[LV] Add additional InLoop redution tests. NFC

llvm/test/Transforms/LoopVectorize/reduction-inloop-uf4.ll

@@ -0,0 +1,68 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=4 -force-vector-width=4 -force-reduction-intrinsics -dce -instcombine -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+
+define i32 @reduction_sum_single(i32* noalias nocapture %A) {
+; CHECK-LABEL: @reduction_sum_single(
+; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 4
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 8
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 12
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP8]] = add <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP9]] = add <4 x i32> [[VEC_PHI1]], [[WIDE_LOAD4]]
+; CHECK-NEXT:    [[TMP10]] = add <4 x i32> [[VEC_PHI2]], [[WIDE_LOAD5]]
+; CHECK-NEXT:    [[TMP11]] = add <4 x i32> [[VEC_PHI3]], [[WIDE_LOAD6]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <4 x i32> [[TMP9]], [[TMP8]]
+; CHECK-NEXT:    [[BIN_RDX7:%.*]] = add <4 x i32> [[TMP10]], [[BIN_RDX]]
+; CHECK-NEXT:    [[BIN_RDX8:%.*]] = add <4 x i32> [[TMP11]], [[BIN_RDX7]]
+; CHECK-NEXT:    [[TMP13:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[BIN_RDX8]])
+; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
+; CHECK:       .lr.ph:
+; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop !2
+; CHECK:       ._crit_edge:
+; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP13]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
+;
+entry:
+  br label %.lr.ph
+
+.lr.ph:                                           ; preds = %entry, %.lr.ph
+  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %l7, %.lr.ph ], [ 0, %entry ]
+  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+  %l3 = load i32, i32* %l2, align 4
+  %l7 = add i32 %sum.02, %l3
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, 256
+  br i1 %exitcond, label %._crit_edge, label %.lr.ph
+
+._crit_edge:                                      ; preds = %.lr.ph
+  %sum.0.lcssa = phi i32 [ %l7, %.lr.ph ]
+  ret i32 %sum.0.lcssa
+}