compiling ptx code on NVIDIA GPU?

Question

I want to intercept at PTX level of opencl programs on NVIDIA GPU.

I imagine the routine would probably look like this.

First, I write an opencl program (both host and device code), using NVIDIA compiler to produce respective ptx code. Then I write what I want to do by modifying the PTX code (please don't ask why I didn't do this on the device C code - I have some reasons for it). But problem is, after being modified, how do I compile this PTX code to binary code?

Use the CUDA toolchain and CUDA driver API. I don't believe there is a way to deal with assembly code or inline assembler instruction with OpenCL. — talonmies
– talonmies, Commented Jul 9, 2012 at 7:02
This works for CUDA wili.cc/blog/ptx.html. Might work for OpenCL too — captain
– captain, Commented Jul 31, 2012 at 10:34

Yu Zhou · Accepted Answer · 2012-07-10 03:41:38Z

1

You can use ptxas, which is included in the CUDA toolkit. It compiles .ptx into .cubin, which can then be loaded with the driver API.

answered Jul 10, 2012 at 3:41

Yu Zhou

8181 gold badge7 silver badges11 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

harrism Over a year ago

I don't think there's a way to re-inject the PTX into OpenCL. You could use the CUDA Driver API and cuModuleLoadData. If you really need to do this low level of PTX manipulation, I recommend you just use CUDA (and possibly the CUDA Compiler SDK (libNVVM).

Collectives™ on Stack Overflow

compiling ptx code on NVIDIA GPU?

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related