[LV] Inline CreateSplatIV call for scalar VFs (NFC).

This is a NFC change split off from D116123, as suggested there. D116123 will remove the last user of CreateSplatIV.
llvm · Jan 13, 2022 · 7ce48be · 7ce48be · jyknight · Jan 14, 2022
1 parent ec0a880
commit 7ce48be
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 3 deletions.
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2580,7 +2580,26 @@ void InnerLoopVectorizer::widenIntOrFpInduction(
   Value *Step = CreateStepValue(ID.getStep());
   if (State.VF.isScalar()) {
     Value *ScalarIV = CreateScalarIV(Step);
-    CreateSplatIV(ScalarIV, Step);
+    Type *ScalarTy = IntegerType::get(ScalarIV->getContext(),
+                                      Step->getType()->getScalarSizeInBits());
+    for (unsigned Part = 0; Part < UF; ++Part) {
+      Value *StartIdx = ConstantInt::get(ScalarTy, Part);
+      Instruction::BinaryOps MulOp = Instruction::Mul;
+      if (Step->getType()->isFloatingPointTy()) {
+        StartIdx = Builder.CreateUIToFP(StartIdx, Step->getType());
+        MulOp = Instruction::FMul;
+      }
+
+      Value *Mul = Builder.CreateBinOp(MulOp, StartIdx, Step);
+      Value *EntryPart = Builder.CreateBinOp(ID.getInductionOpcode(), ScalarIV,
+                                             Mul, "induction");
+      State.set(Def, EntryPart, Part);
+      if (Trunc) {
+        assert(!Step->getType()->isFloatingPointTy() &&
+               "fp inductions shouldn't be truncated");
+        addMetadata(EntryPart, Trunc);
+      }
+    }
     return;
   }
 

diff --git a/llvm/test/Transforms/LoopVectorize/float-induction.ll b/llvm/test/Transforms/LoopVectorize/float-induction.ll
@@ -1603,11 +1603,11 @@ define void @non_primary_iv_float_scalar(float* %A, i64 %N) {
 ; VEC1_INTERL2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; VEC1_INTERL2:       pred.store.continue:
 ; VEC1_INTERL2-NEXT:    br i1 [[TMP6]], label [[PRED_STORE_IF4:%.*]], label [[PRED_STORE_CONTINUE5]]
-; VEC1_INTERL2:       pred.store.if4:
+; VEC1_INTERL2:       pred.store.if6:
 ; VEC1_INTERL2-NEXT:    [[TMP7:%.*]] = fadd fast float [[TMP0]], 1.000000e+00
 ; VEC1_INTERL2-NEXT:    store float [[TMP7]], float* [[TMP2]], align 4
 ; VEC1_INTERL2-NEXT:    br label [[PRED_STORE_CONTINUE5]]
-; VEC1_INTERL2:       pred.store.continue5:
+; VEC1_INTERL2:       pred.store.continue7:
 ; VEC1_INTERL2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
 ; VEC1_INTERL2-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; VEC1_INTERL2-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]