motivation than it does about process technology (G92 (324mm²) -> GF 104/GF114 (367mm²/358mm²) -> GK 104 (294mm²) -> GM 204 (398mm²) ) . The same is true for AMD unsurprisingly at the same performance level of their Nvidia counterparts.
 
Joined
Sep 21, 2014
Messages
25 (0.01/day)
Oh, ffs, the GTX 980 is a fully functional GPU. The GTX 780 is a third tier salvage part. :shadedshu: Why don't you compare pricing for fully functional GPU vs. fully functional GPU - the top GM 204 part is the GTX 980, the top single GK 110 part is the GTX Titan Black (which hasn't been EOL'd)

Paraphrase : GM 204 is bigger than GK 104 but I won't compare any further back than the last GPU because the argument doesn't hold up. You just admitted:

Yet continue to base pricing across two distinct segments in the hierarchy. Die sizes for the second tier GPU have been rising as a general trend - picking out a relative outlier in GK 104 says more about your motivation than it does about process technology (G92 (324mm²) -> GF 104/GF114 (367mm²/358mm²) -> GK 104 (294mm²) -> GM 204 (398mm²) ) . The same is true for AMD unsurprisingly at the same performance level of their Nvidia counterparts.


Actually it does hold up going all the way back the the 8800 Ultra. Even that chip is bigger than the GM 204 in the 980. The GM 204 may be a fully enabled chip but as I'm sure you know the each chip comes from a wafer. Fully enable or not the FACT remains the GM 204 takes up less real estate on said wafer. Which means they will get more chips per wafer compared to the GK 110!!. Given the fact that just about every company I can think of will base part of thier cost on how many chips per wafer, well except Nvidia.

I paid the same for my S2 as my Note 3, my 60in TV cost less in 2014 than my 40in in 2010, Motherboards, RAM, CPU's all about the same price. By no means am I here to defend AMD. Just pointing out that of all the things I just listed Nvidia is the only company that is giving me less of something for more $$$$.
 
Joined
Jun 28, 2014
Messages
2,388 (0.67/day)
Location
Shenandoah Valley, Virginia USA
System Name Home Brewed
Processor i9-7900X and i7-8700K
Motherboard ASUS ROG Rampage VI Extreme & ASUS Prime Z-370 A
Cooling Corsair 280mm AIO & Thermaltake Water 3.0
Memory 64GB DDR4-3000 GSKill RipJaws-V & 32GB DDR4-3466 GEIL Potenza
Video Card(s) 2X-GTX-1080 SLI & 2 GTX-1070Ti 8GB G1 Gaming in SLI
Storage Both have 2TB HDDs for storage, 480GB SSDs for OS, and 240GB SSDs for Steam Games
Display(s) ACER 28" B286HK 4K & Samsung 32" 1080P
Case NZXT Source 540 & Rosewill Rise Chassis
Audio Device(s) onboard
Power Supply Corsair RM1000 & Corsair RM850
Mouse Generic
Keyboard Razer Blackwidow Tournament & Corsair K90
Software Win-10 Professional
Benchmark Scores yes
Good review W1zzard, of a really good performing card. I like the price point it has too. This can only mean lower prices in the GPU market and ~that's~ good news for us consumers.
 
