• Announcements

    • khawk

      Download the Game Design and Indie Game Marketing Freebook   07/19/17

      GameDev.net and CRC Press have teamed up to bring a free ebook of content curated from top titles published by CRC Press. The freebook, Practices of Game Design & Indie Game Marketing, includes chapters from The Art of Game Design: A Book of Lenses, A Practical Guide to Indie Game Marketing, and An Architectural Approach to Level Design. The GameDev.net FreeBook is relevant to game designers, developers, and those interested in learning more about the challenges in game development. We know game development can be a tough discipline and business, so we picked several chapters from CRC Press titles that we thought would be of interest to you, the GameDev.net audience, in your journey to design, develop, and market your next game. The free ebook is available through CRC Press by clicking here. The Curated Books The Art of Game Design: A Book of Lenses, Second Edition, by Jesse Schell Presents 100+ sets of questions, or different lenses, for viewing a game’s design, encompassing diverse fields such as psychology, architecture, music, film, software engineering, theme park design, mathematics, anthropology, and more. Written by one of the world's top game designers, this book describes the deepest and most fundamental principles of game design, demonstrating how tactics used in board, card, and athletic games also work in video games. It provides practical instruction on creating world-class games that will be played again and again. View it here. A Practical Guide to Indie Game Marketing, by Joel Dreskin Marketing is an essential but too frequently overlooked or minimized component of the release plan for indie games. A Practical Guide to Indie Game Marketing provides you with the tools needed to build visibility and sell your indie games. With special focus on those developers with small budgets and limited staff and resources, this book is packed with tangible recommendations and techniques that you can put to use immediately. As a seasoned professional of the indie game arena, author Joel Dreskin gives you insight into practical, real-world experiences of marketing numerous successful games and also provides stories of the failures. View it here. An Architectural Approach to Level Design This is one of the first books to integrate architectural and spatial design theory with the field of level design. The book presents architectural techniques and theories for level designers to use in their own work. It connects architecture and level design in different ways that address the practical elements of how designers construct space and the experiential elements of how and why humans interact with this space. Throughout the text, readers learn skills for spatial layout, evoking emotion through gamespaces, and creating better levels through architectural theory. View it here. Learn more and download the ebook by clicking here. Did you know? GameDev.net and CRC Press also recently teamed up to bring GDNet+ Members up to a 20% discount on all CRC Press books. Learn more about this and other benefits here.
Sign in to follow this  
Followers 0
fir

bandwidth theme and gpu-z info

9 posts in this topic

Maybe i can add something yet to those general performance and fillrate subtopics:

 

I run the fine program named gpu-z and it gives some info about my 

cheap gpu gt610 (worth of 50 dollars probably - i paid 50 for it but i am

from europe, but it seem that it is worldwide price )

 

Pixel Fillrate 1.4GPixels/s (shows the number of pixels that can be rendered to the screen in one second)

Texel Fillrate 5.6 GTexels/s (Shows the number of texels that can be

processen in one second)

Memory Type DDR3 (Please also note that GDDR3 doubles the avaliable bandwith of prewious DDR memory and that GDDR5 doubles the bandwidth od previous GDDR3 memory again)

Bandwidth 8.0GB/s (Shows the effective memory bandwidth avaliable between GPU and graphics memory)

 

Could maybe someone run gpu-z on his gpu and present me this info for his GPu it will maybe help me to clear some bandwith topics..

 

speaking about billions of triangles per second (which i doubt) iznt the general 

drawing limited by those numbers - I mean if triangle is described by some say

80 bytes of data 8.0 GB/80 = only 100 M triangles per second not billions?

 

Could maybe also someone say to me why texel fillrate is 4 times higher than pixel fillrate ? (it seem to me that pixel and texel are just 4 byte vram)?

Edited by fir
0

Share this post


Link to post
Share on other sites

Maybe i can add something yet to those general performance and fillrate subtopics:

 

I run the fine program named gpu-z and it gives some info about my 

cheap gpu gt610 (worth of 50 dollars probably - i paid 50 for it but i am

from europe, but it seem that it is worldwide price )

 

Pixel Fillrate 1.4GPixels/s (shows the number of pixels that can be rendered to the screen in one second)

Texel Fillrate 5.6 GTexels/s (Shows the number of texels that can be

processen in one second)

Memory Type DDR3 (Please also note that GDDR3 doubles the avaliable bandwith of prewious DDR memory and that GDDR5 doubles the bandwidth od previous GDDR3 memory again)

Bandwidth 8.0GB/s (Shows the effective memory bandwidth avaliable between GPU and graphics memory)

 

Could maybe someone run gpu-z on his gpu and present me this info for his GPu it will maybe help me to clear some bandwith topics..

 

speaking about billions of triangles per second (which i doubt) iznt the general 

drawing limited by those numbers - I mean if triangle is described by some say

80 bytes of data 8.0 GB/80 = only 100 M triangles per second not billions?

 

Could maybe also someone say to me why texel fillrate is 4 times higher than pixel fillrate ? (it seem to me that pixel and texel are just 4 byte vram)?

Why you picked up 80bytes per triangle? In perfect scene vertex to triangle ratio is close to one and vertex size is something like this: 12bytes for position. 4bytes fo uv. 6bytes for normal and another 6 for tangent. Add vertex color for 4bytes and you get 32bytes for one vertice.(which is around the same for one triangle with perfect vertice reuse.) Add 6bytes for index and you are still half of the the 80byte figure.

