Compute & Synthetics

Shifting gears, we'll look at the compute and synthetic aspects of the GTX 1660 Ti.

Beginning with CompuBench 2.0, the latest iteration of Kishonti's GPU compute benchmark suite offers a wide array of different practical compute workloads, and we’ve decided to focus on level set segmentation, optical flow modeling, and N-Body physics simulations.

Compute: CompuBench 2.0 - Level Set Segmentation 256

Compute: CompuBench 2.0 - N-Body Simulation 1024K

Compute: CompuBench 2.0 - Optical Flow

On paper, the GTX 1660 Ti looks to provide around 85% of the RTX 2060's compute and shading throughput; for Compubench, we see it achieving around 82% of the latter's performance.

Moving on, we'll also look at single precision floating point performance with FAHBench, the official Folding @ Home benchmark. Folding @ Home is the popular Stanford-backed research and distributed computing initiative that has work distributed to millions of volunteer computers over the internet, each of which is responsible for a tiny slice of a protein folding simulation. FAHBench can test both single precision and double precision floating point performance, with single precision being the most useful metric for most consumer cards due to their low double precision performance.

Compute: Folding @ Home Single Precision

Next is Geekbench 4's GPU compute suite. A multi-faceted test suite, Geekbench 4 runs seven different GPU sub-tests, ranging from face detection to FFTs, and then averages out their scores via their geometric mean. As a result Geekbench 4 isn't testing any one workload, but rather is an average of many different basic workloads.

Compute: Geekbench 4 - GPU Compute - Total Score

In lieu of Blender, which has yet to officially release a stable version with CUDA 10 support, we have the LuxRender-based LuxMark (OpenCL) and V-Ray (OpenCL and CUDA).

Compute/ProViz: LuxMark 3.1 - LuxBall and Hotel

Compute/ProViz: V-Ray Benchmark 1.0.8

We'll also take a quick look at tessellation performance.

Synthetic: TessMark, Image Set 4, 64x Tessellation

Finally, for looking at texel and pixel fillrate, we have the Beyond3D Test Suite. This test offers a slew of additional tests – many of which we use behind the scenes or in our earlier architectural analysis – but for now we’ll stick to simple pixel and texel fillrates.

Synthetic: Beyond3D Suite - Pixel Fillrate

Synthetic: Beyond3D Suite - Integer Texture Fillrate (INT8)

Synthetic: Beyond3D Suite - Floating Point Texture Fillrate (FP32)

The practically identical pixel fill rates for the GTX 1660 Ti and RTX 2060 might seem odd at first blush, but it is an entirely expected result as both GPUs have the same number of ROPs, similar clockspeeds, same GPC/TPC setup, and similar memory configurations. And being the same generation/architecture, there aren't any changes or improvements to DCC. In the same vein, the RTX 2060 puts up a 25% higher texture fillrate over the GTX 1660 Ti as a consequence of having 25% more TMUs (96 vs 120).

 

Total War: Warhammer II Power, Temperature, and Noise
POST A COMMENT

157 Comments

View All Comments

  • Fallen Kell - Friday, February 22, 2019 - link

    I don't have any such hopes for Navi. The reason is that AMD is still competing for the console and part of that is maintaining backwards compatibility for the next generation of consoles with the current gen. This means keeping all the GCN architecture so that graphics optimizations coded into the existing games will still work correctly on the new consoles without the need for any work. Reply
  • GreenReaper - Friday, February 22, 2019 - link

    Uh... I don't think that follows. Yes, it will be a bonus if older games work well on newer consoles without too much effort; but with the length of a console refresh cycle, one would expect a raw performance improvement sufficient to overcome most issues. But it's not as if when GCN took over from VLIW, older games stopped working; architecture change is hidden behind the APIs. Reply
  • Korguz - Friday, February 22, 2019 - link

    Fallen Kell
    " The reason is that AMD is still competing for the console and part of that is maintaining backwards compatibility for the next generation of consoles with the current gen. "
    prove it... show us some links that state this
    Reply
  • Korguz - Friday, February 22, 2019 - link

    CiccioB
    " GCN was dead at its launch time"
    prove it.. links showing this, maybe .....
    Reply
  • CiccioB - Saturday, February 23, 2019 - link

    Aahahah.. prove it.
    9 years of discounted sell are not enough to show you that GCN simply started as half a generation old architecture to end as a generation obsolete one?
    Yes, you may recall the only peak glory in GCN life, that is Hawaii, which was so discounted that made nvidia drop the price of their 780Ti. After that move AMD just brought up a fail after the other, starting with Fiji and it's monster BOM cost just to reach the much cheaper GM200 based cards and following with Polaris (yes, the once labeled "next AMD generation is going to dominate") and then again with Vega and Vega VII is not different.