Joined
Sep 7, 2011
Messages
2,785 (0.61/day)
Location
New Zealand
System Name MoneySink
Processor 2600K @ 4.8
Motherboard P8Z77-V
Cooling AC NexXxos XT45 360, RayStorm, D5T+XSPC tank, Tygon R-3603, Bitspower
Memory 16GB Crucial Ballistix DDR3-1600C8
Video Card(s) GTX 780 SLI (EVGA SC ACX + Giga GHz Ed.)
Storage Kingston HyperX SSD (128) OS, WD RE4 (1TB), RE2 (1TB), Cav. Black (2 x 500GB), Red (4TB)
Display(s) Achieva Shimian QH270-IPSMS (2560x1440) S-IPS
Case NZXT Switch 810
Audio Device(s) onboard Realtek yawn edition
Power Supply Seasonic X-1050
Software Win8.1 Pro
Benchmark Scores 3.5 litres of Pale Ale in 18 minutes.
Actually it does hold up going all the way back the the 8800 Ultra. Even that chip is bigger than the GM 204 in the 980.
Nice trolling. Spend an entire thread prattling on about the GM 204 being a second tier chip then, when the comparison to other second tier chips is made switch to comparing it to the top GPU in the stack.
The GM 204 may be a fully enabled chip but as I'm sure you know the each chip comes from a wafer. Fully enable or not the FACT remains the GM 204 takes up less real estate on said wafer. Which means they will get more chips per wafer compared to the GK 110!!.
Ooooh well done! Now work out the next part!
A wafer contains a number of GPUs of varying functionality.
GM 204 harvest:
GTX 980 ($549)
GTX 970 ($329)
GTX 960 (~$250)

GM 110 harvest (consumer)
GTX Titan Black ($999)
GTX Titan ($999)
GTX 780 Ti ($649)
GTX 780 ($649 -> $500)

Now, why don't you work out some averages and tell me how chips from a GM 204 wafer are more expensive than those from a GK 110 wafer. You do know how to calculate yields from a 12" wafer I take it since you're lecturing me on fancy terms such as "wafer"

IF a wafer contained ALL fully functional dies then your argument holds up. THEY DON'T so YOURS DOESN'T
I paid the same for my S2 as my
I'm going to cut you off right there since I don't care about your shopping
I just listed Nvidia is the only company that is giving me less of something for more $$$$.
Um, well, don't buy it. Making some flawed comparison to justify your position just makes it sound like whining. You have seven posts in this thread and the fact that I could basically deconstruct your argument by just quoting your own words back to you should tell you something about how solid it is.
Why rage on about a card you aren't interested in? The GTX 970 is a star performer of this launch - and even you've admitted that it is a good card, yet out of the FOUR GM 204 reviews posted, THREE of them concern the GTX 970 and you haven't posted a single comment on any of them. Agenda much?
 
Joined
Feb 21, 2008
Messages
4,985 (0.85/day)
Location
Greensboro, NC, USA
System Name Cosmos F1000
Processor i9-9900k
Motherboard Gigabyte Z370XP SLI, BIOS 15a
Cooling Corsair H100i, Panaflo's on case
Memory XPG GAMMIX D30 2x16GB DDR4 3200 CL16
Video Card(s) EVGA RTX 2080 ti
Storage 1TB 960 Pro, 2TB Samsung 850 Pro, 4TB WD Hard Drive
Display(s) ASUS ROG SWIFT PG278Q 27"
Case CM Cosmos 1000
Audio Device(s) logitech 5.1 system (midrange quality)
Power Supply CORSAIR HXi HX1000i 1000watt
Mouse G400s Logitech
Keyboard K65 RGB Corsair Tenkeyless Cherry Red MX
Software Win10 Pro, Win7 x64 Professional
Just pointing out that of all the things I just listed Nvidia is the only company that is giving me less of something for more $$$$.

What matters to most consumers is performance per dollar and not how much wafer they get. I have never bought a card based on the size of its wafer. The power efficiency is an important perk though.

Does anyone know someone who buys hardware for the size of its chip rather than performance or value? I am starting to wonder what you are arguing for. That Nvidia shouldn't succeed doing more with less wafer and profiting? I want AMD to recover but they seem behind in every way.
 
Joined
Oct 26, 2011
Messages
3,145 (0.69/day)
Processor 8700k Intel
Motherboard z370 MSI Godlike Gaming
Cooling Triple Aquacomputer AMS Copper 840 with D5
Memory TridentZ RGB G.Skill C16 3600MHz
Video Card(s) GTX 1080 Ti
Storage Crucial MX SSDs
Display(s) Dell U3011 2560x1600 + Dell 2408WFP 1200x1920 (Portrait)
Case Core P5 Thermaltake
Audio Device(s) Essence STX
Power Supply AX 1500i
Mouse Logitech
Keyboard Corsair
Software Win10
Thanks for the awesome review, always a pleasure reading TPU articles.

