XFX Radeon RX 5600 XT THICC 3 review
Fractal Design Define 7 XL review
Guru3D Rig of the Month - January 2020
Palit GeForce RTX 2070 SUPER GamingPro review
Team Group T-Force DarkZα 3600 MHz DDR4 review
Corsair Scimitar Elite RGB gaming mouse review
Cougar 700K Evo keyboard review
Aorus Liquid Cooler 360 review
AMD Ryzen Threadripper 3990X review
Corsair A500 CPU air cooler review
NVIDIA Pascal GP104 Die Photo
Last week Nvidia announced the Tesla P100 data-center GPU and if you looked closely at the photo's you could already clearly see that big Pascal 15B transistor GPU being used. A new photo this time showing the GP104 GPU (successor to the GM204 = GTX 970/980).
According to the leak the photo shown below is the GP104 (GM204 successor) intended for Nvidia's pending high-end products, and it measures roughly 290-300mm². At the right side you can see Samsung K4G80325FB - 1.5V 8Gb 8Gbps (8000MHz) GDDR5. Word on the street is that this GPU would hold 2560 shader processors.
The rectangular die of the GP104 was measured at 15.35 mm x 19.18 mm which should house (very speculative) a transistor-count of 7.4~7.9 billion. Interesting to see is that this chip is tied towards Samsung 8-gigabit GDDR5 memory chips. These ICs run an effective speed of 8 GHz (GDDR5 and thus not GDDR5X). At 256-bit you'ld be looking at 256 GB/s of bandwidth. The shader processor core count of the GP104 could be closer to 2,560, than the 4,096 from an older report.
Earlier on it was speculated that graphics cards based on these GPUs would be called X70 and X80, the specs do not meet up even slightly though.
Judge rules that Samsung and Qualcomm do not violate Nvidia patents - 10/12/2015 08:10 AM
According to a judge ruling from the International Trade Commission, Samsung and Qualcomm do not violate Nvidia patents. Nvidia released this news themselves on their blog. Nvidia will appeal this r...
AMD and Nvidia prep for next-gen DirectX 12 - 03/24/2015 10:19 AM
Several new sets of slides from AMD and Nvidia as well surfaced on the webs through slideshare, the decks show what the companies have been up to in regards to DirectX 12, and they do look pretty exc...
Nvidia PhysX Source Code Now Available Free - 03/06/2015 08:03 AM
NVIDIA today put more than a decade of research, development and investment in gaming physics into the hands of game developers – by offering free source code for NVIDIA PhysX on GitHub. Thi...
New Nvidia PhysX FleX features - 12/11/2014 09:20 AM
PhysX FleX is a particle based simulation technique for real-time visual effects. So far we showed examples for rigid body stacking, particle piles, soft bodies and fluids. In this video we'll be sho...
Ubisoft and NVIDIA Partner Up for Assassin's Creed Unity Far Cry 4 And More - 06/05/2014 08:03 AM
Ubisoft and NVIDIA today announced the next chapter in their strategic partnership bringing amazing PC gaming experiences to life in Ubisoft's highly anticipated upcoming titles including Assassin's...
PrMinisterGR
Senior Member
Posts: 7005
Joined: 2014-09-27
Senior Member
Posts: 7005
Joined: 2014-09-27
#5256549 Posted on: 04/11/2016 03:46 PM
This is such complete speculation. It all depends on the clocks too. This is more or less a shrunk 980Ti. If it hits 2GHz then it's fine.
This is such complete speculation. It all depends on the clocks too. This is more or less a shrunk 980Ti. If it hits 2GHz then it's fine.
xIcarus
Senior Member
Posts: 941
Joined: 2010-08-24
Senior Member
Posts: 941
Joined: 2010-08-24
#5256555 Posted on: 04/11/2016 03:57 PM
Word. The 950 should not get the GTX badge.
But at least they dropped the GT vs Ultra suffixes, those were a bit confusing.
It should be as it was with the 500 series. 550 and under was GT, 560 and above was GTX.
At least they're not overinflating their numbers like AMD does. 7850, 7870, 7950, 7970, 7990. Versus 650, 660, 670, 680, 690. WTF srsly. It's very confusing and even now I have to look up benchmarks every damn time I want to compare the cards.
I don't see the problem as the GTX brand has been diluted to the point of being meaningless. It used to be only the high end models were GTX, like *70 and *80 series cards. Now you have GTX 950's out the *ss. Seriously? It's a 950.
Word. The 950 should not get the GTX badge.
But at least they dropped the GT vs Ultra suffixes, those were a bit confusing.
It should be as it was with the 500 series. 550 and under was GT, 560 and above was GTX.
