[LV][AArch64] Add test for fp128 fmuladd reduction.(NFC)

This patch add the test for the fmuladd reduction to show the test
change/fail for the cost model change.

Note that without the fp128 load and trunc, there is no failure.

Author: ElvisWang123

llvm/test/Transforms/LoopVectorize/AArch64/f128-fmuladd-reduction.ll

@@ -0,0 +1,113 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -mtriple=aarch64 -mcpu=neoverse-v2 -p loop-vectorize %s -S | FileCheck %s
+define double @fp128_fmuladd_reduction(ptr %start0, ptr %start1, ptr %end0, ptr %end1, double %x, i64 %n) {
+; CHECK-LABEL: define double @fp128_fmuladd_reduction(
+; CHECK-SAME: ptr [[START0:%.*]], ptr [[START1:%.*]], ptr [[END0:%.*]], ptr [[END1:%.*]], double [[X:%.*]], i64 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 4
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], 4
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[N_VEC]], 16
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i8, ptr [[START0]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[N_VEC]], 8
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i8, ptr [[START1]], i64 [[TMP2]]
+; 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 double [ [[X]], %[[VECTOR_PH]] ], [ [[TMP29:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[OFFSET_IDX]], 16
+; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], 32
+; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], 48
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START0]], i64 [[OFFSET_IDX]]
+; CHECK-NEXT:    [[NEXT_GEP1:%.*]] = getelementptr i8, ptr [[START0]], i64 [[TMP4]]
+; CHECK-NEXT:    [[NEXT_GEP2:%.*]] = getelementptr i8, ptr [[START0]], i64 [[TMP5]]
+; CHECK-NEXT:    [[NEXT_GEP3:%.*]] = getelementptr i8, ptr [[START0]], i64 [[TMP6]]
+; CHECK-NEXT:    [[OFFSET_IDX4:%.*]] = mul i64 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX4]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[OFFSET_IDX4]], 16
+; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[OFFSET_IDX4]], 24
+; CHECK-NEXT:    [[NEXT_GEP5:%.*]] = getelementptr i8, ptr [[START1]], i64 [[OFFSET_IDX4]]
+; CHECK-NEXT:    [[NEXT_GEP6:%.*]] = getelementptr i8, ptr [[START1]], i64 [[TMP7]]
+; CHECK-NEXT:    [[NEXT_GEP7:%.*]] = getelementptr i8, ptr [[START1]], i64 [[TMP8]]
+; CHECK-NEXT:    [[NEXT_GEP8:%.*]] = getelementptr i8, ptr [[START1]], i64 [[TMP9]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load fp128, ptr [[NEXT_GEP]], align 16
+; CHECK-NEXT:    [[TMP11:%.*]] = load fp128, ptr [[NEXT_GEP1]], align 16
+; CHECK-NEXT:    [[TMP12:%.*]] = load fp128, ptr [[NEXT_GEP2]], align 16
+; CHECK-NEXT:    [[TMP13:%.*]] = load fp128, ptr [[NEXT_GEP3]], align 16
+; CHECK-NEXT:    [[TMP14:%.*]] = load double, ptr [[NEXT_GEP5]], align 16
+; CHECK-NEXT:    [[TMP15:%.*]] = load double, ptr [[NEXT_GEP6]], align 16
+; CHECK-NEXT:    [[TMP16:%.*]] = load double, ptr [[NEXT_GEP7]], align 16
+; CHECK-NEXT:    [[TMP17:%.*]] = load double, ptr [[NEXT_GEP8]], align 16
+; CHECK-NEXT:    [[TMP18:%.*]] = fptrunc fp128 [[TMP10]] to double
+; CHECK-NEXT:    [[TMP19:%.*]] = fptrunc fp128 [[TMP11]] to double
+; CHECK-NEXT:    [[TMP20:%.*]] = fptrunc fp128 [[TMP12]] to double
+; CHECK-NEXT:    [[TMP21:%.*]] = fptrunc fp128 [[TMP13]] to double
+; CHECK-NEXT:    [[TMP22:%.*]] = fmul double [[TMP18]], [[TMP14]]
+; CHECK-NEXT:    [[TMP23:%.*]] = fmul double [[TMP19]], [[TMP15]]
+; CHECK-NEXT:    [[TMP24:%.*]] = fmul double [[TMP20]], [[TMP16]]
+; CHECK-NEXT:    [[TMP25:%.*]] = fmul double [[TMP21]], [[TMP17]]
+; CHECK-NEXT:    [[TMP26:%.*]] = fadd double [[VEC_PHI]], [[TMP22]]
+; CHECK-NEXT:    [[TMP27:%.*]] = fadd double [[TMP26]], [[TMP23]]
+; CHECK-NEXT:    [[TMP28:%.*]] = fadd double [[TMP27]], [[TMP24]]
+; CHECK-NEXT:    [[TMP29]] = fadd double [[TMP28]], [[TMP25]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP1]], %[[MIDDLE_BLOCK]] ], [ [[START0]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL9:%.*]] = phi ptr [ [[TMP3]], %[[MIDDLE_BLOCK]] ], [ [[START1]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL10:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi double [ [[TMP29]], %[[MIDDLE_BLOCK]] ], [ [[X]], %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR0:%.*]] = phi ptr [ [[PTR0_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; CHECK-NEXT:    [[PTR1:%.*]] = phi ptr [ [[PTR1_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL9]], %[[SCALAR_PH]] ]
+; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL10]], %[[SCALAR_PH]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi double [ [[RED_NEXT:%.*]], %[[LOOP]] ], [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ]
+; CHECK-NEXT:    [[PTR0_NEXT]] = getelementptr i8, ptr [[PTR0]], i64 16
+; CHECK-NEXT:    [[PTR1_NEXT]] = getelementptr i8, ptr [[PTR1]], i64 8
+; CHECK-NEXT:    [[LOAD0:%.*]] = load fp128, ptr [[PTR0]], align 16
+; CHECK-NEXT:    [[LOAD1:%.*]] = load double, ptr [[PTR1]], align 16
+; CHECK-NEXT:    [[TRUNC:%.*]] = fptrunc fp128 [[LOAD0]] to double
+; CHECK-NEXT:    [[RED_NEXT]] = tail call double @llvm.fmuladd.f64(double [[TRUNC]], double [[LOAD1]], double [[RED]])
+; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; CHECK-NEXT:    [[CMP1_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP1_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[LCSSA:%.*]] = phi double [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP29]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret double [[LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr0 = phi ptr [ %ptr0.next, %loop ], [ %start0, %entry ]
+  %ptr1 = phi ptr [ %ptr1.next, %loop ], [ %start1, %entry ]
+  %iv = phi i64 [ %iv.next, %loop ], [ 0, %entry ]
+  %red = phi double [ %red.next, %loop ], [ %x, %entry ]
+  %ptr0.next = getelementptr i8, ptr %ptr0, i64 16
+  %ptr1.next = getelementptr i8, ptr %ptr1, i64 8
+  %load0 = load fp128, ptr %ptr0, align 16
+  %load1 = load double, ptr %ptr1, align 16
+  %trunc = fptrunc fp128 %load0 to double
+  %red.next = tail call double @llvm.fmuladd.f64(double %trunc, double %load1, double %red)
+  %iv.next = add i64 %iv, 1
+  %cmp1.not = icmp eq i64 %iv.next, %n
+  br i1 %cmp1.not, label %exit, label %loop
+
+exit:
+  %lcssa = phi double [ %red.next, %loop ]
+  ret double %lcssa
+}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]]}
+;.