Seems like my Titan SLI has been an awesome investment considering how much it is still holding, especially considering my hefty overclock, which brings performance on par, if not superior to this GPU.

Waiting for big Maxwell to upgrade :toast:
 
Joined
Nov 7, 2007
Messages
32 (0.01/day)
What matters to most consumers is performance per dollar and not how much wafer they get. I have never bought a card based on the size of its wafer. The power efficiency is an important perk though.

Maybe there will be a new review category- "wafer per dollar".

Or maybe no one really cares about wafer size at all.

Personally, I don't care if AMD or NVIDIA figure out how to get their performance off parts with 3 transistors that cost them fifty cents to make. If the part offers more performance than the old high end, uses less power and gives off less heat, it's worth the money to me.

Some seem to be arguing against NVIDIA finding a way to maintain their margins and profitability. What would they prefer? For NVIDIA to be going broke like AMD? That can't be in the best interest of gaming.

As $330 GTX970s outperform $500 290Xs at better power/heat/thermals, one could say that AMD is now robbing consumers. Giving them less desirable performance everywhere that matters for 50% more cash. Getting more wafer for that $170 wouldn't be a key purchase factor for me.
 
Joined
Oct 15, 2010
Messages
951 (0.19/day)
System Name Little Boy / New Guy
Processor AMD Ryzen 9 5900X / Intel Core I5 10400F
Motherboard Asrock X470 Taichi Ultimate / Asus H410M Prime
Cooling ARCTIC Liquid Freezer II 280 A-RGB / ARCTIC Freezer 34 eSports DUO
Memory TeamGroup Zeus 2x16GB 3200Mhz CL16 / Teamgroup 1x16GB 3000Mhz CL18
Video Card(s) Asrock Phantom RX 6800 XT 16GB / Asus RTX 3060 Ti 8GB DUAL Mini V2
Storage Patriot Viper VPN100 Nvme 1TB / OCZ Vertex 4 256GB Sata / Ultrastar 2TB / IronWolf 4TB / WD Red 8TB
Display(s) Compumax MF32C 144Hz QHD / ViewSonic OMNI 27 144Hz QHD
Case Phanteks Eclipse P400A / Montech X3 Mesh
Power Supply Aresgame 850W 80+ Gold / Aerocool 850W Plus bronze
Mouse Gigabyte Force M7 Thor
Keyboard Gigabyte Aivia K8100
Software Windows 10 Pro 64 Bits
Personally I'm just excited to see products this good this cheap.

The GK series chips were great, but fairly costly at first. (pre-GTX780 launch)

The R290X was a face plant launch. Sure, it competed, but the OEM design was a hairdryer.

I disagree on the one company winning harms us.

Intel has had no competition for many years, but they have to sell us better parts at a price we'll pay to keep the doors open.

Unless you think they're saying "Gee fellas if we DON'T sell our bada$$ chips for $300, people will buy FX-8350s!"? LOL- like that would happen.

I knew you were goin to pull out that intel stuff, you see, since intel got the core arch out, they have been incredibly slow to increase the performance, so slow that i have a 4-year old cpu, and it still is going strong as to i don't need to replace it even for 2 more years.....competition is what brings archs like nehalem over netburst.
 
