AnsweredAssumed Answered

What's the best or the recommended way to copy the data from scalar registers to GDS?

Question asked by sp314 on Apr 23, 2019
Latest reply on May 14, 2019 by sp314

Perhaps, there's something that I'm not seeing in the docs, so I apologize in advance.

 

I've got 16 dwords in scalar registers s16-s31. I need to copy that data from the scalar registers to GDS at the GDS base address + 64 bytes offset. The best way I see so far to do this is to

 

- mask all lanes but one in the wave with the exec;
- move the data from the scalar to the vector registers;
- issue a bunch of ds_write_bNNN gds instructions;
- re-enable all lanes with the exec.

 

This sounds cumbersome. Is there a better way to store the data from a bunch of scalar registers to GDS?

 

I've attached a screenshot of the concept of the code that I have (sorry for blanking out the tiny part that's under the NDA, I promise it doesn't matter for this question). This code may not compile or anything, this is a conceptual explanation of what's going on. For the purposes of limiting and simplifying this question, assume that we only have one wave - wave 0 - going over the entire GPU. If it matters, the platform is ROCm on Linux, and the card is Vega 64.

 

Surely, there must be a better way to do this, so I must be missing something? What is it? What's the best way of copying the data from scalar registers to GDS?

 

(Thank you in advance.)

 

Best,
sp

Attachments

Outcomes