Automerge: [msan] Handle llvm.x86.vcvtps2ph.128/256 explicitly (#130705)

thurstond · github-actions[bot] · commit 6f604f0173bc · 2025-03-13T20:45:51.000Z
Check whether each lane is fully initialized, and propagate the shadow per lane instead of using the strict handling of visitInstruction. Updates the tests from llvm/llvm-project#129807
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -207,6 +207,7 @@
 #include <cstddef>
 #include <cstdint>
 #include <memory>
+#include <numeric>
 #include <string>
 #include <tuple>
 
@@ -3273,6 +3274,64 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
     setOriginForNaryOp(I);
   }
 
+  /// Handle x86 SSE single-precision to half-precision conversion.
+  ///
+  /// e.g.,
+  ///      <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0)
+  ///      <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0)
+  /// Note: if the output has more elements, they are zero-initialized (and
+  /// therefore the shadow will also be initialized).
+  ///
+  /// This differs from handleSSEVectorConvertIntrinsic() because it
+  /// propagates uninitialized shadow (instead of checking the shadow).
+  void handleSSEVectorConvertIntrinsicByProp(IntrinsicInst &I) {
+    assert(I.arg_size() == 2);
+    Value *Src = I.getArgOperand(0);
+    assert(Src->getType()->isVectorTy());
+    [[maybe_unused]] Value *RoundingMode = I.getArgOperand(1);
+    assert(RoundingMode->getType()->isIntegerTy());
+
+    // The return type might have more elements than the input.
+    // Temporarily shrink the return type's number of elements.
+    VectorType *ShadowType = cast<VectorType>(getShadowTy(&I));
+    if (ShadowType->getElementCount() ==
+        cast<VectorType>(Src->getType())->getElementCount() * 2)
+      ShadowType = VectorType::getHalfElementsVectorType(ShadowType);
+
+    assert(ShadowType->getElementCount() ==
+           cast<VectorType>(Src->getType())->getElementCount());
+
+    IRBuilder<> IRB(&I);
+    Value *S0 = getShadow(&I, 0);
+
+    /// For scalars:
+    /// Since they are converting from floating-point to integer, the output is
+    /// - fully uninitialized if *any* bit of the input is uninitialized
+    /// - fully ininitialized if all bits of the input are ininitialized
+    /// We apply the same principle on a per-field basis for vectors.
+    Value *Shadow =
+        IRB.CreateSExt(IRB.CreateICmpNE(S0, getCleanShadow(S0)), ShadowType);
+
+    // The return type might have more elements than the input.
+    // Extend the return type back to its original width if necessary.
+    Value *FullShadow = getCleanShadow(&I);
+
+    if (Shadow->getType() == FullShadow->getType()) {
+      FullShadow = Shadow;
+    } else {
+      SmallVector<int, 8> ShadowMask(
+          cast<FixedVectorType>(FullShadow->getType())->getNumElements());
+      std::iota(ShadowMask.begin(), ShadowMask.end(), 0);
+
+      // Append zeros
+      FullShadow =
+          IRB.CreateShuffleVector(Shadow, getCleanShadow(Shadow), ShadowMask);
+    }
+
+    setShadow(&I, FullShadow);
+    setOriginForNaryOp(I);
+  }
+
   // Instrument x86 SSE vector convert intrinsic.
   //
   // This function instruments intrinsics like cvtsi2ss:
@@ -4868,6 +4927,12 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
       break;
     }
 
