[llvm] [VPlan] Account for dead FOR splice simplification in cost model (PR #131486)

[Florian Hahn via llvm-commits]

================
@@ -0,0 +1,111 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -p loop-vectorize -S %s | FileCheck %s
+
+; If a FOR isn't used the VPInstruction::FirstOrderRecurrenceSplice will be dead
+; and won't be costed in the VPlan cost model. Make sure we account for this
+; simplifcation in comparison to the legacy cost model.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64"
+
+define void @no_use() {
+; CHECK-LABEL: define void @no_use() {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <4 x i32> [ <i32 poison, i32 poison, i32 poison, i32 0>, %[[VECTOR_PH]] ], [ [[STEP_ADD:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[STEP_ADD]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD]], splat (i32 4)
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp eq i32 [[INDEX_NEXT]], 40
+; CHECK-NEXT:    br i1 [[TMP0]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[STEP_ADD]], i32 3
+; CHECK-NEXT:    br i1 false, label %[[F_EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 40, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[FOR_COND_I:.*]]
+; CHECK:       [[FOR_COND_I]]:
+; CHECK-NEXT:    [[D_0_I:%.*]] = phi i32 [ [[SCALAR_RECUR_INIT]], %[[SCALAR_PH]] ], [ [[E_0_I:%.*]], %[[FOR_COND_I]] ]
+; CHECK-NEXT:    [[E_0_I]] = phi i32 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[INC_I:%.*]], %[[FOR_COND_I]] ]
+; CHECK-NEXT:    [[INC_I]] = add i32 [[E_0_I]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT_I:%.*]] = icmp eq i32 [[E_0_I]], 43
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT_I]], label %[[F_EXIT]], label %[[FOR_COND_I]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       [[F_EXIT]]:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.cond.i
+
+for.cond.i:
+  %d.0.i = phi i32 [ 0, %entry ], [ %e.0.i, %for.cond.i ]
+  %e.0.i = phi i32 [ 0, %entry ], [ %inc.i, %for.cond.i ]
----------------
fhahn wrote:

Might be slightly clearer to use more descriptive names for phis.
```suggestion
  %for = phi i32 [ 0, %entry ], [ %e.0.i, %for.cond.i ]
  %iv = phi i32 [ 0, %entry ], [ %iv.next, %for.cond.i ]
```

https://github.com/llvm/llvm-project/pull/131486