Skip to content

[msan] Handle Arm NEON pairwise min/max instructions #129824

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 9, 2025
Merged

[msan] Handle Arm NEON pairwise min/max instructions #129824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
15e9764
[msan] Handle Arm NEON pairwise min/max instructions
thurstond Mar 5, 2025
ad0b186
Add note that maybeHandleSimpleNomemIntrinsic may incorrectly match
thurstond Mar 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3129,6 +3129,9 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
/// fine).
///
/// Caller guarantees that this intrinsic does not access memory.
///
/// TODO: "horizontal"/"pairwise" intrinsics are often incorrectly matched by
/// by this handler.
[[maybe_unused]] bool
maybeHandleSimpleNomemIntrinsic(IntrinsicInst &I,
unsigned int trailingFlags) {
Expand Down Expand Up @@ -4871,6 +4874,18 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
setOrigin(&I, getCleanOrigin());
break;

// TODO: handling max/min similarly to AND/OR may be more precise
// Floating-Point Maximum/Minimum Pairwise
case Intrinsic::aarch64_neon_fmaxp:
case Intrinsic::aarch64_neon_fminp:
// Floating-Point Maximum/Minimum Number Pairwise
case Intrinsic::aarch64_neon_fmaxnmp:
case Intrinsic::aarch64_neon_fminnmp:
// Signed/Unsigned Maximum/Minimum Pairwise
case Intrinsic::aarch64_neon_smaxp:
case Intrinsic::aarch64_neon_sminp:
case Intrinsic::aarch64_neon_umaxp:
case Intrinsic::aarch64_neon_uminp:
// Add Pairwise
case Intrinsic::aarch64_neon_addp:
// Floating-point Add Pairwise
Expand Down
Loading