TheRock/compiler/amd-llvm/llvm/test/CodeGen/AArch64/sms-loop-carried-fp-exceptions2.mir

# RUN: llc -mtriple=aarch64 -run-pass=pipeliner -debug-only=pipeliner -aarch64-enable-pipeliner -pipeliner-mve-cg %s -o /dev/null 2>&1 | FileCheck %s
# REQUIRES: asserts

# Test a case where fenv is enabled, there are instructions that may raise a
# floatin-point exception, but there is no instruction for barrier event. In
# this case no loop-carried dependencies are necessary.

# CHECK:      ===== Loop Carried Edges Begin =====
# CHECK-NEXT: ===== Loop Carried Edges End =====

--- |
  define dso_local float @f(ptr nocapture noundef writeonly %a, float noundef %y, i32 noundef %n) local_unnamed_addr {
  entry:
    %conv = tail call float @llvm.experimental.constrained.fptrunc.f32.f64(double 1.000000e+00, metadata !"round.dynamic", metadata !"fpexcept.strict")
    %cmp8 = icmp sgt i32 %n, 0
    br i1 %cmp8, label %for.body.preheader, label %for.cond.cleanup

  for.body.preheader:
    %wide.trip.count = zext nneg i32 %n to i64
    br label %for.body

  for.cond.cleanup:
    %acc.0.lcssa = phi float [ %conv, %entry ], [ %mul, %for.body ]
    ret float %acc.0.lcssa

  for.body:
    %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
    %acc.010 = phi float [ %conv, %for.body.preheader ], [ %mul, %for.body ]
    %tmp = trunc i64 %indvars.iv to i32
    %conv2 = tail call float @llvm.experimental.constrained.sitofp.f32.i32(i32 %tmp, metadata !"round.dynamic", metadata !"fpexcept.strict")
    %add = tail call float @llvm.experimental.constrained.fadd.f32(float %conv2, float %y, metadata !"round.dynamic", metadata !"fpexcept.strict")
    %mul = tail call float @llvm.experimental.constrained.fmul.f32(float %acc.010, float %add, metadata !"round.dynamic", metadata !"fpexcept.strict")
    %0 = shl nuw nsw i64 %indvars.iv, 2
    %scevgep = getelementptr i8, ptr %a, i64 %0
    store float %add, ptr %scevgep, align 4, !tbaa !6
    %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
    %exitcond.not = icmp eq i64 %wide.trip.count, %indvars.iv.next
    br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
  }

  declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)

  declare float @llvm.experimental.constrained.sitofp.f32.i32(i32, metadata, metadata)

  declare float @llvm.experimental.constrained.fadd.f32(float, float, metadata, metadata)

  declare float @llvm.experimental.constrained.fmul.f32(float, float, metadata, metadata)

  !6 = !{!7, !7, i64 0}
  !7 = !{!"float", !8, i64 0}
  !8 = !{!"omnipotent char", !9, i64 0}
  !9 = !{!"Simple C/C++ TBAA"}

...
---
name:            f
tracksRegLiveness: true
body:             |
  bb.0.entry:
    successors: %bb.1, %bb.2
    liveins: $x0, $s0, $w1
  
    %9:gpr32common = COPY $w1
    %8:fpr32 = COPY $s0
    %7:gpr64common = COPY $x0
    %10:fpr64 = FMOVDi 112
    %0:fpr32 = FCVTSDr killed %10, implicit $fpcr
    dead $wzr = SUBSWri %9, 1, 0, implicit-def $nzcv
    Bcc 11, %bb.2, implicit $nzcv
    B %bb.1
  
  bb.1.for.body.preheader:
    %13:gpr32 = ORRWrs $wzr, %9, 0
    %1:gpr64 = SUBREG_TO_REG killed %13, %subreg.sub_32
    %14:gpr64all = COPY $xzr
    %12:gpr64all = COPY %14
    B %bb.3
  
  bb.2.for.cond.cleanup:
    %2:fpr32 = PHI %0, %bb.0, %5, %bb.3
    $s0 = COPY %2
    RET_ReallyLR implicit $s0
  
  bb.3.for.body:
    successors: %bb.2, %bb.3
  
    %3:gpr64common = PHI %12, %bb.1, %6, %bb.3
    %4:fpr32 = PHI %0, %bb.1, %5, %bb.3
    %15:gpr32 = COPY %3.sub_32
    %16:fpr32 = SCVTFUWSri killed %15, implicit $fpcr
    %17:fpr32 = FADDSrr killed %16, %8, implicit $fpcr
    %5:fpr32 = FMULSrr %4, %17, implicit $fpcr
    STRSroX %17, %7, %3, 0, 1 :: (store (s32) into %ir.scevgep, !tbaa !6)
    %18:gpr64common = nuw nsw ADDXri %3, 1, 0
    %6:gpr64all = COPY %18
    dead $xzr = SUBSXrr %1, %18, implicit-def $nzcv
    Bcc 0, %bb.2, implicit $nzcv
    B %bb.3
...