[LLVM][XTHeadVector] Implement intrinsics for vsmul. #75
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As title.
Here is my general thought on implementing intrinsics. I am a newbie in this topic and not have a complete certainty about what I did now. So I wish to discuss it here.
Add test case.
After reading the spec, I find the Intrinsic functions of vsmul and vdiv have one-to-one correspondence, which means they have the same function interface. So I just copy the test case of vdiv to vsmul and substitute 'vdiv' to vsmul. But there is a question here:
Define pseudos and pats.
I imitate other multiply intrinsics part. The cast target of WriteVSIMulV_MX is selected by searching 'vsmul' in the
file RISCVScheduleV.td .
Implement intrinsics for vsmul.
Again, I imitate other multiply intrinsics part. I not sure that choose of 'XVBinaryABX' for th_vsmul is right now.