    What have you not understood that AMD has to use whatever technology available to get a performance near that of a 2080? What do you think will be the improvements nvidia will achieve once they will move to 7nm (or 7nm+)?

    Today AMD is incapable to get to nvidia performances and they also lack their modern features. GCN at 7nm can be as fast a a 1080Ti that is 3 years older. Despite the AMD card still uses more power, which still shows how inefficient GCN architecture is.

    That's why I hope Navi is a real improvement, or we will be left with nvidia monopoly as at 7nm it will really have more than generation of advantage, seen it will be much more efficient and still having new features that AMD will then add only in 3 or 4 years from now.
    Reply
  • Korguz - Saturday, February 23, 2019 - link

    links to what you stated ??? sounds a little like just your opinion, with no links....

    considering that AMD doesnt have the deep pockets that Nvidia has, or the part that amd has to find the funds to R&D BOTH gpus, AND gpus, while nvida can put all the funds that can into R&D, it seems to me that AMD has done ok for that that have had to to work with over the years, with Zen doing well in the CPU space, they might start to have a little more funds to put back into their products, and while i havent read much about Navi, i am also hopeful that it may give nvidia some competition, as we sure do need it...
    Reply
  • CiccioB - Monday, February 25, 2019 - link

    It seems you lack the basic intelligence to understand the facts that can be seen by anyone else.
    You just have hopes that are based on "your opinion", not facts.
    "they might start to have a little more funds to put back into their products". Well, last quarter with Zen selling like never before they managed to have a 28 millions net income.
    Yes, you read right. 28. Nvidia with all its problems got more than 500. Yes, you read right. About 20 times more.
    The facts are 2 (this are numbers based on facts, not opinion, and you can create interpretations on facts, not your hopes of the future):
    - AMD is selling Ryzen CPU at a discount like GPUs and boths have a 0.2% net margin
    - The margins they have on CPU can't compensate the looses they have in the GPU market, and seen that they manage to make some money with console only when there are some spike of requests, I am asking you when and from what AMD will get new funds to pay something.
    You see, it's not that really "a hope" believing that AMD is loosing money for every Vega they sell seen the cost of the BOM with respect to the costs of the competition. Negating this is a "hope it is not real", not a sensible way to ask for "facts".

    You have to know at least basic facts before coming here to ask for links on basic things that everyone that knows this market already knows.
    If you want to start looking less idiot than you do by asking constantly for "proves and links", just start reading quarter results and see what are the effects of the long period strategies both companies have achieved.

    Then, if you have a minimum of technical competence (which I doubt) look at what AMD does with its mm^2 and Watts and what nvidia does.
    Then come again to ask for "links" where I can tell you that AMD architecture is one generation behind (and will be probably left once nvidia will pass to 7nm.. unless Navi is not GCN).

    Do you have other intelligent questions to pose?
    Reply
  • Korguz - Wednesday, February 27, 2019 - link

    right now.. your facts.. are also just your opinion, i would like to see where you get your facts, so i can see the same, thats why i asked for links...
    again.. AMD is fighting 2 fronts, CPUs AND gpus.. Nvida.. GPU ONLY, im not refuting your " facts " about how much each is earning...its obvious... but.. common sense says.. if one company has " 20 times " more income then the other.. then they are able to put more back into the business, then the other... that is why, for the NHL at least, they have have salary caps, to level the playing field so some teams, cant " buy " their way to winning... thats just common sense...
    " AMD is selling Ryzen CPU at a discount like GPUs and boths have a 0.2% net margin "
    and where did you read this.. again.. post a link so we can see the same info... where did you read how much it costs AMD to make losing money on each Vega GPU ?? again.. post links so we can see the SAME info you are...
    " You have to know at least basic facts before coming here to ask for links on basic things that everyone that knows this market already knows. " and some would like to see where you get these " facts " that you keep talking about... thats basic knowledge.