1

Share this post


Link to post
Share on other sites

To hit top triangle rates, you need to be using no textures, no normals, etc. and using triangle strips or some other method of getting one triangle per vertex. So think more a wireframe than an actual scene, and probably barely over 12 bytes per triangle of data. Actual triangle targets for PS4 development seems to be hovering around 100M per second (~4M per frame for 24fps, <2M for 60fps), so that's 1/16th the rated maximum as a result of scene complexity and such. That number will slowly move up as PS4 development matures.

 

Texel fill rate is higher than pixel fill rate because developers do things like using multiple textures on a model. If you read about the architecture of a video card, you'll see texture units mentioned. Those directly correlate to texel fill rate.

2

Share this post


Link to post
Share on other sites

Why you picked up 80bytes per triangle? In perfect scene vertex to triangle ratio is close to one and vertex size is something like this: 12bytes for position. 4bytes fo uv. 6bytes for normal and another 6 for tangent. Add vertex color for 4bytes and you get 32bytes for one vertice.(which is around the same for one triangle with perfect vertice reuse.) Add 6bytes for index and you are still half of the the 80byte figure.

 

well maybe 80 is to much but indeed i do not know how to count that 

- you said above 32 bytes for one vertice - so this is about 70 for the triangle; some vertices are reused but does it do the cut to 30% ?

maybe also not all the vertex data is needed (is the tangent or vertex color needed? i do not did much open gl as fot today only basics

mostly)) So you right probably 40 would be more realistic so 8Gb/40=200M triangles

0

Share this post


Link to post
Share on other sites

To hit top triangle rates, you need to be using no textures, no normals, etc. and using triangle strips or some other method of getting one triangle per vertex. So think more a wireframe than an actual scene, and probably barely over 12 bytes per triangle of data. Actual triangle targets for PS4 development seems to be hovering around 100M per second (~4M per frame for 24fps, <2M for 60fps), so that's 1/16th the rated maximum as a result of scene complexity and such. That number will slowly move up as PS4 development matures.

 

Texel fill rate is higher than pixel fill rate because developers do things like using multiple textures on a model. If you read about the architecture of a video card, you'll see texture units mentioned. Those directly correlate to texel fill rate.

 

Well maybe i will not like counting the wireframe but it would be ok to 

just do flat shading (with only 'environment' ambient light) no textures,

maybe not normal - 

I am refering to to the people which talks bilions triangles per seconds - and i try to build my own image of the things (i know i could test, but got no framework ready yet etc)

 

As to texel fillrate i do not understand this - could you maybe answer it a bit more?

 

Also have you maybe gpu-z small program on your machine could yopu give me the fillrates it raports there?

0

Share this post


Link to post
Share on other sites

A triangle strip with n vertices defines n-2 triangles. So if n is not tiny, you get close to one triangle per vertex.

well, ok

0

Share this post


Link to post
Share on other sites

Those numbers you're quoting a theoretical maximums typically based on the clockspeed as well as the rate of internal fixed-function components on the GPU. So something like "max triangle count" will just tell you the max speed at which the GPU can setup triangles during the rasterization process. It won't account for things like bandwidth required for fetching vertices, or the cost of running vertex shaders. The same goes with pixel fillrate and texel fillrate. In practice these theoretical numbers can never be achieved, because the GPU will end being bottlenecked by some other component.

2

Share this post


Link to post
Share on other sites

Texel is the unit of measurement for a texture, like pixel is the unit of measurement for your screen resolution. Texel fill rate is number of texture units times clock frequency of texture units. For my R9 290, that's 160 TMUs * 950MHz = 152 GTexels/sec. The R9 290 only has 64 ROPs though (for pixels instead of texels), multiplied by the same 950MHZ gives 60.8 GPixels/sec. AMD designed the card with more texture units (TMUs) than pixel units (ROPs), so that's why it has a higher texel fill rate than a pixel fill rate.

 

ROP = Render OutPut

TMU = Texture Mapping Unit

 

http://www.techpowerup.com/gpudb/2397/radeon-r9-290.html provides more detailed information about my card than gpu-z will. Here is the link for your GT610 http://www.techpowerup.com/gpudb/821/geforce-gt-610.html. Hopefully with those links you can see more detailed reasons why different cards act differently.

 

If you take anything away from this discussion, please take away that memory bandwidth is not a good way of predicting how many polygons a scene can support. My R9 290 has 320GB/sec of bandwidth, but it most definitely cannot render 8 billion triangles per second if each triangle averages 40 bytes of data. It will never render over 4 billion triangles per second since it lacks the hardware required to do that.

1

Share this post


Link to post
Share on other sites

Its not neccesary a "way" but it is important factor.

 

those values like 8GB/s are also to low to be a pure teoretical (I said my old DDR2 ram is 3GB/s quite very practical )

 

for my card page list  Bandwidth: 14.4 GB/s

when gpu-z shows 8.0 GB

 

for yr card its Bandwidth: 320 GB/s

 

hmm 

 

also my card is cheap but i like this stuff - low power and

every game i got works perfectly wel on this

 

as to conclusions it is to early on this (because it needs many

benchmarks and factors) but i like to consider such things so

this info I found in a limited way interesting

Edited by fir
0

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now
Sign in to follow this  
Followers 0