WIP: Implement vectorized s2m on PPC #7901
Open
Conversation
This file contains hidden or 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
midronij
force-pushed
the
s2m
branch
2 times, most recently
from
08f39f7 to
b3884df
Compare
midronij
changed the title
midronij
force-pushed
the
s2m
branch
3 times, most recently
from
0d7be95 to
df618e2
Compare
|
you can describe more clearly what needs to be done. expected input and expected output, bit-based conversion or byte-based conversion, or others. otherwise, it can be reviewed with speculations of the semantic. |
zl-wang
suggested changes
Aug 27, 2025
midronij
force-pushed
the
s2m
branch
5 times, most recently
from
c979367 to
49a374e
Compare
midronij
force-pushed
the
s2m
branch
3 times, most recently
from
afe0e7c to
20a7fd0
Compare
gita-omr
reviewed
Sep 9, 2025
midronij
force-pushed
the
s2m
branch
2 times, most recently
from
a7a8726 to
cc68f2b
Compare
gita-omr
reviewed
Sep 9, 2025
midronij
changed the title
midronij
force-pushed
the
s2m
branch
2 times, most recently
from
2ef9b4c to
5a30c08
Compare
midronij
changed the title
midronij
force-pushed
the
s2m
branch
3 times, most recently
from
73a8b65 to
e61c7c1
Compare
gita-omr
reviewed
Sep 29, 2025
midronij
force-pushed
the
s2m
branch
6 times, most recently
from
8e57923 to
96cfe5b
Compare
gita-omr
reviewed
Oct 8, 2025
midronij
force-pushed
the
s2m
branch
3 times, most recently
from
8901887 to
8a4209a
Compare
gita-omr
reviewed
Oct 11, 2025
zl-wang
suggested changes
Oct 14, 2025
Signed-off-by: midronij <[email protected]>
zl-wang
suggested changes
Oct 16, 2025
| generateTrg1Src1Imm2Instruction(cg, TR::InstOpCode::rldimi, node, tmpGPR, srcReg, 32, 0x000000FF00000000); | ||
| } else { | ||
| generateTrg1Src1Imm2Instruction(cg, TR::InstOpCode::rldicr, node, tmpGPR, srcReg, 24, 0xFFFFFFFF00000000); | ||
| generateTrg1Src1Imm2Instruction(cg, TR::InstOpCode::rlwimi, node, tmpGPR, srcReg, 0, 0x000000FF); |
There was a problem hiding this comment.
rldimi is more appropriate here, since rlwimi clears the top 32bits automatically.
midronij
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Implement PPC codegen for
s2m(Short to Mask) on P8+. This operation accepts two byte elements of a given boolean array (read from memory using a halfword load) and converts it into a two-element LongVector mask with the corresponding boolean values.