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
Comments Locked

157 Comments

View All Comments

  • CiccioB - Tuesday, March 5, 2019 - link

    Kid, as I said you lack basic intelligence to recognize when you are just arguing about nothing.
    The number I'm using are those published by AMD and nvidia in their quarter results.
    Now, if you are asking me the links for those reports it means you don't have the minimum idea of what I'm talking about AND you cannot do a simple search with Google.
    So I stand my "insults": you have not the intelligence to argue about this simple topic, so stop writing completely on this site that has much better readers than you and is not gaining anything by your presence.
  • Korguz - Tuesday, March 5, 2019 - link

    ahh here are the insults and name calling... and you are calling me a kid ??

    i can, and have done a simple google search.. BUT, i would like to see the SAME info YOU are looking at as well, but again.. i guess that is just too much to ask of you, is it wrong to want to be able to compare the same facts as you are looking at ? i guess so.. cause you STILL refuse to post where you get your facts and info from, i sure dont have the time so spend who knows how long to do a simple google search...

    by standing by our insults, just shows YOU are the child here.. NOT me, as only CHILDREN resort to insults and name calling...

    as i said in my reply farther down :
    you refuse post links, OR mention your sources, simply because YOU DONT HAVE ANY.. most of what you post.. is probably made up, or rumor, if AT posted things like you do, with no sources, you probably would be all over them asking for links, proof and the like... and by YOUR previous posts, all of your info is made up and false..

    maybe YOU should stop posting your info and facts from rumor sites, and learn to talk with some intelligence your self.
  • Qasar - Tuesday, March 5, 2019 - link

    sorry CiccioB, but i agree with Korguz.. i have tried to find the " facts " on some of the things you have posted in this thread.. and i cant find them.. i also would like to know where you get your " opinions " from.
  • CiccioB - Wednesday, March 6, 2019 - link

    Quarter results!
    It's not really difficult to find them..
    Try "AMD quarter results" and then "nvidia quarter results" in Google search engine and.. voilà, les jeux sont faits. Two clicks and you can read them. Back some years if you want,so you can have a history of what has happened during the last years apart the useless comments by fanboys you find on forums.
    Now, if you have further problems at understanding all those tables and numbers or you do not know what is a gross margin vs a net income, then, you can't come here and argue I have no facts. It's you that can't understand publicly available data.

    So if you want already chewed numbers that someone has interpreted for you, you can read them here:
    https://www.anandtech.com/show/13917/amd-earnings-...

    I wonder what you were looking for for not finding those numbers that have been commented by every site that is about technology.

    @Korguz
    You a re definitely a kid. You surely do not scare me with all those nonsense you write when the solution for YOUR problem (not mine) was simply to read more and write less.
  • Korguz - Thursday, March 7, 2019 - link

    CiccioB you are hilarious !!!
    did you look up the word hypnotize, to see what it means, and how it even relates to this ? as, and i quote YOU " Or you may try to hypnotize the third view " what does that even mean ??

    i KNEW the ONLY link you would mention.. is the EASY one to find.

    BUT... what about all of these LIES :

    " GCN was dead at its launch time"
    " 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? "
    " that is Hawaii, which was so discounted "
    " starting with Fiji and it's monster BOM cost "
    " AMD is selling Ryzen CPU at a discount like GPUs and both have a 0.2% net margin "
    " One is that AMD is discounting every product (GPU and CPU) to a ridiculous margin "
    " a "panic plan" that required about 3 years to create the chips. 3 years ago they already know that they would have panicked at the RTX cards launch and so they made the RT-less chip as well "

    i did the simple google search for the above comments from you, as well as variations.. and guess what.. NOTHING comes up. THESE are the links i would like you to provide, as i cant find any of these LIES . so " It's you that can't understand publicly available data. " the above quotes, are not publicly available data, even your sacred " simple google search " cant find them.

    lastly.. your insults and name calling ( and the fact that you stand by them ).. the only people i hear things like this from.. are from my friends and coworkers TEENAGE CHILDREN. NOT adults.. adults don't resort to things like this, at least the ones that i know... this alone.. shows how immature and childish you really are... i am pretty sure.. you WILL never post links to 98% of the LIES, RUMORS, or your personal speculation, and opinions, because of the simple fact, you just CAN'T, as your sources for all this... simply doesn't exist.

    when you are able to reply to people with out having to resort to name calling and insults, then maybe you might be taken seriously. till then... you are nothing but a lying, immature child, who needs to grow up, and learn how to talk to other people in a respectful manner... maybe YOU should take your OWN advice, and simply read more and write less. Have a good day.
  • D. Lister - Saturday, February 23, 2019 - link

    @CiccioB

    Navi will still be GCN unfortunately.
  • CiccioB - Monday, February 25, 2019 - link

    If so don't cry if price will remain high (if not higher) for the next 3 years.
    We already know why.
  • Simplex - Friday, February 22, 2019 - link

    "EVGA Precision remains some of the best overclocking software on the market."

    Better than MSI Afterburner?
  • Ryan Smith - Friday, February 22, 2019 - link

    I consider both of them to be in the same tier, for what it's worth.
  • Rudde - Friday, February 22, 2019 - link

    In what way does 12nm FFN improve over 16nm? The transistor density is roughly the same, the frequencies see little to no improvement and the power-efficiency has only seen small improvements. Worse yet, the space used per SM has gotten worse. I do know that Turing brings architectural improvements, but are they at the cost of die space? Seems odd that Nvidia wouldn't care about die area when their flagships are huge chips that would benefit from a more dense architecture.

    Or could it be that Turing adds some kind of (sparse) logic that they haven't mentioned?

Log in

Don't have an account? Sign up now