Monday, June 22nd 2020

NVIDIA GeForce "Ampere" Hits 3DMark Time Spy Charts, 30% Faster than RTX 2080 Ti

An unknown NVIDIA GeForce "Ampere" GPU model surfaced on 3DMark Time Spy online database. We don't know if this is the RTX 3080 (RTX 2080 successor), or the top-tier RTX 3090 (RTX 2080 Ti successor). Rumored specs of the two are covered in our older article. The 3DMark Time Spy score unearthed by _rogame (Hardware Leaks) is 18257 points, which is close to 31 percent faster than the RTX 2080 Ti Founders Edition, 22 percent faster than the TITAN RTX, and just a tiny bit slower than KINGPIN's record-setting EVGA RTX 2080 Ti XC. Futuremark SystemInfo reads the GPU clock speeds of the "Ampere" card as 1935 MHz, and its memory clock at "6000 MHz." Normally, SystemInfo reads the memory actual clock (i.e. 1750 MHz for 14 Gbps GDDR6 effective). Perhaps SystemInfo isn't yet optimized for reading memory clocks on "Ampere."
Source: HardwareLeaks
Add your own comment

67 Comments on NVIDIA GeForce "Ampere" Hits 3DMark Time Spy Charts, 30% Faster than RTX 2080 Ti

#51
Th3pwn3r
cucker tarlsonit was both.
I mean I could understand a $1000 2080Ti cause the competition wasn't there (still isn't 2 yrs later,might not be this year),but for a +30-35% over 1080Ti - not really
How was it disappointing when it was and is still the fastest card available? Some of you guys are so clowny.
Posted on Reply
#52
B-Real
Given that in the biggest performance leaper generation in the past many years (or maybe ever), Pascal, the 1080 was about 35% faster and the 1080Ti was nearly 85% faster than the 980Ti, while in this gen the RTX2080 was 9% faster and the 2080Ti nearly 40% faster than the 1080Ti, I would suggest that this is a 3090 (3080Ti?), and we will get the bigger performance jump when comparing Ray Tracing results. I would be really really suprised to see a performance jump close to Pascal, but we will see.
DJ_CasperWell increase is 22% here. No need to lie. And getting these clocks with 2080 Ti could be made easily especially if you own a waterblock on 2080 Ti
22% is the number when you compare it to the MSI 2080Ti. But its around 30 when you compare it with the reference model.
Posted on Reply
#53
ppn
This is not your regular performance increase. Ampere has 2,57 more transistors in the same area. Same goes for the consumer cards. 13% higher clocks, 3x performance. 3090 is just like GTX 680, this can't be the big chip, that would be 780Ti. Unless 8nm.
Posted on Reply
#54
$ReaPeR$
This is probably the 3090/3080ti and the big performance jump will be in the ray tracing part. The 30% performance jump gets this card in 4k high refresh rate territory which is a niche, so it makes more sense for Nvidia to work more on the ray tracing part this gen.
Posted on Reply
#55
medi01
$ReaPeR$4k high refresh rate territory
Can we get basic things straight on tech savvy forum at least?
Game developers target certain resolution, when developing games, with some GPUs taken as baseline.

So there is some GPU taken as "base", some resolution taken as "base" and some framerate taken as "acceptable".

This happens with nearly all games, because higher framerate is a much harder sell than better graphics.


Now, it comes down to what those base GPU, resolution and framerate are.
I would bet on 5700/2070 to be the "base" Cards and, at best, 1440p to be the target resolution.

Now, 4k is 3840x2160, 1440p is 2650x1440 => 4k has 2.17 times more pixels.
Yet the fastest car on the market, 2080Ti, is only 1.3-1.5 times faster than the cards mentioned above.

Conclusion: 4k on xxxxTi is possible with either older games, that were targeting much more modest hardware, or we will need to wait until game developers will start targeting 4k as a base, to even dream of "high fps 4k" on even the obnoxiously priced GPUs.
Posted on Reply
#56
$ReaPeR$
medi01Can we get basic things straight on tech savvy forum at least?
Game developers target certain resolution, when developing games, with some GPUs taken as baseline.

So there is some GPU taken as "base", some resolution taken as "base" and some framerate taken as "acceptable".

This happens with nearly all games, because higher framerate is a much harder sell than better graphics.


Now, it comes down to what those base GPU, resolution and framerate are.
I would bet on 5700/2070 to be the "base" Cards and, at best, 1440p to be the target resolution.

Now, 4k is 3840x2160, 1440p is 2650x1440 => 4k has 2.17 times more pixels.
Yet the fastest car on the market, 2080Ti, is only 1.3-1.5 times faster than the cards mentioned above.