At least they're not overinflating their numbers like AMD does. 7850, 7870, 7950, 7970, 7990. Versus 650, 660, 670, 680, 690. WTF srsly. It's very confusing and even now I have to look up benchmarks every damn time I want to compare the cards.
rl66
Senior Member
Posts: 2288
Joined: 2007-05-31
Senior Member
Posts: 2288
Joined: 2007-05-31
#5256645 Posted on: 04/11/2016 06:49 PM
I haven't seen conclusive proof that HBM actually helps the Fury X to a tangible level. If anyone has such proof, please share it with me.
yes obviously it push to the top, but sadly for us AMD have made terrible choise of HBM1 wich is limited to 4gb...
so the perf are crippled due to lack of ramspace (and in some case even the previous gen high end do better).
now about the "GDDR5 only" drama: on pict i just see prototype or sample, if it work with GDDR5 then it work with GDDR5X too, it's pin to pin compatible (i can already smell old GPU stock with GDDR5X and a new name... lol).
and GDDR5X is clearly nice ram, and cost less than HBM2 (that will be used for high end in red and green flavor for sure).
"don't sell bear's skin before getting it first" none GPU from neither company are ready... let them come out and tested
I haven't seen conclusive proof that HBM actually helps the Fury X to a tangible level. If anyone has such proof, please share it with me.
yes obviously it push to the top, but sadly for us AMD have made terrible choise of HBM1 wich is limited to 4gb...
so the perf are crippled due to lack of ramspace (and in some case even the previous gen high end do better).
now about the "GDDR5 only" drama: on pict i just see prototype or sample, if it work with GDDR5 then it work with GDDR5X too, it's pin to pin compatible (i can already smell old GPU stock with GDDR5X and a new name... lol).
and GDDR5X is clearly nice ram, and cost less than HBM2 (that will be used for high end in red and green flavor for sure).
"don't sell bear's skin before getting it first" none GPU from neither company are ready... let them come out and tested
rl66
Senior Member
Posts: 2288
Joined: 2007-05-31
Senior Member
Posts: 2288
Joined: 2007-05-31
#5256654 Posted on: 04/11/2016 07:08 PM
GTX mean gaming
not only high end at 4K over 100fps
there is some that doesn't need so much power (and money lol)
the gtx950 is aimed at 1080 60fps for Moba and game like WoT etc... and it does this pretty well, and even in some top game from last year it perform really well (i was clearly impress the 1st time i pair it with I3... you get a lot for the money... i understand their success).
it is not high end GPU but clearly a GTX.
I don't see the problem as the GTX brand has been diluted to the point of being meaningless. It used to be only the high end models were GTX, like *70 and *80 series cards. Now you have GTX 950's out the *ss. Seriously? It's a 950.
GTX mean gaming
not only high end at 4K over 100fps
there is some that doesn't need so much power (and money lol)
the gtx950 is aimed at 1080 60fps for Moba and game like WoT etc... and it does this pretty well, and even in some top game from last year it perform really well (i was clearly impress the 1st time i pair it with I3... you get a lot for the money... i understand their success).
it is not high end GPU but clearly a GTX.
Shadowdane
Senior Member
Posts: 1309
Joined: 2004-02-14
Senior Member
Posts: 1309
Joined: 2004-02-14
#5256660 Posted on: 04/11/2016 07:19 PM
I kinda get the feeling big Pascal GP100 will be only for Tesla GPUs. Those big chips are just too expensive to sell for consumer gear. The DX-1 box costs around $130,000 with 8 of those GPUs. If you cut off around $30K for the other server components, your looking around $12,500 per GPU! I don't think we'll see anything like this chip for consumers until 16nm process is mature. I bet the chip yields are horrible right now, hence why they cost a fortune.
I bet the GP104 chip will be a different design entirely. Well still based off the GP100 but with some changes. They will probably kill all the Double Precision (DP) units, games don't really make use of that hardware. That silicon space would be much better utilized for Single Precision (SP) shader cores. Currently half of the silicon space on the GP100 is used for DP units, using that space for SP units would be a much better design for a gaming GPU.
I kinda get the feeling big Pascal GP100 will be only for Tesla GPUs. Those big chips are just too expensive to sell for consumer gear. The DX-1 box costs around $130,000 with 8 of those GPUs. If you cut off around $30K for the other server components, your looking around $12,500 per GPU! I don't think we'll see anything like this chip for consumers until 16nm process is mature. I bet the chip yields are horrible right now, hence why they cost a fortune.
I bet the GP104 chip will be a different design entirely. Well still based off the GP100 but with some changes. They will probably kill all the Double Precision (DP) units, games don't really make use of that hardware. That silicon space would be much better utilized for Single Precision (SP) shader cores. Currently half of the silicon space on the GP100 is used for DP units, using that space for SP units would be a much better design for a gaming GPU.