+    case Intrinsic::x86_vcvtps2ph_128:
+    case Intrinsic::x86_vcvtps2ph_256: {
+      handleSSEVectorConvertIntrinsicByProp(I);
+      break;
+    }
+
     case Intrinsic::fshl:
     case Intrinsic::fshr:
       handleFunnelShift(I);
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/f16c-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/f16c-intrinsics.ll
@@ -3,7 +3,7 @@
 ;
 ; Forked from llvm/test/CodeGen/X86/f16c-intrinsics.ll
 ;
-; Handled by visitInstruction:
+; Handled by handleSSEVectorConvertIntrinsicByProp:
 ; - llvm.x86.vcvtps2ph.128/256
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
@@ -14,15 +14,11 @@ define <8 x i16> @test_x86_vcvtps2ph_128(<4 x float> %a0) #0 {
 ; CHECK-SAME: <4 x float> [[A0:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i32> [[TMP1]] to i128
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i128 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1:![0-9]+]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4:[0-9]+]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:    [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A0]], i32 0)
-; CHECK-NEXT:    store <8 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <8 x i16> [[TMP11]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <8 x i16> [[RES]]
 ;
   %res = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
@@ -35,15 +31,10 @@ define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0) #0 {
 ; CHECK-SAME: <8 x float> [[A0:%.*]]) #[[ATTR0]] {
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x i32> [[TMP1]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne <8 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <8 x i1> [[TMP2]] to <8 x i16>
 ; CHECK-NEXT:    [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A0]], i32 0)
-; CHECK-NEXT:    store <8 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <8 x i16> [[TMP3]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <8 x i16> [[RES]]
 ;
   %res = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
@@ -59,24 +50,19 @@ define void @test_x86_vcvtps2ph_256_m(ptr nocapture %d, <8 x float> %a) nounwind
 ; CHECK-NEXT:    [[TMP17:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
 ; CHECK-NEXT:    [[TMP18:%.*]] = load i64, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP4:%.*]] = bitcast <8 x i32> [[TMP17]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP20:%.*]] = icmp ne <8 x i32> [[TMP17]], zeroinitializer
+; CHECK-NEXT:    [[TMP21:%.*]] = sext <8 x i1> [[TMP20]] to <8 x i16>
 ; CHECK-NEXT:    [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A]], i32 3)
 ; CHECK-NEXT:    [[_MSCMP1:%.*]] = icmp ne i64 [[TMP18]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK:       [[BB6]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
+; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB5:.*]], label %[[BB6:.*]], !prof [[PROF1:![0-9]+]]
+; CHECK:       [[BB5]]:
+; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4:[0-9]+]]
 ; CHECK-NEXT:    unreachable
-; CHECK:       [[BB7]]:
+; CHECK:       [[BB6]]:
 ; CHECK-NEXT:    [[TMP1:%.*]] = ptrtoint ptr [[D]] to i64
 ; CHECK-NEXT:    [[TMP2:%.*]] = xor i64 [[TMP1]], 87960930222080
 ; CHECK-NEXT:    [[TMP3:%.*]] = inttoptr i64 [[TMP2]] to ptr
-; CHECK-NEXT:    store <8 x i16> zeroinitializer, ptr [[TMP3]], align 16
+; CHECK-NEXT:    store <8 x i16> [[TMP21]], ptr [[TMP3]], align 16
 ; CHECK-NEXT:    store <8 x i16> [[TMP0]], ptr [[D]], align 16
 ; CHECK-NEXT:    ret void
 ;
@@ -93,14 +79,11 @@ define void @test_x86_vcvtps2ph_128_m(ptr nocapture %d, <4 x float> %a) nounwind
 ; CHECK-NEXT:    [[TMP9:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
 ; CHECK-NEXT:    [[TMP10:%.*]] = load i64, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x i32> [[TMP9]] to i128
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP12:%.*]] = icmp ne <4 x i32> [[TMP9]], zeroinitializer
+; CHECK-NEXT:    [[TMP13:%.*]] = sext <4 x i1> [[TMP12]] to <4 x i16>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP13]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:    [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A]], i32 3)
