[TTI] Add generic SK_Broadcast shuffle costs

I noticed while fixing PR39368 that we don't have generic shuffle costs for broadcast style shuffles.

This patch adds SK_BROADCAST handling, but exposes ARM/AARCH64 lack of handling of this type, which I've added a fix for at the same time.

Differential Revision: https://reviews.llvm.org/D53570

llvm-svn: 345253

1 files changed, 22 insertions, 3 deletions

diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 39a72f0edeb..a07c1e83a3f 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -400,10 +400,29 @@ int ARMTTIImpl::getAddressComputationCost(Type *Ty, ScalarEvolution *SE,
 
 int ARMTTIImpl::getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
                                Type *SubTp) {
-  // We only handle costs of reverse and select shuffles for now.
-  if (Kind != TTI::SK_Reverse && Kind != TTI::SK_Select)
-    return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+  if (Kind == TTI::SK_Broadcast) {
+    static const CostTblEntry NEONDupTbl[] = {
+        // VDUP handles these cases.
+        {ISD::VECTOR_SHUFFLE, MVT::v2i32, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v2f32, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v2i64, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v2f64, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v4i16, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v8i8,  1},
+
+        {ISD::VECTOR_SHUFFLE, MVT::v4i32, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v4f32, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v8i16, 1},
+        {ISD::VECTOR_SHUFFLE, MVT::v16i8, 1}};
 
+    std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
+
+    if (const auto *Entry = CostTableLookup(NEONDupTbl, ISD::VECTOR_SHUFFLE,
+                                            LT.second))
+      return LT.first * Entry->Cost;
+
+    return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+  }
   if (Kind == TTI::SK_Reverse) {
     static const CostTblEntry NEONShuffleTbl[] = {
         // Reverse shuffle cost one instruction if we are shuffling within a