Compute Performance

As always we'll start with our DirectCompute game example, Civilization V, which uses DirectCompute to decompress textures on the fly. Civ V includes a sub-benchmark that exclusively tests the speed of their texture decompression algorithm by repeatedly decompressing the textures required for one of the game’s leader scenes.  While DirectCompute is used in many games, this is one of the only games with a benchmark that can isolate the use of DirectCompute and its resulting performance.

Compute: Civilization V

Our next benchmark is LuxMark2.0, the official benchmark of SmallLuxGPU 2.0. SmallLuxGPU is an OpenCL accelerated ray tracer that is 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 2.0

Our 3rd benchmark set comes from CLBenchmark 1.1. CLBenchmark contains a number of subtests; we’re focusing on the most practical of them, the computer vision test and the fluid simulation test. The former being a useful proxy for computer imaging tasks where systems are required to parse images and identify features (e.g. humans), while fluid simulations are common in professional graphics work and games alike.

Compute: CLBenchmark 1.1 Computer Vision

Compute: CLBenchmark 1.1 Fluid Simulation

Moving on, our 4th compute benchmark is 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, as Folding @ Home is moving exclusively OpenCL this year with FAHCore 17.

Compute: Folding @ Home: Explicit, Single Precision

Compute: Folding @ Home: Implicit, Single Precision

Our 5th compute benchmark is Sony Vegas Pro 12, an OpenGL and OpenCL video editing and authoring package. Vegas can use GPUs in a few different ways, the primary uses being to accelerate the video effects and compositing process itself, and in the video encoding step. With video encoding being increasingly offloaded to dedicated DSPs these days we’re focusing on the editing and compositing process, rendering to a low CPU overhead format (XDCAM EX). This specific test comes from Sony, and measures how long it takes to render a video.

Compute: Sony Vegas Pro 12 Video Render

Wrapping things up, our final compute benchmark is an in-house project developed by our very own Dr. Ian Cutress. SystemCompute is our first C++ AMP benchmark, utilizing Microsoft’s simple C++ extensions to allow the easy use of GPU computing in C++ programs. SystemCompute in turn is a collection of benchmarks for several different fundamental compute algorithms, as described in this previous article, with the final score represented in points. DirectCompute is the compute backend for C++ AMP on Windows, so this forms our other DirectCompute test.

Compute: SystemCompute v0.5.7.2 C++ AMP Benchmark

Civilization V Synthetics


View All Comments

  • Oxford Guy - Tuesday, March 26, 2013 - link

    It's absolutely ridiculous to release a 1 GB card today when even games like Skyrim need 2 GB at 1080p. Reply
  • Arnulf - Friday, March 22, 2013 - link

    Regarding noise measurement: weighing scale used for absolute measurements may be the "A" scale, but a card is not certain number of dB(A) louder than another card, it is certain number of dB louder (3 dB more would be twice as loud as far as sound pressure level is concerned, measured under same conditions and with same weighing), since your weighing scale used to take absolute measurements is the same.

    This refers to all your statements along the lines of "... but over 3 dB(A) louder ..." etc.
  • warezme - Friday, March 22, 2013 - link

    Middle of the road filler products are so boring. They are usually a mishmash of memory from here, GPU features from there, all so confusing and boring. Just release a full line of new core and memory features, age down your older products according to how they perform compared to the new and be done with it. Reply
  • piroroadkill - Friday, March 22, 2013 - link

    I disagree. This is a compelling midrange card. Reply
  • Spunjji - Friday, March 22, 2013 - link

    Good for you. Many of us disagree and this card has an obvious place in their line-up. Reply
  • CeriseCogburn - Sunday, March 24, 2013 - link

    Oh did you take a survey, or are you speaking for all amd fanboys just because ? Reply
  • CeriseCogburn - Sunday, March 24, 2013 - link

    Hey a least it isn't a THREE GNERATION IN A ROW CLONE !
    Like the 5770.
  • Shadowmaster625 - Friday, March 22, 2013 - link

    Is there any actual evidence to support the conclusion that 1GB is not enough for 1080p? Given the choice between more compute units or more RAM, I would take more compute units. Reply
  • Spunjji - Friday, March 22, 2013 - link

    Right now I believe there would not be. What people are anticipating is an inflation in the size of game assets spurred on by the next generation of consoles. Some people want to keep these things for a few years so it's a legitimate concern for a change! Reply
  • CeriseCogburn - Sunday, March 24, 2013 - link

    Wow how fanboys change from just prior releases with 2GB or 3GB amd crapcards - then it was an ABSOLUTE WIN according to you - necessary and "future proof!" especially for "skyrim mods !"
    You're a good laugh.

Log in

Don't have an account? Sign up now