[InstCombine] Fix miscompile when folding a select into a masked load (#216730)

`visitSelectInst` folds:

    select(mask, masked.load(ptr, mask, PT), FV)

into:

    masked.load(ptr, mask, FV)

The replacement load was previously created at the select, effectively
moving the memory access past any intervening instructions. If one of
them writes the loaded memory, the replacement load reads the updated
value instead of the original one. This was also observed downstream in
[ispc/ispc#3891](ispc/ispc#3891).

The fold was added in `eb8589987267`. The issue is labelled
`regression:22`, so it affects LLVM 22.1 as well as current trunk.

Create the replacement load at the original load's position and require
`FV` to be available there. Otherwise, leave the select unchanged.
Requiring `FV` to be available at the original load means the fold no
longer fires when `FV` is computed between the load and the select. No
existing `llvm/test/Transforms` checks change as a result of this
restriction.

Tests cover an intervening aliasing store and the case where `FV` is
unavailable at the original load. They also guard against carrying over
call-site attributes such as `range` and `noundef` when those attributes
no longer apply.

Fixes #215453

Author: Chennesxu

llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp

@@ -5379,11 +5379,16 @@ Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
   if (match(TrueVal, m_OneUse(m_MaskedLoad(m_Value(MaskedLoadPtr),
                                            m_Specific(CondVal), m_Value())))) {
     auto *LoadInst = cast<IntrinsicInst>(TrueVal);
-    Instruction *In = Builder.CreateMaskedLoad(
-        TrueVal->getType(), MaskedLoadPtr,
-        LoadInst->getParamAlign(0).valueOrOne(), CondVal, FalseVal);
-    In->setAAMetadata(LoadInst->getAAMetadata());
-    return replaceInstUsesWith(SI, In);
+    // Keep the load at its original position to avoid crossing writes. The new
+    // passthrough must therefore be available there.
+    if (DT.dominates(FalseVal, LoadInst)) {
+      Builder.SetInsertPoint(LoadInst);
+      Instruction *In = Builder.CreateMaskedLoad(
+          TrueVal->getType(), MaskedLoadPtr,
+          LoadInst->getParamAlign(0).valueOrOne(), CondVal, FalseVal);
+      In->setAAMetadata(LoadInst->getAAMetadata());
+      return replaceInstUsesWith(SI, In);
+    }
   }
 
   // Canonicalize sign function ashr pattern: select (icmp slt X, 1), ashr X,

llvm/test/Transforms/InstCombine/select-masked_load.ll

@@ -169,6 +169,46 @@ define <vscale x 4 x i32> @fold_sel_into_masked_load_drop_metadata(ptr %loc, <vs
   ret <vscale x 4 x i32> %sel
 }
 
+; Keep the folded load before an intervening aliasing store.
+define <4 x float> @fold_sel_into_masked_load_aliasing_store(ptr %ptr, <4 x i1> %mask, <4 x float> %passthrough) {
+; CHECK-LABEL: @fold_sel_into_masked_load_aliasing_store(
+; CHECK-NEXT:    [[SEL:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 4 [[PTR:%.*]], <4 x i1> [[MASK:%.*]], <4 x float> [[PASSTHROUGH:%.*]])
+; CHECK-NEXT:    store <4 x float> [[PASSTHROUGH]], ptr [[PTR]], align 16
+; CHECK-NEXT:    ret <4 x float> [[SEL]]
+;
+  %load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %ptr, i32 4, <4 x i1> %mask, <4 x float> zeroinitializer)
+  store <4 x float> %passthrough, ptr %ptr, align 16
+  %sel = select <4 x i1> %mask, <4 x float> %load, <4 x float> %passthrough
+  ret <4 x float> %sel
+}
+
+; Do not fold when the new passthrough is unavailable at the old load.
+define <4 x float> @neg_fold_sel_into_masked_load_passthrough_after_load(ptr %ptr, <4 x i1> %mask, <4 x float> %a) {
+; CHECK-LABEL: @neg_fold_sel_into_masked_load_passthrough_after_load(
+; CHECK-NEXT:    [[LOAD:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 4 [[PTR:%.*]], <4 x i1> [[MASK:%.*]], <4 x float> zeroinitializer)
+; CHECK-NEXT:    [[PASSTHROUGH:%.*]] = fadd <4 x float> [[A:%.*]], [[A]]
+; CHECK-NEXT:    [[SEL:%.*]] = select <4 x i1> [[MASK]], <4 x float> [[LOAD]], <4 x float> [[PASSTHROUGH]]
+; CHECK-NEXT:    ret <4 x float> [[SEL]]
+;
+  %load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %ptr, i32 4, <4 x i1> %mask, <4 x float> zeroinitializer)
+  %passthrough = fadd <4 x float> %a, %a
+  %sel = select <4 x i1> %mask, <4 x float> %load, <4 x float> %passthrough
+  ret <4 x float> %sel
+}
+
+; Do not copy result or passthrough attributes (range/noundef) to the new load.
+; Use the current intrinsic form because auto-upgrading the legacy form drops
+; these attributes before InstCombine.
+define <8 x i16> @fold_sel_into_masked_load_drop_attrs(ptr %ptr, <8 x i1> %mask, <8 x i16> %passthrough) {
+; CHECK-LABEL: @fold_sel_into_masked_load_drop_attrs(
+; CHECK-NEXT:    [[SEL:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0(ptr align 2 [[PTR:%.*]], <8 x i1> [[MASK:%.*]], <8 x i16> [[PASSTHROUGH:%.*]])
+; CHECK-NEXT:    ret <8 x i16> [[SEL]]
+;
+  %load = call range(i16 0, 2) <8 x i16> @llvm.masked.load.v8i16.p0(ptr align 2 %ptr, <8 x i1> %mask, <8 x i16> noundef zeroinitializer)
+  %sel = select <8 x i1> %mask, <8 x i16> %load, <8 x i16> %passthrough
+  ret <8 x i16> %sel
+}
+
 !0 = !{!1, !1, i64 0}
 !1 = !{!"int", !2, i64 0}
 !2 = !{!"omnipotent char", !8, i64 0}
@@ -184,3 +224,4 @@ define <vscale x 4 x i32> @fold_sel_into_masked_load_drop_metadata(ptr %loc, <vs
 declare <8 x float> @llvm.masked.load.v8f32.p0(ptr, i32 immarg, <8 x i1>, <8 x float>)
 declare <4 x i32> @llvm.masked.load.v4i32.p0(ptr, i32 immarg, <4 x i1>, <4 x i32>)
 declare <4 x float> @llvm.masked.load.v4f32.p0(ptr, i32 immarg, <4 x i1>, <4 x float>)
+declare <8 x i16> @llvm.masked.load.v8i16.p0(ptr, <8 x i1>, <8 x i16>)