Conclusion: 4k on xxxxTi is possible with either older games, that were targeting much more modest hardware, or we will need to wait until game developers will start targeting 4k as a base, to even dream of "high fps 4k" on even the obnoxiously priced GPUs.
You're joking right?







so take the 2080 ti perf and add 30% and then tell me that the ampere card cant do 4k high refresh.
Posted on Reply
#57
medi01
$ReaPeR$You're joking right?
Battlefield was released good year before 5700 came to the market.

Which part about "4k is 2.2 times more pixels than 1440p, but 2080Ti is only 1.3-1.5 times faster than 5700/2070" did you not understand?
Posted on Reply
#58
$ReaPeR$
medi01Battlefield was released good year before 5700 came to the market.

Which part about "4k is 2.2 times more pixels than 1440p, but 2080Ti is only 1.3-1.5 times faster than 5700/2070" did you not understand?
which part of the benchmarks did you not understand?
Posted on Reply
#59
ThrashZone
Hi,
Wish they'd just release it
Holding off 20 series has been pretty tough.
Posted on Reply
#60
efikkan
medi01Now, 4k is 3840x2160, 1440p is 2650x1440 => 4k has 2.17 times more pixels.
Yet the fastest car on the market, 2080Ti, is only 1.3-1.5 times faster than the cards mentioned above.

Conclusion: 4k on xxxxTi is possible with either older games, that were targeting much more modest hardware, or we will need to wait until game developers will start targeting 4k as a base, to even dream of "high fps 4k" on even the obnoxiously priced GPUs.
If I may add;
Performance scaling in games highly depends on the game engine. For starters, the fragment/pixel shaders usually accounts for ~70-80% of the GPU workload, and scales pretty much linearly with pixel count. Vertex shaders, tessellation etc. run however independently of resolution. But then there is the LoD algorithm in the game, which may choose to use different assets at different resolutions with the "same" detail level, when games does this, you'll typically see higher resolutions consume a lot more VRAM and lower than linear performance scaling.
Posted on Reply
#61
TheoneandonlyMrK
$ReaPeR$You're joking right?







so take the 2080 ti perf and add 30% and then tell me that the ampere card cant do 4k high refresh.
I think you just proved it wouldn't, only two games there get 120 now , game's are not getting simpler and smaller.
Add 30% and in a fair percentage, they're not going to hit 144Hz.
Still these are rumours, no need to care at this point, hopefully they're sand bagging anyway.
Posted on Reply
#62
$ReaPeR$
theoneandonlymrkI think you just proved it wouldn't, only two games there get 120 now , game's are not getting simpler and smaller.
Add 30% and in a fair percentage, they're not going to hit 144Hz.
Still these are rumours, no need to care at this point, hopefully they're sand bagging anyway.
Mate, the most played fps games destiny, csgo, rainbow 6, etc can be maxed with a 2080 ti. The ampere one would easily keep them in the 120-140 fps if not higher. Other games yes, wouldn't be so easy to push but I was talking specifically about fps games. Maybe it's easier if I express my certainty with a percentage, I'm 90% certain.
Posted on Reply
#63
TheoneandonlyMrK
$ReaPeR$Mate, the most played fps games destiny, csgo, rainbow 6, etc can be maxed with a 2080 ti. The ampere one would easily keep them in the 120-140 fps if not higher. Other games yes, wouldn't be so easy to push but I was talking specifically about fps games. Maybe it's easier if I express my certainty with a percentage, I'm 90% certain.
Ok competitive FPS based game's then, I'm with you, fair enough I agree on those terms.
4k is already far more use able then a lot of people believe tbf, I have gamed at 4k 70% of the game's I try, no chance of high FPS for me though obviously.
A 2080ti is already quite capable ,30% would get all game's to run at 4k, still wouldn't mind more than 30% though, fingers crossed.
Posted on Reply
#64
$ReaPeR$
theoneandonlymrkOk competitive FPS based game's then, I'm with you, fair enough I agree on those terms.
4k is already far more use able then a lot of people believe tbf, I have gamed at 4k 70% of the game's I try, no chance of high FPS for me though obviously.
A 2080ti is already quite capable ,30% would get all game's to run at 4k, still wouldn't mind more than 30% though, fingers crossed.
Exactly. I think this is the 3090 but I could be wrong and this could end up being the 3080. We'll see.
Posted on Reply
#65
John Naylor
I don't see the logic of speculating until Wizzard publishes the review.
Posted on Reply
#66
Fluffmeister
I seem to recall 30% above the two year old 2080 Ti was great for "Big Navi". Now it's no big deal.

One or both are true.
Posted on Reply
#67
$ReaPeR$
FluffmeisterI seem to recall 30% above the two year old 2080 Ti was great for "Big Navi". Now it's no big deal.

One or both are true.
Well.. you know how some tend to change the goal posts.. :rolleyes:
Posted on Reply
Add your own comment
May 18th, 2024 12:26 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts