[SLP] Pass VecPred argument to getCmpSelInstrCost.

Check if all compares in VL have the same predicate and pass it to
getCmpSelInstrCost, to improve cost-modeling on targets that only
support compare/select combinations for certain uniform predicates.

This leads to additional vectorization in some cases

```
Same hash: 217 (filtered out)
Remaining: 19
Metric: SLP.NumVectorInstructions

Program                                        base    slp2    diff
 test-suite...marks/SciMark2-C/scimark2.test    11.00   26.00  136.4%
 test-suite...T2006/445.gobmk/445.gobmk.test    79.00  135.00  70.9%
 test-suite...ediabench/gsm/toast/toast.test    54.00   71.00  31.5%
 test-suite...telecomm-gsm/telecomm-gsm.test    54.00   71.00  31.5%
 test-suite...CI_Purple/SMG2000/smg2000.test   426.00  542.00  27.2%
 test-suite...ch/g721/g721encode/encode.test    30.00   24.00  -20.0%
 test-suite...000/186.crafty/186.crafty.test   116.00  138.00  19.0%
 test-suite...ications/JM/ldecod/ldecod.test   697.00  765.00   9.8%
 test-suite...6/464.h264ref/464.h264ref.test   822.00  886.00   7.8%
 test-suite...chmarks/MallocBench/gs/gs.test   154.00  162.00   5.2%
 test-suite...nsumer-lame/consumer-lame.test   621.00  651.00   4.8%
 test-suite...lications/ClamAV/clamscan.test   223.00  231.00   3.6%
 test-suite...marks/7zip/7zip-benchmark.test   680.00  695.00   2.2%
 test-suite...CFP2000/177.mesa/177.mesa.test   2121.00 2129.00  0.4%
 test-suite...:: External/Povray/povray.test   2406.00 2412.00  0.2%
 test-suite...TimberWolfMC/timberwolfmc.test   634.00  634.00   0.0%
 test-suite...CFP2006/433.milc/433.milc.test   1036.00 1036.00  0.0%
 test-suite.../Benchmarks/nbench/nbench.test   321.00  321.00   0.0%
 test-suite...ctions-flt/Reductions-flt.test    NaN      5.00   nan%
```

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D90124

Author: fhahn

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -3455,9 +3455,25 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
       }
       auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
       int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
-      int VecCost =
-          TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
-                                  CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
+
+      // Check if all entries in VL are either compares or selects with compares
+      // as condition that have the same predicates.
+      CmpInst::Predicate VecPred = CmpInst::BAD_ICMP_PREDICATE;
+      bool First = true;
+      for (auto *V : VL) {
+        CmpInst::Predicate CurrentPred;
+        auto MatchCmp = m_Cmp(CurrentPred, m_Value(), m_Value());
+        if ((!match(V, m_Select(MatchCmp, m_Value(), m_Value())) &&
+             !match(V, MatchCmp)) ||
+            (!First && VecPred != CurrentPred)) {
+          VecPred = CmpInst::BAD_ICMP_PREDICATE;
+          break;
+        }
+        First = false;
+        VecPred = CurrentPred;
+      }
+      int VecCost = TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
+                                            VecPred, CostKind, VL0);
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::FNeg:

llvm/test/Transforms/SLPVectorizer/AArch64/horizontal.ll

@@ -15,7 +15,7 @@ target triple = "aarch64--linux"
 ; YAML-NEXT: Function:        test_select
 ; YAML-NEXT: Args:
 ; YAML-NEXT:   - String:          'Vectorized horizontal reduction with cost '
-; YAML-NEXT:   - Cost:            '-8'
+; YAML-NEXT:   - Cost:            '-20'
 ; YAML-NEXT:   - String:          ' and with tree size '
 ; YAML-NEXT:   - TreeSize:        '8'
 
@@ -244,7 +244,7 @@ for.end:                                          ; preds = %for.end.loopexit, %
 ; YAML-NEXT: Function:        test_unrolled_select
 ; YAML-NEXT: Args:
 ; YAML-NEXT:   - String:          'Vectorized horizontal reduction with cost '
-; YAML-NEXT:   - Cost:            '-31'
+; YAML-NEXT:   - Cost:            '-37'
 ; YAML-NEXT:   - String:          ' and with tree size '
 ; YAML-NEXT:   - TreeSize:        '10'