[AArch64] Improve cost of non-zero lane splats

This adds a cost for non-zero lane splats, which is not included by default in
SK_Broadcast but can be handled by aarch64 dup lane instruction.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -3939,7 +3939,10 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
       LT.second.getVectorNumElements() == Mask.size() &&
       (Kind == TTI::SK_PermuteTwoSrc || Kind == TTI::SK_PermuteSingleSrc) &&
       (isZIPMask(Mask, LT.second, Unused) ||
-       isUZPMask(Mask, LT.second, Unused)))
+       isUZPMask(Mask, LT.second, Unused) ||
+       // Check for non-zero lane splats
+       all_of(drop_begin(Mask),
+              [&Mask](int M) { return M < 0 || M == Mask[0]; })))
     return 1;
 
   if (Kind == TTI::SK_Broadcast || Kind == TTI::SK_Transpose ||

llvm/test/Analysis/CostModel/AArch64/shuffle-other.ll

@@ -361,9 +361,9 @@ define void @uzp() {
 define void @multipart() {
 ; CHECK-LABEL: 'multipart'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16a = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16b = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v16c = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v16d = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16c = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16d = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v32a = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a4 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32idrev = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>