Compute

Jumping into compute, we’re once again treading into familar territory. Pitcairn is Pitcairn is Pitcairn, and for the 270 series this will result in the same general performance increases we've seen elsewhere. 270 will of course be the bigger winner, owing to its upgrade to a fully enabled Pitcairn part. Also, on a quick housekeeping note we'll only be looking at the HIS 270 here. Our primary interest is on a broad architectural basis, rather than the minor impact from factory overclocks.

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

Both 270 cards do well for themselves here. The 270X holds the overall edge of course, though it’s interesting to note that the 270 and GTX 660 are virtually tied here.

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

AMD consistently rules the roost on LuxMark, so there aren’t any surprises here. This chart is essentially just the AMD GCN cards sorted by performance, followed by their older VLIW cards and the GeForce cards.

Our 3rd 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

Like LuxMark, Sony Vegas is a benchmark dominated by AMD. The lead here is so great that the 270 could run this benchmark twice over before the GTX 660 completed it once.

Our 4th 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 Fluid Simulation

Compute: CLBenchmark 1.1 Computer Vision

Both CLBenchmark’s fluid simulation benchmark and the computer vision benchmark go to AMD here. The GTX 660 and GTX 760 are not competitive here.

Moving on, our 5th 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 has moved exclusively to OpenCL this year with FAHCore 17.

Compute: Folding @ Home: Explicit, Single Precision

Compute: Folding @ Home: Implicit, Single Precision

When it comes to Folding@Home, the winner is highly dependent on the specific test. For the explicit simulation the GTX 660 is a significant laggard, leaving the 270 series to take the top spots for sub-$200 cards. In the implicit test however none of the 270 cards can hold their ground against the GTX 660, not even the 270X. Folding@Home uses a mix of these data types so there won’t be any one clear winner, but the 270 series loses by a smaller margin in implicit than the GTX 660 does in explicit.

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

SystemCompute is another compute benchmark that goes to AMD. The 270 and 270X handily beat the GTX 760, never mind the GTX 660.

Synthetics Power, Temperature, & Noise
POST A COMMENT

59 Comments

View All Comments

  • Waveblade - Wednesday, November 13, 2013 - link

    It's like different people work on different products! Reply
  • Roland00Address - Wednesday, November 13, 2013 - link

    A commandment of any cell phone reviews, thou shall not rush battery life tests. Reply
  • Tetracycloide - Wednesday, November 13, 2013 - link

    Be thou particularly careful testing battery life when thine available anecdotes vary wildly. Be thou definitive. Reply
  • slayerxj - Wednesday, November 13, 2013 - link

    I may not read the article very carefully, and I keep wondering that why 280X has a star behind it. Reply
  • Gigaplex - Wednesday, November 13, 2013 - link

    I'm getting a little tired of this TDP nonsense. Two cards with the same TDP from the same product family of the same manufacturer that clearly consume different amounts of power - the TDP numbers are now meaningless. And don't get me started on Intels SDP. Reply
  • yannigr - Wednesday, November 13, 2013 - link

    If both are under 150W, then where is the problem? Maybe R9 270 consumes close to 130W-140W and not 150W, giving the necessary room to AMD's partners to oc the chip without passing the 150W limit. Reply
  • dylan522p - Wednesday, November 13, 2013 - link

    OCed 270 is 270x Reply
  • slapdashbr - Monday, November 18, 2013 - link

    Under 150W means it only needs one 6-pin power connector (like the 7850 or 660 which it replaces/competes with) and in general is much more power-efficient. The 270 (non-x) is aimed more at builders with power limits or old systems that can't support a dual-6-pin GPU, or perhaps computational tasks where performance per watt is more important than performance per card. The 270x is full-powered but less efficient and is better suited for gamers and tweakers. I wouldn't get a 270 to save $20 unless the lower power limit was important, in which case it's actually a good buy, as it should still edge out a gtx 660 while staying under 150W total power. Reply
  • dylan522p - Wednesday, November 13, 2013 - link

    SDP at least makes sense. Reply
  • maximumGPU - Wednesday, November 13, 2013 - link

    quick comment on the DCUII coolers from asus. I too have been very impressed with them. my goal was silent yet powerful computing, and the DCUII cooler on my GTX670 plays that part admirably. Reply

Log in

Don't have an account? Sign up now