llvm-project/llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll

151 lines
6.6 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -loop-vectorize -mtriple=x86_64-apple-darwin %s | FileCheck %s
; Two mostly identical functions. The only difference is the presence of
; fast-math flags on the second. The loop is a pretty simple reduction:
; for (int i = 0; i < 32; ++i)
; if (arr[i] != 42)
; tot += arr[i];
define double @sumIfScalar(double* nocapture readonly %arr) {
; CHECK-LABEL: @sumIfScalar(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[I_NEXT:%.*]], [[NEXT_ITER:%.*]] ]
; CHECK-NEXT: [[TOT:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[TOT_NEXT:%.*]], [[NEXT_ITER]] ]
; CHECK-NEXT: [[ADDR:%.*]] = getelementptr double, double* [[ARR:%.*]], i32 [[I]]
; CHECK-NEXT: [[NEXTVAL:%.*]] = load double, double* [[ADDR]]
; CHECK-NEXT: [[TST:%.*]] = fcmp une double [[NEXTVAL]], 4.200000e+01
; CHECK-NEXT: br i1 [[TST]], label [[DO_ADD:%.*]], label [[NO_ADD:%.*]]
; CHECK: do.add:
; CHECK-NEXT: [[TOT_NEW:%.*]] = fadd double [[TOT]], [[NEXTVAL]]
; CHECK-NEXT: br label [[NEXT_ITER]]
; CHECK: no.add:
; CHECK-NEXT: br label [[NEXT_ITER]]
; CHECK: next.iter:
; CHECK-NEXT: [[TOT_NEXT]] = phi double [ [[TOT]], [[NO_ADD]] ], [ [[TOT_NEW]], [[DO_ADD]] ]
; CHECK-NEXT: [[I_NEXT]] = add i32 [[I]], 1
; CHECK-NEXT: [[AGAIN:%.*]] = icmp ult i32 [[I_NEXT]], 32
; CHECK-NEXT: br i1 [[AGAIN]], label [[LOOP]], label [[DONE:%.*]]
; CHECK: done:
; CHECK-NEXT: [[TOT_NEXT_LCSSA:%.*]] = phi double [ [[TOT_NEXT]], [[NEXT_ITER]] ]
; CHECK-NEXT: ret double [[TOT_NEXT_LCSSA]]
;
entry:
br label %loop
loop:
%i = phi i32 [0, %entry], [%i.next, %next.iter]
%tot = phi double [0.0, %entry], [%tot.next, %next.iter]
%addr = getelementptr double, double* %arr, i32 %i
%nextval = load double, double* %addr
%tst = fcmp une double %nextval, 42.0
br i1 %tst, label %do.add, label %no.add
do.add:
%tot.new = fadd double %tot, %nextval
br label %next.iter
no.add:
br label %next.iter
next.iter:
%tot.next = phi double [%tot, %no.add], [%tot.new, %do.add]
%i.next = add i32 %i, 1
%again = icmp ult i32 %i.next, 32
br i1 %again, label %loop, label %done
done:
ret double %tot.next
}
define double @sumIfVector(double* nocapture readonly %arr) {
; CHECK-LABEL: @sumIfVector(
; 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 i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x double> [ zeroinitializer, [[VECTOR_PH]] ], [ [[PREDPHI:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i32> undef, i32 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i32> [[BROADCAST_SPLATINSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1>
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr double, double* [[ARR:%.*]], i32 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr double, double* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x double>, <2 x double>* [[TMP3]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fcmp fast une <2 x double> [[WIDE_LOAD]], <double 4.200000e+01, double 4.200000e+01>
; CHECK-NEXT: [[TMP5:%.*]] = fadd fast <2 x double> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT: [[TMP6:%.*]] = xor <2 x i1> [[TMP4]], <i1 true, i1 true>
; CHECK-NEXT: [[PREDPHI]] = select <2 x i1> [[TMP4]], <2 x double> [[TMP5]], <2 x double> [[VEC_PHI]]
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 2
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 32
; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK: middle.block:
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <2 x double> [[PREDPHI]], <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <2 x double> [[PREDPHI]], [[RDX_SHUF]]
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[BIN_RDX]], i32 0
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 32, 32
; CHECK-NEXT: br i1 [[CMP_N]], label [[DONE:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 32, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[TMP8]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[I_NEXT:%.*]], [[NEXT_ITER:%.*]] ]
; CHECK-NEXT: [[TOT:%.*]] = phi double [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[TOT_NEXT:%.*]], [[NEXT_ITER]] ]
; CHECK-NEXT: [[ADDR:%.*]] = getelementptr double, double* [[ARR]], i32 [[I]]
; CHECK-NEXT: [[NEXTVAL:%.*]] = load double, double* [[ADDR]]
; CHECK-NEXT: [[TST:%.*]] = fcmp fast une double [[NEXTVAL]], 4.200000e+01
; CHECK-NEXT: br i1 [[TST]], label [[DO_ADD:%.*]], label [[NO_ADD:%.*]]
; CHECK: do.add:
; CHECK-NEXT: [[TOT_NEW:%.*]] = fadd fast double [[TOT]], [[NEXTVAL]]
; CHECK-NEXT: br label [[NEXT_ITER]]
; CHECK: no.add:
; CHECK-NEXT: br label [[NEXT_ITER]]
; CHECK: next.iter:
; CHECK-NEXT: [[TOT_NEXT]] = phi double [ [[TOT]], [[NO_ADD]] ], [ [[TOT_NEW]], [[DO_ADD]] ]
; CHECK-NEXT: [[I_NEXT]] = add i32 [[I]], 1
; CHECK-NEXT: [[AGAIN:%.*]] = icmp ult i32 [[I_NEXT]], 32
; CHECK-NEXT: br i1 [[AGAIN]], label [[LOOP]], label [[DONE]], !llvm.loop !2
; CHECK: done:
; CHECK-NEXT: [[TOT_NEXT_LCSSA:%.*]] = phi double [ [[TOT_NEXT]], [[NEXT_ITER]] ], [ [[TMP8]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret double [[TOT_NEXT_LCSSA]]
;
entry:
br label %loop
loop:
%i = phi i32 [0, %entry], [%i.next, %next.iter]
%tot = phi double [0.0, %entry], [%tot.next, %next.iter]
%addr = getelementptr double, double* %arr, i32 %i
%nextval = load double, double* %addr
%tst = fcmp fast une double %nextval, 42.0
br i1 %tst, label %do.add, label %no.add
do.add:
%tot.new = fadd fast double %tot, %nextval
br label %next.iter
no.add:
br label %next.iter
next.iter:
%tot.next = phi double [%tot, %no.add], [%tot.new, %do.add]
%i.next = add i32 %i, 1
%again = icmp ult i32 %i.next, 32
br i1 %again, label %loop, label %done
done:
ret double %tot.next
}