The Myths Of Graphics Card Performance: Debunked, Part 2

Performance Engineering And Value Over Time

Optimizing Your Gaming PC

Myth: Optimizing a gaming PC’s performance is an art, not a science.

Performance engineering is all about throughput and bottlenecks. Tuning a gaming PC’s performance, in principle, is little different than tuning a mammoth IBM mainframe for a specific workload. The key concept is that your setup is only as fast as the lowest-throughput device in the rendering chain. If you’re pushing high resolutions and the most taxing graphics quality settings, that weak point is probably going to be your GPU.

There are rare cases when the CPU can inhibit performance, appearing as the bottleneck. Those tend to be physics- or AI-heavy tasks, which are rather uncommon in modern games. Alternatively, titles that go light on eye candy end up running at very high frame rates (vanilla Skyrim, for instance) limited by the host processor.

X: Rebirth, a rare example of a game bottlenecking on poor code optimization rather than GPU utilization

The amount of graphics memory on your card, its graphics memory bandwidth, system memory (RAM) capacity, PCIe connectivity and bus traffic rarely bottleneck graphics performance. The only times when you’d see differently would be on a system configured near Windows' minimum requirements or in a poorly-optimized application (X: Rebirth sadly comes to mind).

Does that mean that faster RAM won’t help bolster your frame rates? No - improving the performance of a component not on the so-called "critical path" will help some. But those gains tend to be modest.

Upgrading the components currently limiting your gaming experience, on the other hand, tends to yield closer-to-linear benefits. As long as graphics are your bottleneck, swapping out a lower-end card with a higher-end one with twice the potential can almost double your performance.

Thus, the optimization of PC gaming, while a complex science, is very much a science still.

Where Do You Get The Biggest Value For Your Money?

Myth: Get the fastest CPU you can afford.

Value arguments are inherently different to tackle, since they’re so subjective. Please take my observations as personal thoughts more than irrefutable truths. You situation may very well be different based on your needs and current hardware setup.

In my experience, of the hardware you can buy, displays tend to last the longest. I bought a 30" Apple Cinema Display in 2004, brought it across the ocean with me and I'm still happily using it as a wonderful secondary display 10 years later. Thus, my personal mantra is to upgrade your monitor rarely, but spare no expense on it when you do.

Close to displays, you'll find speakers and headphones high up on my list. Quality audio equipment almost never becomes obsolete. And audio gear tends to retain its value well, so if you ever decide to upgrade, eBay will treat you well.

Quality power supplies cannot be under-emphasized. While seemingly unexciting, a PSU going bad can really ruin your day by not only rendering your system inoperable, but possibly damaging other equipment as well. In addition, PSUs are some of the most time-intensive components to "swap out" when they start exhibiting problems. You probably don’t need a huge power supply, but you don’t want to run your PSU constantly above ~80% of its rated capacity either, as doing so results in increased noise, lower efficiency and decreased lifespan.

Mice and keyboards fall into a distant fourth place. I mourned the loss of my Logitech MX510 mouse after six years of honorable (and intense) service. For a bit of nostalgia, check out Logitech New Mouse Range Goes Back to the Future.

Other PC components tend to age pretty quickly. Motherboards and CPUs rarely remain in production more than a couple of years. GPUs are replaced by new generations at more or less the same rate. Storage seems to get infinitely cheaper and increasingly faster. The performance impact of RAM on gaming in minimal. Wi-Fi routers and DSL/cable modems improve almost every year. PC cases can be recycled, but newer ones tend to introduce notable improvements. Fans and coolers (air or liquid), being mechanical components, tend to have defined lifespans and are bound to die on you eventually, requiring repair or replacement.

Furthermore, the rate of innovation in the CPU world has slowed considerably. The recent launches of Haswell-E on LGA 2011-v3 and Haswell on LGA 1150 were fairly unimpressive from a gaming perspective; check out The Core i7-4770K Review: Haswell Is Faster; Desktop Enthusiasts Yawn.

On a per-clock basis (at 4 GHz), even the Core i7-4770K offers little real-world benefit compared to a five-year-old Core i7-950 with an aggressively overclocked GeForce GTX 690, as you can see from this 3DMark comparison. The -4770K only fares marginally better in the Physics and Combined tests. It takes pushing the Haswell-based chip to 4.6 GHz to eke out less than a 1 FPS difference, as seen in this other 3DMark comparison. In short, CPUs make very little difference in modern gaming PCs. You most likely don't need to upgrade your host processor unless your platform is very old. And, even if you choose to, Don Woligroski’s Best Gaming CPUs For The Money column shows that any dollar spent above $200 is most likely overkill.