    " if you have a minimum of technical competence " actually.. i have quite a bit of technical competence, i build my own comps, even work on my own car when i am able to. " look at what AMD does with its mm^2 and Watts and what nvidia does. " that just shows nvidia's architecture is just more efficient, and needs less power for that it does...

    lastly.. i have been civil and polite to you in my posts.. resorting to name calling and insults, does not prove your points, or make your supposed " facts " and more real. quite frankly.. resorting to name calling and insults, just shows how immature and childish you are.. that is a fact
    Reply
  • CiccioB - Thursday, February 28, 2019 - link

    where did you read how much it costs AMD to make losing money on each Vega GPU ??

    Did you read last (and understood) AMD latest quarter results?
    Have you seen the total cost of production and the relative net income?
    Have you an idea of how the margin is calculated (yes, it takes into account the production costs that are reported in the quarter results)?
    Have you understood half of what I have written when based on facts that AMD just made $28 of NET income last quarter there are 2 possible ways of seeing the cause of those pitiful numbers? One is that AMD is discounting every product (GPU and CPU) to a ridiculous margin, the other that Zen is sold at a profit while GPUs are not? Or you may try to hypnotize the third view, that they are selling Zen at a loss and GPU with a big margin. Anything is good, but at leas one of these is true. Take the one you prefer and then try to think which one requires less artificial hypothesis to be true (someone once said that the best solution is most often the most simple one).
    that just shows nvidia's architecture is just more efficient, and needs less power for that it does

    That demonstrates that nvidia architecture is simply one generation head, as what changes from a generation to the other is usually the performance you can get from a certain die are which sucks a certain amount of energy and just is the reason because a x80 level card today costs >$1000. If you can get the same 1080Ti performance (and so I'm not considering the new features nvidia has added to Turing) by using a complete new PP node, more current and HBM just 3 years later, then you may arrive at the conclusion that something is not working correctly on what you have created.

    So my statement that GCN was dead at launch (when a 7970 was on par with a GTX680 which was smaller and uses much less energy) just finds it perfect demonstration in Vega 20 where GCN is simply 3 years back with a BOM costing at least twice that of the 1080Ti (and still using more energy).

    Now, if you can't understand the minimum basic facts and your hope is that their interpretation using a completely genuine and coherent thesis is wrong and requires "fact and links", than it is no my problem.
    Continue to hope that what I wrote is totally rubbish and that you are the one with the right answer to this particular situation. However what I said is completely coherent with t e facts that we have been witnessing from GCN launch up to now.
    Reply
  • Korguz - Friday, March 1, 2019 - link

    " Have you seen the total cost of production and the relative net income? "
    no.. thats is why i asked you to post where you got this from, so i can see the same info, what part do YOU not understand ?
    " based on facts that AMD just made $28 of NET income last quarter" because you continue to refuse to even mention where you get these supposed facts from, i think your facts, are false.
    " One is that AMD is discounting every product (GPU and CPU) to a ridiculous margin"
    and WHERE have you read this??? has any one else read this, and can verify it?? i sure dont remember reading anything about this, any where

    what does being hypnotized have to do with anything ?? do you even know what hypnotize means ?
    just in case, this is what it means :
    to put in the hypnotic state.
    to influence, control, or direct completely, as by personal charm, words, or domination: The speaker hypnotized the audience with his powerful personality.

    again.. resorting to being insulting means you are just immature and childish....

    look.. you either post links, or mention where you are getting your facts and info from, so i can also see the SAME facts and info with out having to spend hours looking.. so i can make the the same conclusions, or, admit, you CANT post where you get your facts and info from, because, they are just your opinion, and nothing else.. but i guess asking a child to mention where they get their facts and info from, so one can then see the same facts and info, is just to much to ask...
    Reply

Log in

Don't have an account? Sign up now