summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp6
-rw-r--r--llvm/test/Transforms/InstCombine/masked_intrinsics.ll3
2 files changed, 6 insertions, 3 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
index 2dea7eea404..1d52938d1f8 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
@@ -1437,7 +1437,11 @@ Value *InstCombiner::SimplifyDemandedVectorElts(Value *V, APInt DemandedElts,
switch (II->getIntrinsicID()) {
case Intrinsic::masked_gather: // fallthrough
case Intrinsic::masked_load: {
- APInt DemandedPtrs(DemandedElts), DemandedPassThrough(DemandedElts);
+ // Subtlety: If we load from a pointer, the pointer must be valid
+ // regardless of whether the element is demanded. Doing otherwise risks
+ // segfaults which didn't exist in the original program.
+ APInt DemandedPtrs(APInt::getAllOnesValue(VWidth)),
+ DemandedPassThrough(DemandedElts);
if (auto *CV = dyn_cast<ConstantVector>(II->getOperand(2)))
for (unsigned i = 0; i < VWidth; i++) {
Constant *CElt = CV->getAggregateElement(i);
diff --git a/llvm/test/Transforms/InstCombine/masked_intrinsics.ll b/llvm/test/Transforms/InstCombine/masked_intrinsics.ll
index 48c8f78f990..582fd8f5c82 100644
--- a/llvm/test/Transforms/InstCombine/masked_intrinsics.ll
+++ b/llvm/test/Transforms/InstCombine/masked_intrinsics.ll
@@ -56,10 +56,9 @@ define <2 x double> @load_lane0(<2 x double>* %ptr, double %pt) {
ret <2 x double> %res
}
-; FIXME: the output here demonstrates a miscompile!
define double @load_all(double* %base, double %pt) {
; CHECK-LABEL: @load_all(
-; CHECK-NEXT: [[PTRS:%.*]] = getelementptr double, double* [[BASE:%.*]], <4 x i64> <i64 undef, i64 undef, i64 2, i64 undef>
+; CHECK-NEXT: [[PTRS:%.*]] = getelementptr double, double* [[BASE:%.*]], <4 x i64> <i64 0, i64 undef, i64 2, i64 3>
; CHECK-NEXT: [[RES:%.*]] = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> [[PTRS]], i32 4, <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x double> undef)
; CHECK-NEXT: [[ELT:%.*]] = extractelement <4 x double> [[RES]], i64 2
; CHECK-NEXT: ret double [[ELT]]
OpenPOWER on IntegriCloud