Litterature about GPU architecture ?

Started by
6 comments, last by Hodgman 9 years, 1 month ago

I am looking for clear and easy-to-understand references about (modern) GPU architectures, that would for example explain (in generic terms) the flow of data, the way problems such as synchronization issues are handled. etc.

Most often the documents I find are:

- Presentation slides

- Technical specifications

Since those are quite hard to understand, I am looking for explanation with sentences written in "regular" English.

So far the closest thing to what I need are probably the posts "A trip through the Graphics Pipeline" by Fabian Giesen.

Are there any good books with the same level of quality and clarity, dealing with GPU architecture?

Advertisement

I know that you said that you don't like slides, but have you had a look through this presentation? It's a bit out of date at this point, but still mostly relevent. The author of that presentation also wrote an article that you can read, and teaches a course on Parallel Compute Architectures that you can follow along with.

Perhaps this is a bit of shameless self-promotion, but I talked a bit about memory operations on modern hardware, it may be of your interest.

They're a bit outdated, but the ATI Radeon 2000 programming guide and Depth In Depth from Emil Persson explain a lot of background concepts that are still relevant today (Hi Z, Z Compression, Early Z, Fast Z Clear, dynamic branching and divergence).
Seeing his two recent talks for modern archs is also useful to find the differences.

You mean, something like this?

I have found this article on gl buffer transfer provides a really good foundation for memory management in gpu drivers from the perspective of an application programmer. The textbook it's from is definitely a bit old (2012 I think), but it may still be relevant.

If you're comfortable with reading through hardware documentation, then AMD have some on their website.

http://developer.amd.com/resources/documentation-articles/developer-guides-manuals/

I think it's the programming guides under Open GPU Documentation that you want to look at.

EDIT: Just reread the OP where you say you want easiest to digest material. The above link is still something you could bookmark if you ever want to go back to it :)

Here is a presentation lecture on the matter, from an ATi/AMD engineer:

Found this today: https://developer.nvidia.com/content/life-triangle-nvidias-logical-pipeline

This topic is closed to new replies.

Advertisement