Compute

Shifting gears, let’s take a look at compute performance on GTX 1080 Ti.

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

The OpenCL situation for NVIDIA right now is a bit weird. The company is in the middle of rolling out OpenCL 2.0 support to their video cards – something that I had actually given up hope on until it happened – and as a result their OpenCL drivers are in a state of flux as company continues to refine their updated driver. The end result is that OpenCL performance has dipped a bit compared to where the GTX 1080 launched at back in May, with said card dropping from 4138 points to 3648 points. Not that the GTX 1080 Ti is too fazed, mind you – it’s still king of the hill by a good degree – but the point is that once NVIDIA gets their drivers sorted out, there’s every reason to believe that NVIDIA can improve their OpenCL performance.

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 LuxMark, CompuBench shows some minor performance regressions on the GTX 1080 as compared to the card’s launch. None the less, this doesn’t do anything to impede the GTX 1080 Ti’s status as the fastest of the GeForce cards. It dominates every sub-benchmark, including Optical Flow, where the original GTX 1080 was unable to pull away from AMD’s last-generation Radeon R9 Fury X.

Hitman Synthetics
Comments Locked

161 Comments

View All Comments

  • mapesdhs - Saturday, March 11, 2017 - link

    It would be delayed for a month by their Customs lunacy. :D
  • Meteor2 - Tuesday, March 14, 2017 - link

    I'd love to see an Anandtech investigation of what pairings of CPU and GPU really do give the best FPS/price ratio. Could a 1080 Ti bottleneck an i5, for an example? Would a 7600 be ok but a 2500 choke?
  • Gc - Thursday, March 9, 2017 - link

    Do Re Mi Fa So La Ti ....
    "Ti" is a clever marketing name for a penultimate card.
    11GB further emphasizes that it is leading buyers toward the ultimate.
  • Ranger1065 - Friday, March 10, 2017 - link

    Great review, well done Anandtech.
  • TheJian - Friday, March 10, 2017 - link

    Should be interesting to see how AMD does with 8GB for Vega.

    Looks like the best Vega can hope for is a tie and they themselves (Raja) said they only had enough software engineers to be working on Vulkan drivers. So that means Dx11/OpenGL and possible DX12 won't be very good, or could take ages to catch up if AMD doesn't make some money to hire more people. I really hope Vega launch doesn't end up like Ryzen (motherboards all over the place having issues, and SMT etc issues in games). I think I'll wait out Vega and maybe even 1080r2 with GDDR5x & faster clocks before jumping. Also have to wait for AMD to fix ryzen if they can. At least the motherboard part, as sites like PCper think the game part will stay the same forever. AMD talking Ryzen rev2 already (that fixes things) makes me think PCper etc are correct.

    Still, an exciting time for hardware and a great time to buy a PC this year. Even the low end is getting a major boost probably. The 1060 is low to me no point in spending under $200 if you want to really game IMHO, faster speeds, GDDR5x, could be interesting. That combo could make a really great HTPC. I wonder how much faster 1060 will get. Pity it seems AMD has no access to GDDR5x as nvidia is using it all.

    Just read Hardocp's review, 30-35% faster than 1080. Much the same as here. AMD has a rough road ahead (so do their shareholders). That said, competition is good :)
  • Ken_g6 - Friday, March 10, 2017 - link

    Hm, 11GB RAM, 11Gbps, 11.3 TFLOPs. Why do I get the impression Marketing wanted to use the phrase "goes to eleven" for this card? Did they announce it with Spinal Tap music?
  • Ryan Smith - Saturday, March 11, 2017 - link

    They did not. Though clearly they should have.
  • mapesdhs - Saturday, March 11, 2017 - link

    Even SGI did this. IIRC:

    "audiopanel -spinaltap"

    Changes the scale to 11. :D
  • oranos - Friday, March 10, 2017 - link

    pretty meh if you own a gtx 1080 already. higher TDP, lower base clocks.
  • justaviking - Friday, March 10, 2017 - link

    30% faster is "meh"?

Log in

Don't have an account? Sign up now