+; CHECK-NEXT:    [[_MSPROP:%.*]] = shufflevector <8 x i16> [[TMP11]], <8 x i16> splat (i16 -1), <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[TMP0]], <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[_MSCMP1:%.*]] = icmp ne i64 [[TMP10]], 0
 ; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB7:.*]], label %[[BB8:.*]], !prof [[PROF1]]
@@ -111,7 +94,7 @@ define void @test_x86_vcvtps2ph_128_m(ptr nocapture %d, <4 x float> %a) nounwind
 ; CHECK-NEXT:    [[TMP2:%.*]] = ptrtoint ptr [[D]] to i64
 ; CHECK-NEXT:    [[TMP3:%.*]] = xor i64 [[TMP2]], 87960930222080
 ; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i64 [[TMP3]] to ptr
-; CHECK-NEXT:    store <4 x i16> zeroinitializer, ptr [[TMP4]], align 8
+; CHECK-NEXT:    store <4 x i16> [[_MSPROP]], ptr [[TMP4]], align 8
 ; CHECK-NEXT:    store <4 x i16> [[TMP1]], ptr [[D]], align 8
 ; CHECK-NEXT:    ret void
 ;
@@ -129,26 +112,24 @@ define void @test_x86_vcvtps2ph_128_m2(ptr nocapture %hf4x16, <4 x float> %f4X86
 ; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i32> [[TMP0]] to i128
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i128 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:    [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
+; CHECK-NEXT:    [[TMP13:%.*]] = bitcast <8 x i16> [[TMP14]] to <2 x i64>
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x double>
+; CHECK-NEXT:    [[_MSPROP:%.*]] = extractelement <2 x i64> [[TMP13]], i32 0
 ; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <2 x double> [[TMP12]], i32 0
 ; CHECK-NEXT:    [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB7:.*]], label %[[BB8:.*]], !prof [[PROF1]]
-; CHECK:       [[BB7]]:
+; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
+; CHECK:       [[BB8]]:
 ; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
 ; CHECK-NEXT:    unreachable
-; CHECK:       [[BB8]]:
+; CHECK:       [[BB9]]:
 ; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
 ; CHECK-NEXT:    [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
 ; CHECK-NEXT:    [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
-; CHECK-NEXT:    store i64 0, ptr [[TMP17]], align 8
+; CHECK-NEXT:    store i64 [[_MSPROP]], ptr [[TMP17]], align 8
 ; CHECK-NEXT:    store double [[VECEXT]], ptr [[HF4X16]], align 8
 ; CHECK-NEXT:    ret void
 ;
@@ -167,27 +148,25 @@ define void @test_x86_vcvtps2ph_128_m3(ptr nocapture %hf4x16, <4 x float> %f4X86
 ; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i32> [[TMP0]] to i128
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i128 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label %[[BB3:.*]], label %[[BB4:.*]], !prof [[PROF1]]
-; CHECK:       [[BB3]]:
-; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
-; CHECK-NEXT:    unreachable
-; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
+; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:    [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
-; CHECK-NEXT:    [[TMP12:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x i64>
+; CHECK-NEXT:    [[TMP12:%.*]] = bitcast <8 x i16> [[TMP13]] to <2 x i64>
+; CHECK-NEXT:    [[TMP14:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x i64>
 ; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <2 x i64> [[TMP12]], i32 0
+; CHECK-NEXT:    [[VECEXT1:%.*]] = extractelement <2 x i64> [[TMP14]], i32 0
 ; CHECK-NEXT:    [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB7:.*]], label %[[BB8:.*]], !prof [[PROF1]]
-; CHECK:       [[BB7]]:
+; CHECK-NEXT:    br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
+; CHECK:       [[BB8]]:
 ; CHECK-NEXT:    call void @__msan_warning_noreturn() #[[ATTR4]]
 ; CHECK-NEXT:    unreachable
-; CHECK:       [[BB8]]:
+; CHECK:       [[BB9]]:
 ; CHECK-NEXT:    [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
 ; CHECK-NEXT:    [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
 ; CHECK-NEXT:    [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
-; CHECK-NEXT:    store i64 0, ptr [[TMP17]], align 8
-; CHECK-NEXT:    store i64 [[VECEXT]], ptr [[HF4X16]], align 8
+; CHECK-NEXT:    store i64 [[VECEXT]], ptr [[TMP17]], align 8
+; CHECK-NEXT:    store i64 [[VECEXT1]], ptr [[HF4X16]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -199,6 +178,3 @@ entry:
 }
 
 attributes #0 = { sanitize_memory }
-;.
-; CHECK: [[PROF1]] = !{!"branch_weights", i32 1, i32 1048575}
-;.
