System Light Dark

xentr_theme_editor

xentr_page_setup xentr_appearance xentr_sidebar

  • xentr_page_width

    xentr_toggle_page_width

    xentr_page_width_description

    xentr_color_pickers

    xentr_toggle_color_picker

    xentr_toggle_color_picker_description

    xentr_typography

    xentr_select_the_font_you_want_to_use

    xentr_node_layout

    xentr_grid_layout

    xentr_grid_layout_description

  • Style variation

    xentr_select_the_style_variation_you_want_to_use
    System Light Dark

  • xentr_sidebar

    xentr_toggles_sidebar

    xentr_sidebar_description

    xentr_sticky_sidebar

    xentr_sticky_sidebar_description
    xentr_sidebar_position
    Left
    Right
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

GPU Benchmarking Methods Investigated: The Comment Thread

I got a question here. Assuming I'm understanding time demos, game sequences, and in game benchmark correctly, each time you use the game sequences wouldn't the results be a bit different? Because not everything would remain the same, such as where you face, what's going on in the environment, etc. Like for example we use the opening of CoD:MW, you're put through a test to test your reflexes in a makeshift cargo ship where you have to shoot at pieces of wood, throw grenades, etc. Each time you do that, some things change, like where you shoot, where the grenade is thrown, which way you face. All this results in different FPS due to the different amount of work that the GPU needs to process.

Sorry if this is a poor question, but I can't really think of a better way to ask this right now.
 
xentr_thread_starter
geokilla said:
I got a question here. Assuming I'm understanding time demos, game sequences, and in game benchmark correctly, each time you use the game sequences wouldn't the results be a bit different? Because not everything would remain the same, such as where you face, what's going on in the environment, etc. Like for example we use the opening of CoD:MW, you're put through a test to test your reflexes in a makeshift cargo ship where you have to shoot at pieces of wood, throw grenades, etc. Each time you do that, some things change, like where you shoot, where the grenade is thrown, which way you face. All this results in different FPS due to the different amount of work that the GPU needs to process.

Sorry if this is a poor question, but I can't really think of a better way to ask this right now.
Click to expand...

You are talking about variance. This is addressed in two ways: multiple runs of the same sequence and trying to use sections which use scripted events.
 
Scripted, as in the same things happen each time you do it. Repeatability is the key for getting the proper FPS between different runs of the benchmark/demo/level.
 
Video Cards

This is why I finally settled here rather than one of the other sites. While I still read the other sites reviews, it seems to me this one is most objective and strives to be as impartial as possible. By doing this, the proof is in the pudding. I'm not chastising any sites or building up this one, yeah right, but how many sites have made attempts to be this transparent about their testing methods?

In their defense I'm not all that knowledgeable, nor have I been involved in this field for very long,however when reading these articles I can relate to what is being said and done. On top of that, the help given without any condescending or above reproach views make me feel welcome and keep me coming back and asking questions which to be honest I would never dream of asking on certain other sites for fear of being ridiculed and/or chastised. After all, we all started from the beginning at some point. Kudos to SKYMTL and the HWC team. And to all of its members for keeping it real and being so helpful to such a noob as myself, thank you very much.

Keep up the good work folks!!!
:thumb::biggrin::clap::clap::clap:
 
SugarJ said:
Scripted, as in the same things happen each time you do it. Repeatability is the key for getting the proper FPS between different runs of the benchmark/demo/level.
Click to expand...
Which goes back to what I was talking about doesn't it? Something different could occur each time, whether its big or small.
 
Annnnd once again it takes a SKY Canuck to open people's eyes. Amazing job bro, I am very proud to be a Canuck right now! And the accompanying how to with downloads is fan-bloody-tastic. Thanks for all the hard work I cannot begin to fathom the dedication and focus it takes to pull this kind of thing together.
 
geokilla said:
Which goes back to what I was talking about doesn't it? Something different could occur each time, whether its big or small.
Click to expand...

Not in a time demo or in-game benchmark. In open game play , yes absolutely it can. That's why you do multiple runs, and over a longer time frame, so that your average FPS is closer to what it actually should be. In a short clip or 20 second play through, you could have events that spike or drop your framerate for a couple seconds. That will have more of an impact on the average framerate in a short run, while the effect would tend to be minimized in a longer run.
 
You must log in or register to reply here.

Latest posts

xentr_legal_notice_title

xentr_legal_notice_description

Back
Top