From 2f4f8fcf64c67ee327e19b74a82a2330cfb32312 Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@gmail.com>
Date: Sun, 1 Mar 2020 00:01:38 -0800
Subject: [PATCH] [X86] Don't add DELETED_NODES to DAG combine worklist after
 calling SimplifyDemandedBits/SimplifyDemandedVectorElts.

These AddToWorklist calls were added in 84cd968f75bbd6e0fbabecc29d2c1090263adec7.
It's possible the SimplifyDemandedBits/SimplifyDemandedVectorElts
triggered CSE that deleted N. Detect that and avoid adding N
to the worklist.

Fixes PR45067.
---
 llvm/lib/Target/X86/X86ISelLowering.cpp | 18 ++++++++++++------
 llvm/test/CodeGen/X86/pr45067.ll        | 23 +++++++++++++++++++++++
 2 files changed, 35 insertions(+), 6 deletions(-)
 create mode 100644 llvm/test/CodeGen/X86/pr45067.ll

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 956f57d..4c3fd0d 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -42212,7 +42212,8 @@ static SDValue combineMaskedStore(SDNode *N, SelectionDAG &DAG,
   if (Mask.getScalarValueSizeInBits() != 1) {
     APInt DemandedBits(APInt::getSignMask(VT.getScalarSizeInBits()));
     if (TLI.SimplifyDemandedBits(Mask, DemandedBits, DCI)) {
-      DCI.AddToWorklist(N);
+      if (N->getOpcode() != ISD::DELETED_NODE)
+        DCI.AddToWorklist(N);
       return SDValue(N, 0);
     }
     if (SDValue NewMask =
@@ -42479,7 +42480,8 @@ static SDValue combineVEXTRACT_STORE(SDNode *N, SelectionDAG &DAG,
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
   if (TLI.SimplifyDemandedVectorElts(StoredVal, DemandedElts, KnownUndef,
                                      KnownZero, DCI)) {
-    DCI.AddToWorklist(N);
+    if (N->getOpcode() != ISD::DELETED_NODE)
+      DCI.AddToWorklist(N);
     return SDValue(N, 0);
   }
 
@@ -43828,7 +43830,8 @@ static SDValue combineBT(SDNode *N, SelectionDAG &DAG,
   unsigned BitWidth = N1.getValueSizeInBits();
   APInt DemandedMask = APInt::getLowBitsSet(BitWidth, Log2_32(BitWidth));
   if (DAG.getTargetLoweringInfo().SimplifyDemandedBits(N1, DemandedMask, DCI)) {
-    DCI.AddToWorklist(N);
+    if (N->getOpcode() != ISD::DELETED_NODE)
+      DCI.AddToWorklist(N);
     return SDValue(N, 0);
   }
 
@@ -43846,7 +43849,8 @@ static SDValue combineCVTPH2PS(SDNode *N, SelectionDAG &DAG,
     APInt DemandedElts = APInt::getLowBitsSet(8, 4);
     if (TLI.SimplifyDemandedVectorElts(Src, DemandedElts, KnownUndef, KnownZero,
                                        DCI)) {
-      DCI.AddToWorklist(N);
+      if (N->getOpcode() != ISD::DELETED_NODE)
+        DCI.AddToWorklist(N);
       return SDValue(N, 0);
     }
 
@@ -44755,7 +44759,8 @@ static SDValue combineX86GatherScatter(SDNode *N, SelectionDAG &DAG,
     const TargetLowering &TLI = DAG.getTargetLoweringInfo();
     APInt DemandedMask(APInt::getSignMask(Mask.getScalarValueSizeInBits()));
     if (TLI.SimplifyDemandedBits(Mask, DemandedMask, DCI)) {
-      DCI.AddToWorklist(N);
+      if (N->getOpcode() != ISD::DELETED_NODE)
+        DCI.AddToWorklist(N);
       return SDValue(N, 0);
     }
   }
@@ -44847,7 +44852,8 @@ static SDValue combineGatherScatter(SDNode *N, SelectionDAG &DAG,
     const TargetLowering &TLI = DAG.getTargetLoweringInfo();
     APInt DemandedMask(APInt::getSignMask(Mask.getScalarValueSizeInBits()));
     if (TLI.SimplifyDemandedBits(Mask, DemandedMask, DCI)) {
-      DCI.AddToWorklist(N);
+      if (N->getOpcode() != ISD::DELETED_NODE)
+        DCI.AddToWorklist(N);
       return SDValue(N, 0);
     }
   }
diff --git a/llvm/test/CodeGen/X86/pr45067.ll b/llvm/test/CodeGen/X86/pr45067.ll
new file mode 100644
index 0000000..fc1baa3
--- /dev/null
+++ b/llvm/test/CodeGen/X86/pr45067.ll
@@ -0,0 +1,23 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skylake | FileCheck %s
+
+@global = external global i32, align 4
+
+define void @foo(<8 x i32>* %x, <8 x i1> %y) {
+; CHECK-LABEL: foo:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; CHECK-NEXT:    vpbroadcastq _global@{{.*}}(%rip), %ymm2
+; CHECK-NEXT:    vpgatherqd %xmm1, (,%ymm2), %xmm3
+; CHECK-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; CHECK-NEXT:    vpslld $31, %ymm0, %ymm0
+; CHECK-NEXT:    vinserti128 $1, %xmm3, %ymm3, %ymm1
+; CHECK-NEXT:    vpmaskmovd %ymm1, %ymm0, (%rdi)
+; CHECK-NEXT:    ud2
+  %tmp = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> <i32* @global, i32* @global, i32* @global, i32* @global, i32* @global, i32* @global, i32* @global, i32* @global>, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
+  call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> %tmp, <8 x i32>* %x, i32 4, <8 x i1> %y)
+  unreachable
+}
+
+declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>, i32, <8 x i1>, <8 x i32>)
+declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
-- 
2.7.4