llvm/test/CodeGen/AArch64/fp16_fast_math.ll

; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=aarch64 -mattr=-fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-CVT
; RUN: llc < %s -mtriple=aarch64 -mattr=+fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-FP16

; Check that the output instructions have the same fast math flags as the input
; fadd, even when fadd is promoted to float type.

define half @normal_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: normal_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: normal_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd half %x, %y
  ret half %add
}

define half @fast_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: fast_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: fast_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nnan ninf nsz arcp contract afn reassoc nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd fast half %x, %y
  ret half %add
}

define half @ninf_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: ninf_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = ninf nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = ninf nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: ninf_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = ninf nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd ninf half %x, %y
  ret half %add
}