GPUs are a different story. These are the components where spending additional dollars makes a real difference, subject to diminishing returns. Check out Best Graphics Cards For The Money for the latest deep-dive in this area. One word of warning: while SLI/CrossFire solutions may be attractive from a prospective value angle, keep in mind that dual-GPU scaling isn’t always linear. And not all games support those technologies. As a result, you might want to consider shopping for a faster single-GPU card first.

  • iam2thecrowe
    i've always had a beef with gpu ram utillization and how its measured and what driver tricks go on in the background. For example my old gtx660's never went above 1.5gb usage, searching forums suggests a driver trick as the last 512mb is half the speed due to it's weird memory layout. Upon getting my 7970 with identical settings memory usage loading from the same save game shot up to near 2gb. I found the 7970 to be smoother in the games with high vram usage compared to the dual 660's despite frame rates being a little lower measured by fraps. I would love one day to see an article "the be all and end all of gpu memory" covering everything.

    Another thing, i'd like to see a similar pcie bandwidth test across a variety of games and some including physx. I dont think unigine would throw much across the bus unless the card is running out of vram where it has to swap to system memory, where i think the higher bus speeds/memory speed would be an advantage.
    Reply
  • blackmagnum
    Suggestion for Myths Part 3: Nvidia offers superior graphics drivers, while AMD (ATI) gives better image quality.
    Reply
  • chimera201
    About HDTV refresh rates:
    http://www.rtings.com/info/fake-refresh-rates-samsung-clear-motion-rate-vs-sony-motionflow-vs-lg-trumotion
    Reply
  • photonboy
    Implying that an i7-4770K is little better than an i7-950 is just dead wrong for quite a number of games.

    There are plenty of real-world gaming benchmarks that prove this so I'm surprised you made such a glaring mistake. Using a synthetic benchmark is not a good idea either.

    Frankly, I found the article was very technically heavy were not necessary like the PCIe section and glossed over other things very quickly. I know a lot about computers so maybe I'm not the guy to ask but it felt to me like a non-PC guy wouldn't get the simplified and straightforward information he wanted.
    Reply
  • eldragon0
    If you're going to label your article "graphics performance myths" Please don't limit your article to just gaming, It's a well made and researched article, but as Photonboy touched, the 4770k vs 950 are about as similar as night and day. Try using that comparison for graphical development or design, and you'll get laughed off the site. I'd be willing to say it's rendering capabilities are actual multiples faster at those clock speeds.
    Reply
  • SteelCity1981
    photonboy this article isn't for non pc people, because non pc people wouldn't care about detailed stuff like this.
    Reply
  • renz496
    14561510 said:
    Suggestion for Myths Part 3: Nvidia offers superior graphics drivers

    even if toms's hardware really did their own test it doesn't really useful either because their test setup won't represent million of different pc configuration out there. you can see one set of driver working just fine with one setup and totally broken in another setup even with the same gpu being use. even if TH represent their finding you will most likely to see people to challenge the result if it did not reflect his experience. in the end the thread just turn into flame war mess.

    14561510 said:
    Suggestion for Myths Part 3: while AMD (ATI) gives better image quality.

    this has been discussed a lot in other tech forum site. but the general consensus is there is not much difference between the two actually. i only heard about AMD cards the in game colors can be a bit more saturated than nvidia which some people take that as 'better image quality'.
    Reply
  • ubercake
    Just something of note... You don't necessarily need Ivy Bridge-E to get PCIe 3.0 bandwidth. Sandy Bridge-E people with certain motherboards can run PCIe 3.0 with Nvidia cards (just like you can with AMD cards). I've been running the Nvidia X79 patch and getting PCIe gen 3 on my P9X79 Pro with a 3930K and GTX 980.
    Reply
  • dovah-chan
    There is one AM3+ board with PCI-E 3.0. That would be the Sabertooth Rev. 2.
    Reply
  • ubercake
    Another article on Tom's Hardware by which the 'ASUS ROG Swift PG...' link listed for an unbelievable price takes you to the PB278Q page.

    A little misleading.
    Reply