Skip to content
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.

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

Fix potential crash in SLPVectorizer caused by missing check #95937

Merged
merged 3 commits into from
Jul 2, 2024
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
2 changes: 1 addition & 1 deletion llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -835,7 +835,7 @@ static InstructionsState getSameOpcode(ArrayRef<Value *> VL,
auto *CallBase = cast<CallInst>(IBase);
if (Call->getCalledFunction() != CallBase->getCalledFunction())
return InstructionsState(VL[BaseIndex], nullptr, nullptr);
if (Call->hasOperandBundles() &&
if (Call->hasOperandBundles() && CallBase->hasOperandBundles() &&
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if (Call->hasOperandBundles() && CallBase->hasOperandBundles() &&
if (Call->hasOperandBundles() && (!CallBase->hasOperandBundles() ||

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is the idea that if CallBase doesn't have an operandBundle is ignored?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The idea is that two calls are incompatible if they have different operand bundles. If one has a bundle but another does not, they are still incompatible.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Right, but if we have that change we will return true no? i.e Call->hasOperandBundles() == true and !CallBase->hasOperandBundles() == true will enter the branch. Unless I misunderstood your change

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, it will execute return. And that's fine, this return returns false, not true

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh ok, We just don't want a fallthrough

!std::equal(Call->op_begin() + Call->getBundleOperandsStartIndex(),
Call->op_begin() + Call->getBundleOperandsEndIndex(),
CallBase->op_begin() +
Expand Down
43 changes: 43 additions & 0 deletions llvm/test/Transforms/SLPVectorizer/AArch64/uselistorder.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=slp-vectorizer -S -pass-remarks-missed=slp-vectorizer 2>&1 | FileCheck %s

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"

; This test has UB but the crash in #95016 only happens with it
define void @uselistorder_test() {
; CHECK-LABEL: @uselistorder_test(
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> poison, double 0.000000e+00, i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> [[TMP1]], double 0.000000e+00, i32 1
; CHECK-NEXT: [[TMP3:%.*]] = fadd <2 x double> [[TMP2]], zeroinitializer
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> zeroinitializer, [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = fmul <2 x double> [[TMP4]], zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = select <2 x i1> zeroinitializer, <2 x double> zeroinitializer, <2 x double> [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = fmul <2 x double> [[TMP6]], zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = fadd <2 x double> [[TMP7]], zeroinitializer
; CHECK-NEXT: store <2 x double> [[TMP8]], ptr null, align 8
; CHECK-NEXT: ret void
;
%max1 = call double @llvm.maximum.f64(double 0.000000e+00, double 0.000000e+00) [ "a_list"(ptr null) ]
%add1 = fadd double %max1, 0.000000e+00
%mul1 = fmul double 0.000000e+00, %add1
%mul2 = fmul double %mul1, 0.000000e+00
%sel1 = select i1 false, double 0.000000e+00, double %mul2
%max2 = call double @llvm.maximum.f64(double 0.000000e+00, double 0.000000e+00)
%add2 = fadd double %max2, 0.000000e+00
%mul3 = fmul double 0.000000e+00, %add2
%mul4 = fmul double %mul3, 0.000000e+00
%sel2 = select i1 false, double 0.000000e+00, double %mul4
%mul5 = fmul double %sel2, 0.000000e+00
%add3 = fadd double 0.000000e+00, %mul5
%gep1 = getelementptr { double, [1 x [2 x double]] }, ptr null, i64 0, i32 1
store double %add3, ptr %gep1, align 8
%mul6 = fmul double %sel1, 0.000000e+00
%add4 = fadd double %mul6, 0.000000e+00
store double %add4, ptr null, align 8
ret void
}

declare double @llvm.maximum.f64(double, double) #0

attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
Loading