Compute

Shifting gears, let’s take a look at compute performance on GTX 1060.

As we already had the chance to categorize the Pascal architecture’s compute performance in our GTX 1080 review, there shouldn’t be any surprises here. But it will be interesting to see whether the GTX 1060’s higher ratio of memory bandwidth per FLOP materially impacts overall compute performance.

Starting us off for our look at compute is LuxMark3.1, the latest version of the official benchmark of LuxRender. LuxRender’s GPU-accelerated rendering mode is an OpenCL based ray tracer that forms a part of the larger LuxRender suite. Ray tracing has become a stronghold for GPUs in recent years as ray tracing maps well to GPU pipelines, allowing artists to render scenes much more quickly than with CPUs alone.

Compute: LuxMark 3.1 - Hotel

While GTX 1060 could hang with GTX 980 in gaming benchmarks, we don’t start off the same way with compute benchmarks, with the last-generation flagship holding about 17% ahead. Unfortunately for NVIDIA, this is about where GTX 1060 needed to be to best RX 480; instead it ends up trailing the AMD competition. Otherwise the performance gain versus the GTX 960 stands at 65%.

For our second set of compute benchmarks we have CompuBench 1.5, the successor to CLBenchmark. CompuBench offers a wide array of different practical compute workloads, and we’ve decided to focus on face detection, optical flow modeling, and particle simulations.

Compute: CompuBench 1.5 - Face Detection

Compute: CompuBench 1.5 - Optical Flow

Compute: CompuBench 1.5 - Particle Simulation 64K

Like with GTX 1080, relative performance is all over the place. GTX 1060 wins with face detection, loses at optical flow, and wins again at particle simulation. Even the gains versus GTX 960 are a bit more uneven, though at the end of the day GTX 1060 ends up being significantly faster than its predecessor with all 3 sub-benchmarks.

Moving on, our 3rd compute benchmark is the next generation release of 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. Each precision has two modes, explicit and implicit, the difference being whether water atoms are included in the simulation, which adds quite a bit of work and overhead. This is another OpenCL test, utilizing the OpenCL path for FAHCore 21.

Compute: Folding @ Home Single Precision

Compute: Folding @ Home Double Precision

Finally, in Folding@Home, we see the usual split between single precision and double precision performance. GTX 1060 is solidly in the lead when using FP32, but NVIDIA’s poor FP64 rate means that if double precision is needed, RX 480 will pull ahead.

Hitman Synthetics
POST A COMMENT

184 Comments

View All Comments

  • lilmoe - Saturday, August 6, 2016 - link

    This is becoming the next "where is Kai" thing. This is getting redundant and, frankly extremely rude. Stop. I started enjoying some of their content AFTER Anand left.

    There's quite a bit of bias, but regulars can ignore all that and focus on the important info they're looking for.

    We made it clear to them that we expect better in terms of quality and timely delivery. I'm sure they listened and took 7 Notes.
    Reply
  • TallestJon96 - Friday, August 5, 2016 - link

    I think this is the best card of NVIDIAs lineup so far. Generationally, it destroys the previous card, which frankly the 960 sucked, especially compared to the 760 or the 970. The 960s only saving grace was the $200 price point. 2gb wasn't good, the 970 crushed it, the 380 was a better deal, and even the 760 beat it sometimes.

    Compared to the 960, its 80% faster, has 3x times the ram, and costs $50 more.

    Most importantly, this card will be a success vecause it is the card that can easily handle 1080p60 at a good price. Like the 970 before it, the gtx 1060 handles 1080p with ease, and will continue to do so with 15% more performance than the 970 and 2gb more ram.

    I will recommend this card to many people.
    Reply
  • fanofanand - Friday, August 5, 2016 - link

    I love that people keep claiming this is a $250 card. Maybe someday, but that day isn't today. Reply
  • bananaforscale - Friday, August 5, 2016 - link

    Maybe it is, excluding (VAT and import) taxes, margins and such. Reply
  • HollyDOL - Saturday, August 6, 2016 - link

    Cheapest model (from Zotac) around here costs $326 :-( Reply
  • eddman - Saturday, August 6, 2016 - link

    There are four $250 1060s on newegg, with the same specs as the FE version. Reply
  • fanofanand - Saturday, August 6, 2016 - link

    You mean the listings titled "out of stock"? Of course there are higher priced versions available. Surprise surprise. Reply
  • eddman - Saturday, August 6, 2016 - link

    As if 480s aren't out of stock. The point is, there ARE $250 1060s. Availability is another matter. Reply
  • bug77 - Monday, August 8, 2016 - link

    It says "ships in 3-5 days" on most of them, so I don't see your problem. Reply
  • Mugur - Sunday, August 7, 2016 - link

    In my country the Zotac mini 1060 is cheaper with the equivalent of 25$ than the cheapest RX 480 8 GB... Reply

Log in

Don't have an account? Sign up now