[AArch64] Limit vector splitting to vectors of size larger than 128bit

The intent of this code is to split larger vectors into smaller shuffles, but
it currently triggering on some small vector types. Limit it to vectors of size
>128bit.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -5448,6 +5448,7 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
   // If we have a Mask, and the LT is being legalized somehow, split the Mask
   // into smaller vectors and sum the cost of each shuffle.
   if (!Mask.empty() && isa<FixedVectorType>(Tp) && LT.second.isVector() &&
+      LT.second.getScalarSizeInBits() * Mask.size() > 128 &&
       Tp->getScalarSizeInBits() == LT.second.getScalarSizeInBits() &&
       Mask.size() > LT.second.getVectorNumElements() && !Index && !SubTp) {
 

llvm/test/Transforms/SLPVectorizer/AArch64/vectorizable-selects-uniform-cmps.ll

@@ -253,11 +253,11 @@ define void @select_uniform_ugt_16xi8(ptr %ptr, i8 %x) {
 ; CHECK-NEXT:    [[S_8:%.*]] = select i1 [[CMP_8]], i8 [[TMP1]], i8 [[X:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load <2 x i8>, ptr [[GEP_9]], align 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x i8>, ptr [[GEP_12]], align 1
+; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> poison, <16 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <2 x i8> [[TMP2]], <2 x i8> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i8> [[TMP2]], <2 x i8> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> [[TMP4]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 8, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i8> poison, i8 [[L_11]], i32 0
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <16 x i8> [[TMP10]], <16 x i8> poison, <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP11]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 8, i32 9, i32 10, i32 27, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[L_11]], i32 11
 ; CHECK-NEXT:    [[TMP7:%.*]] = call <16 x i8> @llvm.vector.insert.v16i8.v8i8(<16 x i8> [[TMP6]], <8 x i8> [[TMP0]], i64 0)
 ; CHECK-NEXT:    [[TMP8:%.*]] = call <16 x i8> @llvm.vector.insert.v16i8.v4i8(<16 x i8> [[TMP7]], <4 x i8> [[TMP3]], i64 12)
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp ugt <16 x i8> [[TMP8]], splat (i8 -1)

llvm/test/Transforms/VectorCombine/AArch64/shuffletoidentity.ll

@@ -262,8 +262,10 @@ define <8 x half> @splatandidentity(<8 x half> %a, <8 x half> %b) {
 
 define <8 x half> @splattwice(<8 x half> %a, <8 x half> %b) {
 ; CHECK-LABEL: @splattwice(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x half> [[A:%.*]], <8 x half> poison, <8 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <8 x half> [[B:%.*]], <8 x half> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT:    [[AS:%.*]] = shufflevector <8 x half> [[A:%.*]], <8 x half> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[BS:%.*]] = shufflevector <8 x half> [[B:%.*]], <8 x half> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x half> [[AS]], <4 x half> poison, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x half> [[BS]], <4 x half> poison, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
 ; CHECK-NEXT:    [[R:%.*]] = fadd <8 x half> [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    ret <8 x half> [[R]]
 ;