This is an archive of the discontinued LLVM Phabricator instance.

Differential D89172

[mlir] [standard] fixed typo in comment
ClosedPublic

Authored by aartbik on Oct 9 2020, 4:56 PM.

Details

Reviewers
mehdi_amini
grosul1
rriddle
Commits
rG3c366740ca24: [mlir] [standard] fixed typo in comment
Summary

There is an atomic_rmw and a generic_atomic_rmw operation.
The doc of the latter incorrectly referred to former though.

Diff Detail

Event Timeline

aartbik created this revision.Oct 9 2020, 4:56 PM
Herald added a project: Restricted Project. · View Herald TranscriptOct 9 2020, 4:56 PM
Herald added subscribers: tatianashp, msifontes, jurahul and 12 others. · View Herald Transcript
aartbik requested review of this revision.Oct 9 2020, 4:56 PM
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald TranscriptOct 9 2020, 4:56 PM
aartbik added reviewers: mehdi_amini, grosul1.Oct 9 2020, 4:57 PM
rriddle accepted this revision.Oct 9 2020, 4:58 PM
This revision is now accepted and ready to land.Oct 9 2020, 4:58 PM
rriddle added a comment.Oct 9 2020, 4:58 PM

Please feel free to just submit these types of fixes directly in the future. Thanks!

aartbik added a comment.Oct 9 2020, 4:59 PM

Thank you River!

This revision was landed with ongoing or failed builds.Oct 9 2020, 5:04 PM
Closed by commit rG3c366740ca24: [mlir] [standard] fixed typo in comment (authored by aartbik). · Explain Why
This revision was automatically updated to reflect the committed changes.
aartbik added a commit: rG3c366740ca24: [mlir] [standard] fixed typo in comment.
Harbormaster completed remote builds in B74670: Diff 297364.Oct 9 2020, 5:12 PM

Revision Contents

PathSize
mlir/
include/
mlir/
Dialect/
StandardOps/
IR/
2 lines

Diff 297365

mlir/include/mlir/Dialect/StandardOps/IR/Ops.td

Show First 20 Lines • Show All 613 Lines • ▼ Show 20 Lines
def GenericAtomicRMWOp : Std_Op<"generic_atomic_rmw", [ def GenericAtomicRMWOp : Std_Op<"generic_atomic_rmw", [
SingleBlockImplicitTerminator<"AtomicYieldOp">, SingleBlockImplicitTerminator<"AtomicYieldOp">,
TypesMatchWith<"result type matches element type of memref", TypesMatchWith<"result type matches element type of memref",
"memref", "result", "memref", "result",
"$_self.cast<MemRefType>().getElementType()"> "$_self.cast<MemRefType>().getElementType()">
]> { ]> {
let summary = "atomic read-modify-write operation with a region"; let summary = "atomic read-modify-write operation with a region";
let description = [{ let description = [{
The `atomic_rmw` operation provides a way to perform a read-modify-write The `generic_atomic_rmw` operation provides a way to perform a read-modify-write
sequence that is free from data races. The memref operand represents the sequence that is free from data races. The memref operand represents the
buffer that the read and write will be performed against, as accessed by buffer that the read and write will be performed against, as accessed by
the specified indices. The arity of the indices is the rank of the memref. the specified indices. The arity of the indices is the rank of the memref.
The result represents the latest value that was stored. The region contains The result represents the latest value that was stored. The region contains
the code for the modification itself. The entry block has a single argument the code for the modification itself. The entry block has a single argument
that represents the value stored in `memref[indices]` before the write is that represents the value stored in `memref[indices]` before the write is
performed. No side-effecting ops are allowed in the body of performed. No side-effecting ops are allowed in the body of
`GenericAtomicRMWOp`. `GenericAtomicRMWOp`.
▲ Show 20 Lines • Show All 3,142 Lines • Show Last 20 Lines