[ARM] MVE shuffle broadcast costs

A VDUP will perform a vector broadcast in a single instruction. Update the cost
model for MVE accordingly.

Code originally by David Sherwood.

Differential Revision: https://reviews.llvm.org/D63448

llvm-svn: 368589

diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 4e87f25..f3da1b8 100644 (file)
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -514,6 +514,23 @@ int ARMTTIImpl::getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
         return LT.first * Entry->Cost;
     }
   }
+  if (ST->hasMVEIntegerOps()) {
+    if (Kind == TTI::SK_Broadcast) {
+      static const CostTblEntry MVEDupTbl[] = {
+          // VDUP handles these cases.
+          {ISD::VECTOR_SHUFFLE, MVT::v4i32, 1},
+          {ISD::VECTOR_SHUFFLE, MVT::v8i16, 1},
+          {ISD::VECTOR_SHUFFLE, MVT::v16i8, 1},
+          {ISD::VECTOR_SHUFFLE, MVT::v4f32, 1},
+          {ISD::VECTOR_SHUFFLE, MVT::v8f16, 1}};
+
+      std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
+
+      if (const auto *Entry = CostTableLookup(MVEDupTbl, ISD::VECTOR_SHUFFLE,
+                                              LT.second))
+        return LT.first * Entry->Cost;
+    }
+  }
   return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
 }
 

diff --git a/llvm/test/Analysis/CostModel/ARM/shuffle.ll b/llvm/test/Analysis/CostModel/ARM/shuffle.ll
index 53668b7..78c2dc8 100644 (file)
--- a/llvm/test/Analysis/CostModel/ARM/shuffle.ll
+++ b/llvm/test/Analysis/CostModel/ARM/shuffle.ll
@@ -5,16 +5,16 @@
 define void @broadcast() {
 ; CHECK-MVE-LABEL: 'broadcast'
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v7 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v9 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %v10 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v10 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v11 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v12 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v13 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v12 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v13 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v14 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v15 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v16 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> zeroinitializer
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v17 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v15 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> zeroinitializer
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v17 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Unknown cost for instruction: %v18 = shufflevector <8 x half> undef, <8 x half> undef, <4 x i32> zeroinitializer
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;