[NVPTX] support immediate values in st.param instructions #91523
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Artem-B
reviewed
May 8, 2024
There was a problem hiding this comment.
Just curious -- do we expect to see any benefits from this in SASS?
ptxas usally deals with mov const->register; op(register) just fine and with parameters living mostly in registers, the notion of vectorized loads/stores in parameter space is largely a fiction.
What does this change buy us, other than a few less register moves on PTX level?
Artem-B
reviewed
May 13, 2024
Artem-B
approved these changes
May 14, 2024
Artem-B
approved these changes
May 14, 2024
| !strconcat("st.param.v2", opstr, | ||
| " \t[param$a+$b], {{$val, $val2}};"), | ||
| []>; | ||
| multiclass StoreParamInst<NVPTXRegClass regclass, Operand IMMType, string opstr, bit support_imm = true> { |
AlexMaclean
force-pushed
the
upstream/st.param-imm
branch
from
d1fb3df
to
e328d6a
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Add support for generating
st.paraminstructions with direct use of immediates. This eliminates the need for amovinstruction prior to thest.paramresulting in more concise emitted PTX.