Re:Demystifying GPU Compute Architectures – By Babbage
by dist-epoch on Tuesday February 06, 2024 @07:13PM
(#39282805)
OpenGL code is actually running on the CPU. From this CPU running code you can send shaders to the driver, in source code form or bytecode form, and the driver does the final compilation to GPU machine code.
[ Parent
| on HN ]
Re:Demystifying GPU Compute Architectures – By Babbage
by Xeamek on Tuesday February 06, 2024 @08:16PM
(#39283260)
Pedantry.
Yes you are running your code on the cpu, but you are using opengl defined api to do so.
Having a text generation and parsing, or having a function calls passed to/from drivers- those a simply implementation details
Re:Demystifying GPU Compute Architectures – By Babbage
by toasterlovin on Wednesday February 07, 2024 @01:16AM
(#39285138)
Modern CPUs being able to run 30 year old binaries as-is is pretty different than a GPU requiring a driver to compile byte code into machine code at runtime.
Re:Demystifying GPU Compute Architectures – By Babbage
by Xeamek on Wednesday February 07, 2024 @11:16AM
(#39290351)
How is that different?
Re:Demystifying GPU Compute Architectures – By Babbage
by toasterlovin on Wednesday February 07, 2024 @01:38PM
(#39292397)
You seem like you're being purposefully obtuse about this, so I'm going to disengage after this. But, generally speaking, a programming language which compiles to machine code which is executed directly by the CPU is widely considered to have a significantly different architecture than one which is compiled to byte code to be executed by a virtual machine. This architectural choice has many downstream ramifications. And the difference in execution model between CPUs and GPUs is similar in nature and comes with similar ramifications. Such as, for example, operating system support for GPUs.