[SLP] Check for PHI nodes (potentially cycles!) when checking dependencies

When checking for dependecies for gather nodes with users with the same
last instruction, cannot rely on the index order, if there is (even
potential!) cycle in the graph, which may cause order not work correctly
and cause compiler crash.

Fixes llvm#127128

(cherry picked from commit ac217ee)

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -13181,8 +13181,16 @@ BoUpSLP::isGatherShuffledSingleRegisterEntry(
           continue;
         // If the user instruction is used for some reason in different
         // vectorized nodes - make it depend on index.
+        // If any vector node is PHI node, this dependency might not work
+        // because of cycle dependencies, so disable it.
         if (TEUseEI.UserTE != UseEI.UserTE &&
-            TEUseEI.UserTE->Idx < UseEI.UserTE->Idx)
+            (TEUseEI.UserTE->Idx < UseEI.UserTE->Idx ||
+             any_of(
+                 VectorizableTree,
+                 [](const std::unique_ptr<TreeEntry> &TE) {
+                   return TE->State == TreeEntry::Vectorize &&
+                          TE->getOpcode() == Instruction::PHI;
+                 })))
           continue;
       }
 

llvm/test/Transforms/SLPVectorizer/X86/delayed-gather-emission.ll

@@ -31,7 +31,7 @@ define void @test() {
 ; CHECK-NEXT:    [[TOBOOL:%.*]] = fcmp une float [[I2]], 0.000000e+00
 ; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <2 x i32> <i32 poison, i32 0>
 ; CHECK-NEXT:    [[TMP9]] = insertelement <2 x float> [[TMP8]], float [[I2]], i32 0
-; CHECK-NEXT:    [[TMP10]] = shufflevector <2 x float> [[TMP9]], <2 x float> [[TMP2]], <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT:    [[TMP10]] = insertelement <2 x float> [[TMP2]], float [[I2]], i32 0
 ; CHECK-NEXT:    br i1 [[TOBOOL]], label [[BB1]], label [[BB2]]
 ;
 entry:

llvm/test/Transforms/SLPVectorizer/X86/matching-gather-nodes-phi-users.ll

@@ -8,7 +8,7 @@
 ; YAML: Function:        test
 ; YAML: Args:
 ; YAML:   - String:          'Stores SLP vectorized with cost '
-; YAML:   - Cost:            '-6'
+; YAML:   - Cost:            '-3'
 ; YAML:   - String:          ' and with tree size '
 ; YAML:   - TreeSize:        '14'
 ; YAML: ...

llvm/test/Transforms/SLPVectorizer/X86/perfect-matched-reused-bv.ll

@@ -7,16 +7,17 @@ define void @test() {
 ; CHECK-NEXT:  [[BB:.*]]:
 ; CHECK-NEXT:    br label %[[BB1:.*]]
 ; CHECK:       [[BB1]]:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i32> [ zeroinitializer, %[[BB]] ], [ [[TMP4:%.*]], %[[BB4:.*]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = or <2 x i32> [[TMP0]], zeroinitializer
+; CHECK-NEXT:    [[PHI:%.*]] = phi i32 [ 0, %[[BB]] ], [ [[ADD6:%.*]], %[[BB4:.*]] ]
+; CHECK-NEXT:    [[PHI2:%.*]] = phi i32 [ 0, %[[BB]] ], [ 0, %[[BB4]] ]
+; CHECK-NEXT:    [[OR:%.*]] = or i32 [[PHI2]], 0
+; CHECK-NEXT:    [[OR3:%.*]] = or i32 [[PHI]], 0
 ; CHECK-NEXT:    br i1 false, label %[[BB7:.*]], label %[[BB4]]
 ; CHECK:       [[BB4]]:
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> <i32 0, i32 poison>, <2 x i32> <i32 2, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = add <2 x i32> zeroinitializer, [[TMP2]]
-; CHECK-NEXT:    [[TMP4]] = add <2 x i32> zeroinitializer, [[TMP2]]
+; CHECK-NEXT:    [[ADD6]] = add i32 [[PHI]], 0
 ; CHECK-NEXT:    br i1 false, label %[[BB7]], label %[[BB1]]
 ; CHECK:       [[BB7]]:
-; CHECK-NEXT:    [[TMP5:%.*]] = phi <2 x i32> [ [[TMP1]], %[[BB1]] ], [ [[TMP3]], %[[BB4]] ]
+; CHECK-NEXT:    [[PHI8:%.*]] = phi i32 [ [[OR]], %[[BB1]] ], [ 0, %[[BB4]] ]
+; CHECK-NEXT:    [[PHI9:%.*]] = phi i32 [ [[OR3]], %[[BB1]] ], [ [[ADD6]], %[[BB4]] ]
 ; CHECK-NEXT:    ret void
 ;
 bb:

llvm/test/Transforms/SLPVectorizer/X86/phi-node-with-cycle.ll

@@ -0,0 +1,59 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S --passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell < %s | FileCheck %s
+
+define void @test(float %0) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: float [[TMP0:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x float> <float 0.000000e+00, float poison>, float [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = fdiv <2 x float> [[TMP2]], zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x float> <float poison, float 0.000000e+00>, float [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = fdiv <2 x float> [[TMP4]], zeroinitializer
+; CHECK-NEXT:    br label %[[BB6:.*]]
+; CHECK:       [[BB6]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x float> [[TMP5]], zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = fsub <2 x float> zeroinitializer, [[TMP7]]
+; CHECK-NEXT:    br label %[[BB10:.*]]
+; CHECK:       [[BB9:.*]]:
+; CHECK-NEXT:    br label %[[BB10]]
+; CHECK:       [[BB10]]:
+; CHECK-NEXT:    [[TMP11:%.*]] = phi <2 x float> [ [[TMP8]], %[[BB6]] ], [ poison, %[[BB9]] ]
+; CHECK-NEXT:    br label %[[BB12:.*]]
+; CHECK:       [[BB12]]:
+; CHECK-NEXT:    [[TMP13:%.*]] = fmul <2 x float> [[TMP3]], zeroinitializer
+; CHECK-NEXT:    [[TMP14:%.*]] = fsub <2 x float> [[TMP11]], [[TMP13]]
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
+; CHECK-NEXT:    [[TMP17:%.*]] = fadd float [[TMP15]], [[TMP16]]
+; CHECK-NEXT:    [[TMP18:%.*]] = call float @llvm.fabs.f32(float [[TMP17]])
+; CHECK-NEXT:    ret void
+;
+  %2 = fdiv float 0.000000e+00, 0.000000e+00
+  %3 = fdiv float 0.000000e+00, 0.000000e+00
+  %4 = fdiv float %0, 0.000000e+00
+  br label %5
+
+5:
+  %6 = fmul float %4, 0.000000e+00
+  %7 = fsub float 0.000000e+00, %6
+  %8 = fmul float %3, 0.000000e+00
+  %9 = fsub float 0.000000e+00, %8
+  br label %11
+
+10:
+  br label %11
+
+11:
+  %12 = phi float [ %7, %5 ], [ 0.000000e+00, %10 ]
+  %13 = phi float [ %9, %5 ], [ 0.000000e+00, %10 ]
+  br label %14
+
+14:
+  %15 = fmul float %2, 0.000000e+00
+  %16 = fsub float %12, %15
+  %17 = fmul float %4, 0.000000e+00
+  %18 = fsub float %13, %17
+  %19 = fadd float %16, %18
+  %20 = call float @llvm.fabs.f32(float %19)
+  ret void
+}
+