[VPlan] Use lane only for single-scalar select conditions.

Author: fhahn

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -597,8 +597,11 @@ Value *VPInstruction::generate(VPTransformState &State) {
     llvm_unreachable("should be handled by VPPhi::execute");
   }
   case Instruction::Select: {
-    bool OnlyFirstLaneUsed = vputils::onlyFirstLaneUsed(this);
-    Value *Cond = State.get(getOperand(0), OnlyFirstLaneUsed);
+    bool OnlyFirstLaneUsed =
+        State.VF.isScalar() || vputils::onlyFirstLaneUsed(this);
+    Value *Cond =
+        State.get(getOperand(0),
+                  OnlyFirstLaneUsed || vputils::isSingleScalar(getOperand(0)));
     Value *Op1 = State.get(getOperand(1), OnlyFirstLaneUsed);
     Value *Op2 = State.get(getOperand(2), OnlyFirstLaneUsed);
     return Builder.CreateSelect(Cond, Op1, Op2, Name);

llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll

@@ -424,7 +424,8 @@ define void @predicated_udiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[V:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; CHECK-NEXT:    [[TMP10:%.*]] = select <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> splat (i64 1)
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <vscale x 2 x i1> [[TMP6]], i32 0
+; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP7]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> splat (i64 1)
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -468,7 +469,8 @@ define void @predicated_udiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; FIXED-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V:%.*]], i64 0
 ; FIXED-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; FIXED-NEXT:    [[TMP0:%.*]] = icmp ne <4 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; FIXED-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[TMP0]], <4 x i64> [[BROADCAST_SPLAT]], <4 x i64> splat (i64 1)
+; FIXED-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
+; FIXED-NEXT:    [[TMP5:%.*]] = select i1 [[TMP1]], <4 x i64> [[BROADCAST_SPLAT]], <4 x i64> splat (i64 1)
 ; FIXED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FIXED:       vector.body:
 ; FIXED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -549,7 +551,8 @@ define void @predicated_sdiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[V:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; CHECK-NEXT:    [[TMP10:%.*]] = select <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> splat (i64 1)
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <vscale x 2 x i1> [[TMP6]], i32 0
+; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP7]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> splat (i64 1)
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -593,7 +596,8 @@ define void @predicated_sdiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; FIXED-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V:%.*]], i64 0
 ; FIXED-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; FIXED-NEXT:    [[TMP0:%.*]] = icmp ne <4 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; FIXED-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[TMP0]], <4 x i64> [[BROADCAST_SPLAT]], <4 x i64> splat (i64 1)
+; FIXED-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
+; FIXED-NEXT:    [[TMP5:%.*]] = select i1 [[TMP1]], <4 x i64> [[BROADCAST_SPLAT]], <4 x i64> splat (i64 1)
 ; FIXED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FIXED:       vector.body:
 ; FIXED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]

llvm/test/Transforms/LoopVectorize/reduction-small-size.ll

@@ -88,7 +88,8 @@ define i8 @PR34687_no_undef(i1 %c, i32 %x, i32 %n) {
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <4 x i1> poison, i1 [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i1> [[BROADCAST_SPLATINSERT2]], <4 x i1> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = select <4 x i1> [[BROADCAST_SPLAT]], <4 x i32> [[BROADCAST_SPLAT2]], <4 x i32> splat (i32 1)
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i1> [[BROADCAST_SPLAT]], i32 0
+; CHECK-NEXT:    [[TMP0:%.*]] = select i1 [[TMP2]], <4 x i32> [[BROADCAST_SPLAT2]], <4 x i32> splat (i32 1)
 ; CHECK-NEXT:    [[TMP1:%.*]] = sdiv <4 x i32> splat (i32 99), [[TMP0]]
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[BROADCAST_SPLAT]], <4 x i32> [[TMP1]], <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]