MrBonk
Senior Member
Posts: 3022
Joined: 2012-02-02
Senior Member
Posts: 3022
Joined: 2012-02-02
#5256750 Posted on: 04/11/2016 11:37 PM
Guess i'll be waiting for the 1080/x80 Ti then. Hopefully AMD has a better product or comparable one so the price isn't super high.
I kinda get the feeling big Pascal GP100 will be only for Tesla GPUs. Those big chips are just too expensive to sell for consumer gear. The DX-1 box costs around $130,000 with 8 of those GPUs. If you cut off around $30K for the other server components, your looking around $12,500 per GPU! I don't think we'll see anything like this chip for consumers until 16nm process is mature. I bet the chip yields are horrible right now, hence why they cost a fortune.
I bet the GP104 chip will be a different design entirely. Well still based off the GP100 but with some changes. They will probably kill all the Double Precision (DP) units, games don't really make use of that hardware. That silicon space would be much better utilized for Single Precision (SP) shader cores. Currently half of the silicon space on the GP100 is used for DP units, using that space for SP units would be a much better design for a gaming GPU.
Yeah, but by default. Workstation GPUs automatically cost more just because they can. They have ECC and other features not used on Consumer cards.
Trust me, there's no way Tesla cards actually cost 12k$ to make. They probably cost a fraction of that.
Guess i'll be waiting for the 1080/x80 Ti then. Hopefully AMD has a better product or comparable one so the price isn't super high.
I kinda get the feeling big Pascal GP100 will be only for Tesla GPUs. Those big chips are just too expensive to sell for consumer gear. The DX-1 box costs around $130,000 with 8 of those GPUs. If you cut off around $30K for the other server components, your looking around $12,500 per GPU! I don't think we'll see anything like this chip for consumers until 16nm process is mature. I bet the chip yields are horrible right now, hence why they cost a fortune.
I bet the GP104 chip will be a different design entirely. Well still based off the GP100 but with some changes. They will probably kill all the Double Precision (DP) units, games don't really make use of that hardware. That silicon space would be much better utilized for Single Precision (SP) shader cores. Currently half of the silicon space on the GP100 is used for DP units, using that space for SP units would be a much better design for a gaming GPU.
Yeah, but by default. Workstation GPUs automatically cost more just because they can. They have ECC and other features not used on Consumer cards.
Trust me, there's no way Tesla cards actually cost 12k$ to make. They probably cost a fraction of that.
Denial
Senior Member
Posts: 12568
Joined: 2004-05-16
Senior Member
Posts: 12568
Joined: 2004-05-16
#5256755 Posted on: 04/11/2016 11:51 PM
Guess i'll be waiting for the 1080/x80 Ti then. Hopefully AMD has a better product or comparable one so the price isn't super high.
Yeah, but by default. Workstation GPUs automatically cost more just because they can. They have ECC and other features not used on Consumer cards.
Trust me, there's no way Tesla cards actually cost 12k$ to make. They probably cost a fraction of that.
They obviously cost a fraction of that, but the point is yields at the start of a new node, especially 600mm2 chip, are going to be really low. You're going to lose over 75% of a wafer. High margins will offset that, which is why they are reserving GP100's to high margin products at the start of production.
Guess i'll be waiting for the 1080/x80 Ti then. Hopefully AMD has a better product or comparable one so the price isn't super high.
Yeah, but by default. Workstation GPUs automatically cost more just because they can. They have ECC and other features not used on Consumer cards.
Trust me, there's no way Tesla cards actually cost 12k$ to make. They probably cost a fraction of that.
They obviously cost a fraction of that, but the point is yields at the start of a new node, especially 600mm2 chip, are going to be really low. You're going to lose over 75% of a wafer. High margins will offset that, which is why they are reserving GP100's to high margin products at the start of production.
xIcarus
Senior Member
Posts: 941
Joined: 2010-08-24
Senior Member
Posts: 941
Joined: 2010-08-24
#5257481 Posted on: 04/13/2016 02:08 PM
Wow I never thought of that, it makes perfect sense. They can still make great profit this way.
They obviously cost a fraction of that, but the point is yields at the start of a new node, especially 600mm2 chip, are going to be really low. You're going to lose over 75% of a wafer. High margins will offset that, which is why they are reserving GP100's to high margin products at the start of production.
Wow I never thought of that, it makes perfect sense. They can still make great profit this way.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 191
Joined: 2007-05-26
I don't see the problem as the GTX brand has been diluted to the point of being meaningless. It used to be only the high end models were GTX, like *70 and *80 series cards. Now you have GTX 950's out the *ss. Seriously? It's a 950.