Joined
Jun 28, 2014
Messages
2,388 (0.67/day)
Location
Shenandoah Valley, Virginia USA
System Name Home Brewed
Processor i9-7900X and i7-8700K
Motherboard ASUS ROG Rampage VI Extreme & ASUS Prime Z-370 A
Cooling Corsair 280mm AIO & Thermaltake Water 3.0
Memory 64GB DDR4-3000 GSKill RipJaws-V & 32GB DDR4-3466 GEIL Potenza
Video Card(s) 2X-GTX-1080 SLI & 2 GTX-1070Ti 8GB G1 Gaming in SLI
Storage Both have 2TB HDDs for storage, 480GB SSDs for OS, and 240GB SSDs for Steam Games
Display(s) ACER 28" B286HK 4K & Samsung 32" 1080P
Case NZXT Source 540 & Rosewill Rise Chassis
Audio Device(s) onboard
Power Supply Corsair RM1000 & Corsair RM850
Mouse Generic
Keyboard Razer Blackwidow Tournament & Corsair K90
Software Win-10 Professional
Benchmark Scores yes
I have never bought a card based on the size of its wafer.

Me neither,...................I just buy the most performance & features that I can afford at the time I'm buying a GPU. I read reviews from about four tech sites that let me know if a part has any problems, and I rule out some GPUs based on that.
I'm still new to TPU, but I like the reviews here so far.

My two GTX-570s were great when I bought them years ago. My two GTX-680s were even better and together, they still deliver good performance.
I bought two R9-280X OC GPU's and never looked back. They're pretty good cards, and worth every penny spent.

My latest buy is a single 4GB GTX-760 and that's going into a M-ITX build with room for just one GPU. These new NVIDIA offerings are something to look forward to.
 
Joined
Nov 7, 2007
Messages
32 (0.01/day)
I knew you were goin to pull out that intel stuff, you see, since intel got the core arch out, they have been incredibly slow to increase the performance, so slow that i have a 4-year old cpu, and it still is going strong as to i don't need to replace it even for 2 more years.....competition is what brings archs like nehalem over netburst.

I could have sworn it was a combination of engineering breakthroughs and invention.

Are you implying NVIDIA would have released Maxwell three years ago if AMD had a chip at this level three years ago, because "competition" drove them to it?

I have to differ. AMD would be launching a Maxwell-esque this week if that were true. I think they're "going" to launch a revision of 290X with a water cooler and some minor manufacturing process improvements instead, and give away games with it.

Why isn't competition driving them to catch up with intel? Surely intel has been beating them down for years and years, that competition should have drove them to innovate a better arch than Faildozer?
 
Joined
Oct 15, 2010
Messages
951 (0.19/day)
System Name Little Boy / New Guy
Processor AMD Ryzen 9 5900X / Intel Core I5 10400F
Motherboard Asrock X470 Taichi Ultimate / Asus H410M Prime
Cooling ARCTIC Liquid Freezer II 280 A-RGB / ARCTIC Freezer 34 eSports DUO
Memory TeamGroup Zeus 2x16GB 3200Mhz CL16 / Teamgroup 1x16GB 3000Mhz CL18
Video Card(s) Asrock Phantom RX 6800 XT 16GB / Asus RTX 3060 Ti 8GB DUAL Mini V2
Storage Patriot Viper VPN100 Nvme 1TB / OCZ Vertex 4 256GB Sata / Ultrastar 2TB / IronWolf 4TB / WD Red 8TB
Display(s) Compumax MF32C 144Hz QHD / ViewSonic OMNI 27 144Hz QHD
Case Phanteks Eclipse P400A / Montech X3 Mesh
Power Supply Aresgame 850W 80+ Gold / Aerocool 850W Plus bronze
Mouse Gigabyte Force M7 Thor
Keyboard Gigabyte Aivia K8100
Software Windows 10 Pro 64 Bits
I could have sworn it was a combination of engineering breakthroughs and invention.

Are you implying NVIDIA would have released Maxwell three years ago if AMD had a chip at this level three years ago, because "competition" drove them to it?

I have to differ. AMD would be launching a Maxwell-esque this week if that were true. I think they're "going" to launch a revision of 290X with a water cooler and some minor manufacturing process improvements instead, and give away games with it.

Why isn't competition driving them to catch up with intel? Surely intel has been beating them down for years and years, that competition should have drove them to innovate a better arch than Faildozer?

Maybe not three years earlier but definetly sooner.

Remember when AMD was nothing and intel was everithing? rest my case.
 
Top