logoalt Hacker News

ychen306today at 3:55 PM1 replyview on HN

How do you deal with target-specific inline asm like tcgen05.mma?


Replies

msondtoday at 5:16 PM

We haven’t yet released support for tcgen05, but we’ll deal with it the same way we deal with other inline PTX: parsing it and converting it to target-appropriate instructions together with the rest of the program.

This is something we’ve done already for the hopper-class tensorcore instructions, and the blackwell ones will map similarly, though likely with a kernel launch involved.