[llvm] [VPlan] Try to hoist Previous (and operands), if sinking fails for FORs. (PR #108945)

[Florian Hahn via llvm-commits]

================
@@ -278,3 +278,67 @@ exit:
   store double %.lcssa, ptr %C
   ret i64 %.in.lcssa
 }
+
+; Test for https://github.com/llvm/llvm-project/issues/106523.
+define void @for_iv_trunc_optimized(ptr %dst) {
+; CHECK-LABEL: @for_iv_trunc_optimized(
+; CHECK-NEXT:  bb:
+; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <4 x i32> [ <i32 poison, i32 poison, i32 poison, i32 1>, [[VECTOR_PH]] ], [ [[STEP_ADD:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR1:%.*]] = phi <4 x i32> [ <i32 poison, i32 poison, i32 poison, i32 0>, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 1, i32 2, i32 3, i32 4>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[STEP_ADD]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
+; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <4 x i32> [[VECTOR_RECUR]], <4 x i32> [[VEC_IND]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[VEC_IND]], <4 x i32> [[STEP_ADD]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT:    [[TMP2:%.*]] = or <4 x i32> [[TMP0]], zeroinitializer
+; CHECK-NEXT:    [[TMP3]] = or <4 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i32> [[TMP5]], i32 3
+; CHECK-NEXT:    store i32 [[TMP6]], ptr [[DST:%.*]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD]], <i32 4, i32 4, i32 4, i32 4>
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 336
+; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[STEP_ADD]], i32 3
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT3:%.*]] = extractelement <4 x i32> [[TMP3]], i32 3
+; CHECK-NEXT:    br i1 false, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 337, [[MIDDLE_BLOCK]] ], [ 1, [[BB:%.*]] ]
+; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ], [ 1, [[BB]] ]
+; CHECK-NEXT:    [[SCALAR_RECUR_INIT4:%.*]] = phi i32 [ [[VECTOR_RECUR_EXTRACT3]], [[MIDDLE_BLOCK]] ], [ 0, [[BB]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[ADD:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[FOR_1:%.*]] = phi i32 [ [[TRUNC:%.*]], [[LOOP]] ], [ [[SCALAR_RECUR_INIT]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[FOR_2:%.*]] = phi i32 [ [[OR:%.*]], [[LOOP]] ], [ [[SCALAR_RECUR_INIT4]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[OR]] = or i32 [[FOR_1]], 0
+; CHECK-NEXT:    [[ADD]] = add i64 [[IV]], 1
+; CHECK-NEXT:    store i32 [[FOR_2]], ptr [[DST]], align 4
+; CHECK-NEXT:    [[ICMP:%.*]] = icmp ult i64 [[IV]], 337
+; CHECK-NEXT:    [[TRUNC]] = trunc i64 [[IV]] to i32
+; CHECK-NEXT:    br i1 [[ICMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+bb:
+  br label %loop
+
+loop:
+  %iv = phi i64 [ %add, %loop ], [ 1, %bb ]
+  %for.1 = phi i32 [ %trunc, %loop ], [ 1, %bb ]
+  %for.2 = phi i32 [ %or, %loop ], [ 0, %bb ]
+  %or = or i32 %for.1, 0
----------------
fhahn wrote:

Added, thanks!

https://github.com/llvm/llvm-project/pull/108945