Do New Drivers Really Boost Performance?

What Should The Nvidia and AMD Drivers Be Able To Do?

These are some of the changes made to to the 177.92 beta release. Ed.: Nvidia has since released its GeForce 178.13 driver package, which adds WHQL certification, along with PhysX acceleration, 2- and 3-way SLI on the Skulltrail and, according to Nvidia, significant performance improvements versus its 175 driver. These are the exact same optimizations we’ll be testing here today, only in a different package.

Multiple improvements added in the 3D application performance. The following describes numerous examples of improvements measured with driver v177.92 WHQL over driver v175.19 WHQL:

  • Improvement with a single graphics processor of up to 11% with 3DMark Vantage (setting ‘Performance’)
  • Improvement with a single graphics processor of up to 11% with Assassin’s Creed DX10
  • Improvement with a single graphics processor of up to 15% with Bioshock DX10 Improvement with a single graphics processor of up to 15% with Call of Duty 4
  • Improvement with a single graphics processor of up to 8% with Enemy Territory: Quake Wars
  • Improvement with a dual SLI of up to 7% with Bioshock DX10
  • Improvement with a dual SLI of up to 10% with Company of Heroes: Opposing Fronts DX10
  • Improvement with a dual SLI of up to 12% with Enemy Territory: Quake Wars
  • Improvement with a dual SLI of up to 10% with World in Conflict DX10

Assassins Creed, Call of Duty 4 and Enemy Territory: Quake Wars are all included in the Tom’s Hardware benchmark suite, which means that the above claims can be proven.

This is an excerpt from the version highlights of the ATI graphics driver Catalyst 8.8. Ed.: Again, a recent driver refresh put our numbers here behind by a revision. However, none of the changes in AMD’s most recent release notes suggest performance has changed.

  • Call of Duty: Corruption is no longer noticed when having Quad CrossFire enabled and an HDMI 1080p display device connected. Further details can be found in topic number 737-35112
  • Devil May Cry 4: Anti-Aliasing no longer fails to function when playing the game with CrossFire enabled
  • Dirt: Playing the German Crossover track (Rally World Event) no longer results in the grand stands and chain link fences not being displayed correctly when CrossFire is enabled and MSAA is disabled
  • Hellgate London: Setting the display resolution to 2560x1600 no longer results in the game failing to respond
  • Lineage II: Switching between the game and the Windows desktop no longer results in the desktop appearing brighter than its original setting. Exiting the game and restarting the operating system may also result in the desktop brightness failing to be restored to its original setting. Further details can be found in topic number 737-35108
  • Lost Planet (DX9): Enabling CrossFire, AA to 4x, AF to 8x, and having all of the in-game options set to high no longer results in the game failing to respond when running the performance test
  • Mahjongg Artifacts: Flickering is no longer noticed when playing the game on pre-configured name brand systems
  • Mass Effect: Playing the game with CrossFire enabled no longer results in corruption being noticed on the AA menu
  • NASCAR demo: Setting all the in-game options to the highest levels no longer results in corruption being noticed on systems containing an ATI Radeon HD 2400 series of product and running Windows Vista
  • Quake 4: Corruption is no longer noticed when starting a new game on systems running either Windows XP or Vista and containing an ATI Radeon HD 48x0 series of product
  • Second Life: Playing the game on a CrossFire configured system (ATI Radeon HD 2400 and above) no longer results in corruption and slow performance being noticed
  • Unreal Tournament 3: The game no longer intermittently fails to launch when a map has texture detail set to maximum. Further details can be found in topic number 737-31189
  • World In Conflict: Setting the video quality to high no longer results in corruption being noticed
  • pcgamer12
    Great article.
    Reply
  • cangelini
    LedrosTo bad you used 8.8 drivers instead of the 8.9 ones. Real smart people.
    This is observed in the piece and should not affect performance.
    Reply
  • curnel_D
    Lol.
    Reply
  • neiroatopelcc
    SoulLance"Unfortunately for AMD and its customers, the PowerPlay optimization for energy-efficient 2D operation is not included in the Catalyst 8.8 driver for the Radeon HD 4870. Quake Wars refuses to start using the Catalyst 8.8, but it works fine with the Catalyst 8.6 and 8.7."But neither should comments like this appear when everyone on the planet reads a labels that clearly say "Use latest drivers from manufacturer".
    Can you please translate this into english?
    I have no idea what you mean to say with your comment, other than the obvious (that you disagree on some level with the article)
    Reply
  • randomizer
    He's saying you shouldn't criticise newer drivers because most hardware and software packaging has a label, or a section in the manual, telling you to use the latest drivers. So latest = best as far as he is concerned.
    Reply
  • In reference to overclocking graphics cards, I'm pretty sure that XFX card warranties cover overclocking to some degree, though you'd have to double check their warranty fine print.
    Reply
  • neiroatopelcc
    SneppyIn reference to overclocking graphics cards, I'm pretty sure that XFX card warranties cover overclocking to some degree, though you'd have to double check their warranty fine print.Having had experience with two failing xfx cards (both 8800gtx's actually), I've got to warn you though, that their warranty is a bit fictional. While they may actually cover broken products, you can easily risk waiting months for a replacement.
    Proof of my claim in case someone unexpectedly doubts it : http://www.opel.cc/xfx8800gtx/xfx.htm
    That was the first failing card. The second I haven't even bothered sending in, and just bought an 4870 instead of waiting months.
    Reply
  • cryogenic
    We all know there were cases in the past when "Newer drivers provided substantial performance improvements" in various applications or games. Analyzing performance with a few select driver sets can can't lead to the conclusion that drivers are irrelevant, or that from a "professional" stand point the latest drivers shouldn't be chosen.
    Reply
  • randomizer
    CryogenicAnalyzing performance with a few select driver sets can can't lead to the conclusion that drivers are irrelevantBut it can lead to the conclusion that current drivers are irrelevant, or rather less relevant.
    Reply
  • cryogenic
    randomizer
    That's a good,true and useful conclusion, but it's not a general one, only specific to this particular set of drivers.
    Reply