[VPlan] Return invalid cost if any skeleton block has invalid costs.

llvm/lib/Transforms/Vectorize/VPlan.cpp

@@ -1072,9 +1072,13 @@ InstructionCost VPlan::cost(ElementCount VF, VPCostContext &Ctx) {
   // blocks, like the preheader or middle blocks.
   InstructionCost Cost = getVectorLoopRegion()->cost(VF, Ctx);
 
-  // If any instructions in the middle block are invalid return invalid.
-  // TODO: Remove once no VPlans with VF == vscale x 1 and first-order recurrences are created.
-  if (!getMiddleBlock()->cost(VF, Ctx).isValid())
+  // If any instructions in the skeleton outside loop regions are invalid return
+  // invalid.
+  if (any_of(VPBlockUtils::blocksOnly<VPBasicBlock>(
+                 vp_depth_first_shallow(getEntry())),
+             [&VF, &Ctx](VPBasicBlock *VPBB) {
+               return !VPBB->cost(VF, Ctx).isValid();
+             }))
     return InstructionCost::getInvalid();
 
   return Cost;

llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll

@@ -1,47 +1,28 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 5
-; REQUIRES: asserts
-; RUN: opt -passes=loop-vectorize -mtriple=aarch64 -mattr=+sve -S \
-; RUN:   -debug-only=loop-vectorize %s 2>&1 | FileCheck %s
+; RUN: opt -passes=loop-vectorize -mtriple=aarch64 -mattr=+sve -S %s | FileCheck %s
 
-; FIXME: Hoisted vector code should be costed with scalable cost.
-; In this example, `<vscale x 4 x float> @llvm.minimumnum` has an invalid cost,
-; and hence should not be produced by LoopVectorize.
-
-; CHECK: LV: Found an estimated cost of Invalid for VF vscale x 4 For instruction:   %res = tail call float @llvm.minimumnum.f32(float %arg, float 0.000000e+00)
 define void @cost_hoisted_vector_code(ptr %p, float %arg) {
 ; CHECK-LABEL: define void @cost_hoisted_vector_code(
 ; CHECK-SAME: ptr [[P:%.*]], float [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8
 ; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
 ; CHECK:       [[VECTOR_PH]]:
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 8
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 -1, [[TMP3]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 -1, [[N_MOD_VF]]
-; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 8
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[ARG]], i64 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x float> [[BROADCAST_SPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = add i64 1, [[N_VEC]]
-; CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> [[BROADCAST_SPLAT]], <vscale x 4 x float> zeroinitializer)
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[ARG]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> [[BROADCAST_SPLAT]], <4 x float> zeroinitializer)
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[INDEX:%.*]] = add i64 1, [[INDEX1]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr float, ptr [[P]], i64 [[INDEX]]
-; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP10:%.*]] = mul nuw i64 [[TMP9]], 4
-; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr float, ptr [[TMP8]], i64 [[TMP10]]
-; CHECK-NEXT:    store <vscale x 4 x float> [[TMP7]], ptr [[TMP8]], align 4
-; CHECK-NEXT:    store <vscale x 4 x float> [[TMP7]], ptr [[TMP11]], align 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr float, ptr [[TMP8]], i32 4
+; CHECK-NEXT:    store <4 x float> [[TMP0]], ptr [[TMP8]], align 4
+; CHECK-NEXT:    store <4 x float> [[TMP0]], ptr [[TMP2]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], 8
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], -8
+; CHECK-NEXT:    br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 -1, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], [[EXIT:label %.*]], label %[[SCALAR_PH]]
+; CHECK-NEXT:    br label %[[SCALAR_PH]]
 ; CHECK:       [[SCALAR_PH]]:
 ;
 entry: