[SLP][NFC] Add precommit test for unprofitable ordered fadd reductions (llvm#199428)

Adds a test case reproducing a scenario where the cost model incorrectly
evaluates an unprofitable ordered fadd reduction chain as profitable.

Further details can be found on this issue:
llvm#199267

Author: KavinTheG

llvm/test/Transforms/SLPVectorizer/RISCV/ordered-reduction.ll

@@ -0,0 +1,78 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -S --passes=slp-vectorizer -mtriple=riscv64-unknown-linux-gnu -mattr="+v" < %s | FileCheck %s
+
+target triple = "riscv64-unknown-linux-gnu"
+
+define void @test1(ptr %arrayidx.i60, ptr %24, ptr %arrayidx44.i61, double %.pre117.i70, double %.pre116.i68, double %.pre115.i67, double %.pre114.i65, double %.pre113.i64, double %.pre.i62) {
+; CHECK-LABEL: define void @test1(
+; CHECK-SAME: ptr [[ARRAYIDX_I60:%.*]], ptr [[TMP0:%.*]], ptr [[ARRAYIDX44_I61:%.*]], double [[DOTPRE117_I70:%.*]], double [[DOTPRE116_I68:%.*]], double [[DOTPRE115_I67:%.*]], double [[DOTPRE114_I65:%.*]], double [[DOTPRE113_I64:%.*]], double [[DOTPRE_I62:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[FOR_COND_PREHEADER:.*]]:
+; CHECK-NEXT:    br label %[[FOR_BODY:.*]]
+; CHECK:       [[FOR_BODY]]:
+; CHECK-NEXT:    [[TMP1:%.*]] = phi double [ [[DOTPRE117_I70]], %[[FOR_COND_PREHEADER]] ], [ [[TMP9:%.*]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP2:%.*]] = phi double [ [[DOTPRE116_I68]], %[[FOR_COND_PREHEADER]] ], [ [[TMP1]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP3:%.*]] = phi double [ [[DOTPRE115_I67]], %[[FOR_COND_PREHEADER]] ], [ [[TMP8:%.*]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP4:%.*]] = phi double [ [[DOTPRE114_I65]], %[[FOR_COND_PREHEADER]] ], [ [[DIV_I86:%.*]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = phi double [ [[DOTPRE113_I64]], %[[FOR_COND_PREHEADER]] ], [ [[TMP7:%.*]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = phi double [ [[DOTPRE_I62]], %[[FOR_COND_PREHEADER]] ], [ [[TMP5]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[INDVARS_IV_I72:%.*]] = phi i64 [ 1, %[[FOR_COND_PREHEADER]] ], [ [[INDVARS_IV_NEXT_I74:%.*]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[ADD_I73:%.*]] = fadd double [[TMP5]], [[TMP6]]
+; CHECK-NEXT:    [[INDVARS_IV_NEXT_I74]] = add nuw nsw i64 [[INDVARS_IV_I72]], 1
+; CHECK-NEXT:    [[ARRAYIDX23_I75:%.*]] = getelementptr inbounds nuw [8 x i8], ptr [[ARRAYIDX_I60]], i64 [[INDVARS_IV_NEXT_I74]]
+; CHECK-NEXT:    [[TMP7]] = load double, ptr [[ARRAYIDX23_I75]], align 8
+; CHECK-NEXT:    [[ARRAYIDX34_I78:%.*]] = getelementptr inbounds nuw [8 x i8], ptr [[TMP0]], i64 [[INDVARS_IV_I72]]
+; CHECK-NEXT:    [[ARRAYIDX40_I80:%.*]] = getelementptr inbounds nuw [8 x i8], ptr [[TMP0]], i64 [[INDVARS_IV_NEXT_I74]]
+; CHECK-NEXT:    [[TMP8]] = load double, ptr [[ARRAYIDX40_I80]], align 8
+; CHECK-NEXT:    [[ARRAYIDX60_I84:%.*]] = getelementptr inbounds nuw [8 x i8], ptr [[ARRAYIDX44_I61]], i64 [[INDVARS_IV_NEXT_I74]]
+; CHECK-NEXT:    [[TMP9]] = load double, ptr [[ARRAYIDX60_I84]], align 8
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <8 x double> poison, double [[TMP7]], i32 0
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <8 x double> [[TMP10]], double [[ADD_I73]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <8 x double> [[TMP11]], double [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <8 x double> [[TMP12]], double [[TMP3]], i32 3
+; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[TMP8]], i32 4
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[TMP2]], i32 5
+; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[TMP1]], i32 6
+; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[TMP9]], i32 7
+; CHECK-NEXT:    [[TMP18:%.*]] = call double @llvm.vector.reduce.fadd.v8f64(double -0.000000e+00, <8 x double> [[TMP17]])
+; CHECK-NEXT:    [[DIV_I86]] = fdiv double [[TMP18]], 9.000000e+00
+; CHECK-NEXT:    store double [[DIV_I86]], ptr [[ARRAYIDX34_I78]], align 8
+; CHECK-NEXT:    [[EXITCOND_NOT_I87:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT_I74]], 1999
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT_I87]], label %[[FOR_END:.*]], label %[[FOR_BODY]]
+; CHECK:       [[FOR_END]]:
+; CHECK-NEXT:    ret void
+;
+for.cond.preheader:
+  br label %for.body
+
+for.body:
+  %25 = phi double [ %.pre117.i70, %for.cond.preheader ], [ %33, %for.body ]
+  %26 = phi double [ %.pre116.i68, %for.cond.preheader ], [ %25, %for.body ]
+  %27 = phi double [ %.pre115.i67, %for.cond.preheader ], [ %32, %for.body ]
+  %28 = phi double [ %.pre114.i65, %for.cond.preheader ], [ %div.i86, %for.body ]
+  %29 = phi double [ %.pre113.i64, %for.cond.preheader ], [ %31, %for.body ]
+  %30 = phi double [ %.pre.i62, %for.cond.preheader ], [ %29, %for.body ]
+  %indvars.iv.i72 = phi i64 [ 1, %for.cond.preheader ], [ %indvars.iv.next.i74, %for.body ]
+  %add.i73 = fadd double %29, %30
+  %indvars.iv.next.i74 = add nuw nsw i64 %indvars.iv.i72, 1
+  %arrayidx23.i75 = getelementptr inbounds nuw [8 x i8], ptr %arrayidx.i60, i64 %indvars.iv.next.i74
+  %31 = load double, ptr %arrayidx23.i75, align 8
+  %add24.i76 = fadd double %add.i73, %31
+  %add30.i77 = fadd double %28, %add24.i76
+  %arrayidx34.i78 = getelementptr inbounds nuw [8 x i8], ptr %24, i64 %indvars.iv.i72
+  %add35.i79 = fadd double %27, %add30.i77
+  %arrayidx40.i80 = getelementptr inbounds nuw [8 x i8], ptr %24, i64 %indvars.iv.next.i74
+  %32 = load double, ptr %arrayidx40.i80, align 8
+  %add41.i81 = fadd double %32, %add35.i79
+  %add48.i82 = fadd double %26, %add41.i81
+  %add54.i83 = fadd double %25, %add48.i82
+  %arrayidx60.i84 = getelementptr inbounds nuw [8 x i8], ptr %arrayidx44.i61, i64 %indvars.iv.next.i74
+  %33 = load double, ptr %arrayidx60.i84, align 8
+  %add61.i85 = fadd double %33, %add54.i83
+  %div.i86 = fdiv double %add61.i85, 9.000000e+00
+  store double %div.i86, ptr %arrayidx34.i78, align 8
+  %exitcond.not.i87 = icmp eq i64 %indvars.iv.next.i74, 1999
+  br i1 %exitcond.not.i87, label %for.end, label %for.body
+
+for.end:
+  ret void
+}