Return lower cost for dupq

Author: huntergr-arm

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -5583,6 +5583,26 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
     Kind = TTI::SK_PermuteSingleSrc;
   }
 
+  // Segmented shuffle matching.
+  if (ST->hasSVE2p1() && CostKind == TTI::TCK_RecipThroughput &&
+      Kind == TTI::SK_PermuteSingleSrc && isa<FixedVectorType>(Tp) &&
+      Tp->getPrimitiveSizeInBits().isKnownMultipleOf(128)) {
+
+    FixedVectorType *VTy = cast<FixedVectorType>(Tp);
+    unsigned Segments = VTy->getPrimitiveSizeInBits() / 128;
+    unsigned SegmentElts = VTy->getNumElements() / Segments;
+
+    // dupq zd.t, zn.t[idx]
+    unsigned Lane = (unsigned)Mask[0];
+    if (SegmentElts * Segments == Mask.size() && Lane < SegmentElts) {
+      bool IsDupQ = true;
+      for (unsigned I = 1; I < Mask.size(); ++I)
+        IsDupQ &= (unsigned)Mask[I] == Lane + ((I / SegmentElts) * SegmentElts);
+      if (IsDupQ)
+        return LT.first;
+    }
+  }
+
   // Check for broadcast loads, which are supported by the LD1R instruction.
   // In terms of code-size, the shuffle vector is free when a load + dup get
   // folded into a LD1R. That's what we check and return here. For performance

llvm/test/Analysis/CostModel/AArch64/segmented-shufflevector-patterns.ll

@@ -4,11 +4,11 @@
 ;; Broadcast indexed lane within 128b segments (dupq zd.t, zn.t[idx])
 define void @dup_within_each_segment() #0 {
 ; CHECK-LABEL: 'dup_within_each_segment'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %dupq_b11 = shufflevector <32 x i8> poison, <32 x i8> poison, <32 x i32> <i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %dupq_h2 = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %dupq_s3 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 7, i32 7, i32 7, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %dupq_d0 = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %dupq_512b_d1 = shufflevector <8 x i64> poison, <8 x i64> poison, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %dupq_b11 = shufflevector <32 x i8> poison, <32 x i8> poison, <32 x i32> <i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27, i32 27>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %dupq_h2 = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %dupq_s3 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %dupq_d0 = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %dupq_512b_d1 = shufflevector <8 x i64> poison, <8 x i64> poison, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %dupq_b11 = shufflevector <32 x i8> poison, <32 x i8> poison, <32 x i32> <i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11,