PresentMon: Performance In DirectX, OpenGL, And Vulkan

Even More Data To Evaluate

FPS Vs. CPU Utilization

It can be difficult to identify bottlenecks or single-out the advantages/disadvantages of different APIs using a Fraps or PresentMon capture on its own. Adding the sensor data our software captures currently changes that, though.

First, let's consider the utilization of two CPUs, starting with the faster one. We can clearly see performance isn't being held back by any kind of host processing bottleneck.

The picture changes dramatically as we drop our cards into a lower-end platform. It's easy to see when and where graphics performance is limited by a CPU bottleneck. In addition, you can see how the load drops under DirectX 12 while using the Radeon RX 480, while the opposite appears true with Nvidia's GeForce GTX 1060.

FPS Vs. Power Consumption

A drop in CPU load is expressed partly by lower power consumption. We can scrutinize this more closely by testing DirectX 11 against DX 12 on our two systems, each with two graphics cards.

What we find is that the CPU's power consumption corresponds more or less to the CPU load.

This effect is also observable on the weaker CPU, though it's not quite as pronounced.

Attentive readers may have noticed that our recently-updated Nvidia Titan X Pascal 12GB Review featured improved charts, including temperature history. The data for this came from our new tool, replacing third-party software we were using previously.

Conclusion

We have seen that pure bar graphs are well and good, but they're certainly not the last word when it comes to evaluating graphics performance. There's a ton of additional analysis that can go into reviewing video cards, and we're elbow-deep. The emphasis at this point is presenting the most valuable data, without overwhelming anyone, in a way that makes sense.

Our advantage as editors is that we always see the full data dump. So as it's sorted through, potential problem areas become clear and we can prioritize certain performance passages or sensor read-outs. Moving forward, we'll handle all of this on a case-by-case basis to ensure you get the information you need to guide your purchasing decision.

A special thanks to all of the readers who helped shape our direction. Whether it was emails, comment section posts, or group discussions on other forums, we listened every step of the way. This is actually where the idea for our stuttering index came from.

In the end, it's all a neat balancing act between information that enthusiasts can use and illustrations easier for the masses to digest. One thing's for sure, though: we're sure there's something here for everyone.


MORE: Best Deals


MORE: Hot Bargains @PurchDeals

Follow us on Facebook, Google+, RSS, Twitter and YouTube.

  • godfather666
    Great stuff. I hope Directx 12's disappointing performance is a Hitman-specific problem.
    Reply
  • tomspown
    The title says "Performance In DirectX, OpenGL, And Vulkan" am i missing pages or just going blind, i read the article then i skimmed through it twice and has nothing to do with Vulkan only power consumption at the end.
    Reply
  • maddad
    Apologies to TOMSPOWN; Accidentally voted your comment down. I too really didn't get what this article was about.
    Reply
  • jtd871
    Igor, some of the charts mislabel the 1060 as the 480. Noticeable especially when the red and green coloring is used. Interesting stuff. I'm pleased to see you digging deeper with the data gathering, analysis and interpretation. It makes for more informed purchasing decisions.
    Reply
  • neblogai
    This is great- a lot of important data is revealed when doing diligent analysis like this. I have only two notices/questions:
    1) Is CPU load measured as total average of all cores, or maximum of a single most loaded core? Single cores at 100% might explain some of the slow frames-it would be great to have a graph with those two together.
    2) In the forum when people ask for builds, or about bottlenecks, they rarely tell what monitor, resolution, adaptive or fixed frame rate will be used. Similarly here- article could make note of available monitor technology. Frame times will get a special treatment on most popular- 60Hz fixed refresh rate without VSync, making actual frame times, and user experience completely different than can be expected from frame-time graphs here. Monitors with adaptive sync can also change frame-times, as well as their functions like Low Frame Compensation. It would be great if this was taken into account by few extra tests, or at least by giving notice with links to explanation of frame-time effect on different types and abilities of monitors. That would make it a full picture, and an excellent guide for intelligent purchase decision.
    Reply
  • blazorthon
    When it comes to digging deep into the numbers for performance, Tom's tends to be ahead of the crowd and this just brings that margin up further. Excellent read.

    @TOMSPOWN and MADDAD:
    The techniques and software used in this article is compatible with Vulkan, that is the point they were making related to Vulkan. Unlike Fraps, what they're doing now is compatible with more than just DX11, in fact it's apparently compatible with all of the graphics APIs we care about, which makes testing both more accurate and easier for them to manage.
    Reply
  • FormatC
    @tomspown
    The translated title is a little bit misleading, I agree. The exact translation of the original title is:
    THDE internally: How we measure and evaluate the graphics performance
    Just for interest:
    Our interpreter also works with OCAT (AMDs free GUI for PresentMon) and FCAT (in all versions).

    @jtd871:
    Which chart? I can't find it.
    Reply
  • chimera201
    ^ Both charts in 'Performance Versus Smoothness' -> 'Frame Rate Versus Frame Time Difference' has the bottom left chart with RX 480 label.

    Are you going to make game bench articles with this? Haven't seen any game benches on TH lately.
    Reply
  • jtd871
    @FormatC

    Under "Frame Rate Versus Frame Time Difference", 3rd page. I am presuming that the red chart is for the 480, the green for the 1060. Some of the green charts are labeled as the 480 card.
    Reply
  • erad84
    The TechReport's 99th percentile frame time graphs are a great way to summarise how smooth or not a cards results are.
    Their frames spent beyond X fram time bar graphs help convey this too.

    You article is good and the graphs are nice but I think TechReports graph ideas are the best I've seen for performance smoothness summaries. Plus they're easier to understand and glean info from at a glance as they're simpler to look at.
    Reply