llvm/test/CodeGen/LoongArch/fp16-promote.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc --mtriple=loongarch32 --mattr=+d < %s | FileCheck %s --check-prefix=LA32
; RUN: llc --mtriple=loongarch64 --mattr=+d < %s | FileCheck %s --check-prefix=LA64

define void @test_load_store(ptr %p, ptr %q) nounwind {
; LA32-LABEL: test_load_store:
; LA32:       # %bb.0:
; LA32-NEXT:    ld.h $a0, $a0, 0
; LA32-NEXT:    st.h $a0, $a1, 0
; LA32-NEXT:    ret
;
; LA64-LABEL: test_load_store:
; LA64:       # %bb.0:
; LA64-NEXT:    ld.h $a0, $a0, 0
; LA64-NEXT:    st.h $a0, $a1, 0
; LA64-NEXT:    ret
  %a = load half, ptr %p
  store half %a, ptr %q
  ret void
}

define float @test_fpextend_float(ptr %p) nounwind {
; LA32-LABEL: test_fpextend_float:
; LA32:       # %bb.0:
; LA32-NEXT:    ld.hu $a0, $a0, 0
; LA32-NEXT:    b %plt(__gnu_h2f_ieee)
;
; LA64-LABEL: test_fpextend_float:
; LA64:       # %bb.0:
; LA64-NEXT:    ld.hu $a0, $a0, 0
; LA64-NEXT:    b %plt(__gnu_h2f_ieee)
  %a = load half, ptr %p
  %r = fpext half %a to float
  ret float %r
}

define double @test_fpextend_double(ptr %p) nounwind {
; LA32-LABEL: test_fpextend_double:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    ld.hu $a0, $a0, 0
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fcvt.d.s $fa0, $fa0
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fpextend_double:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -16
; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    ld.hu $a0, $a0, 0
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fcvt.d.s $fa0, $fa0
; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 16
; LA64-NEXT:    ret
  %a = load half, ptr %p
  %r = fpext half %a to double
  ret double %r
}

define void @test_fptrunc_float(float %f, ptr %p) nounwind {
; LA32-LABEL: test_fptrunc_float:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 8 # 4-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    st.h $a0, $fp, 0
; LA32-NEXT:    ld.w $fp, $sp, 8 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fptrunc_float:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -16
; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 0 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    st.h $a0, $fp, 0
; LA64-NEXT:    ld.d $fp, $sp, 0 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 16
; LA64-NEXT:    ret
  %a = fptrunc float %f to half
  store half %a, ptr %p
  ret void
}

define void @test_fptrunc_double(double %d, ptr %p) nounwind {
; LA32-LABEL: test_fptrunc_double:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 8 # 4-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    bl %plt(__truncdfhf2)
; LA32-NEXT:    st.h $a0, $fp, 0
; LA32-NEXT:    ld.w $fp, $sp, 8 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fptrunc_double:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -16
; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 0 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    bl %plt(__truncdfhf2)
; LA64-NEXT:    st.h $a0, $fp, 0
; LA64-NEXT:    ld.d $fp, $sp, 0 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 16
; LA64-NEXT:    ret
  %a = fptrunc double %d to half
  store half %a, ptr %p
  ret void
}

define half @test_fadd_reg(half %a, half %b) nounwind {
; LA32-LABEL: test_fadd_reg:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 8 # 4-byte Folded Spill
; LA32-NEXT:    fst.d $fs0, $sp, 0 # 8-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    move $a0, $a1
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmov.s $fs0, $fa0
; LA32-NEXT:    move $a0, $fp
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fadd.s $fa0, $fa0, $fs0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    fld.d $fs0, $sp, 0 # 8-byte Folded Reload
; LA32-NEXT:    ld.w $fp, $sp, 8 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fadd_reg:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -32
; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 16 # 8-byte Folded Spill
; LA64-NEXT:    fst.d $fs0, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    move $a0, $a1
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmov.s $fs0, $fa0
; LA64-NEXT:    move $a0, $fp
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fadd.s $fa0, $fa0, $fs0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    fld.d $fs0, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $fp, $sp, 16 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 32
; LA64-NEXT:    ret
  %r = fadd half %a, %b
  ret half %r
}

define void @test_fadd_mem(ptr %p, ptr %q) nounwind {
; LA32-LABEL: test_fadd_mem:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -32
; LA32-NEXT:    st.w $ra, $sp, 28 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 24 # 4-byte Folded Spill
; LA32-NEXT:    st.w $s0, $sp, 20 # 4-byte Folded Spill
; LA32-NEXT:    fst.d $fs0, $sp, 8 # 8-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    ld.hu $s0, $a0, 0
; LA32-NEXT:    ld.hu $a0, $a1, 0
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmov.s $fs0, $fa0
; LA32-NEXT:    move $a0, $s0
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fadd.s $fa0, $fa0, $fs0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    st.h $a0, $fp, 0
; LA32-NEXT:    fld.d $fs0, $sp, 8 # 8-byte Folded Reload
; LA32-NEXT:    ld.w $s0, $sp, 20 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $fp, $sp, 24 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 28 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 32
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fadd_mem:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -32
; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 16 # 8-byte Folded Spill
; LA64-NEXT:    st.d $s0, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    fst.d $fs0, $sp, 0 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    ld.hu $s0, $a0, 0
; LA64-NEXT:    ld.hu $a0, $a1, 0
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmov.s $fs0, $fa0
; LA64-NEXT:    move $a0, $s0
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fadd.s $fa0, $fa0, $fs0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    st.h $a0, $fp, 0
; LA64-NEXT:    fld.d $fs0, $sp, 0 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $s0, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $fp, $sp, 16 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 32
; LA64-NEXT:    ret
  %a = load half, ptr %p
  %b = load half, ptr %q
  %r = fadd half %a, %b
  store half %r, ptr %p
  ret void
}

define half @test_fmul_reg(half %a, half %b) nounwind {
; LA32-LABEL: test_fmul_reg:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 8 # 4-byte Folded Spill
; LA32-NEXT:    fst.d $fs0, $sp, 0 # 8-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    move $a0, $a1
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmov.s $fs0, $fa0
; LA32-NEXT:    move $a0, $fp
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmul.s $fa0, $fa0, $fs0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    fld.d $fs0, $sp, 0 # 8-byte Folded Reload
; LA32-NEXT:    ld.w $fp, $sp, 8 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fmul_reg:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -32
; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 16 # 8-byte Folded Spill
; LA64-NEXT:    fst.d $fs0, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    move $a0, $a1
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmov.s $fs0, $fa0
; LA64-NEXT:    move $a0, $fp
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmul.s $fa0, $fa0, $fs0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    fld.d $fs0, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $fp, $sp, 16 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 32
; LA64-NEXT:    ret
  %r = fmul half %a, %b
  ret half %r
}

define void @test_fmul_mem(ptr %p, ptr %q) nounwind {
; LA32-LABEL: test_fmul_mem:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -32
; LA32-NEXT:    st.w $ra, $sp, 28 # 4-byte Folded Spill
; LA32-NEXT:    st.w $fp, $sp, 24 # 4-byte Folded Spill
; LA32-NEXT:    st.w $s0, $sp, 20 # 4-byte Folded Spill
; LA32-NEXT:    fst.d $fs0, $sp, 8 # 8-byte Folded Spill
; LA32-NEXT:    move $fp, $a0
; LA32-NEXT:    ld.hu $s0, $a0, 0
; LA32-NEXT:    ld.hu $a0, $a1, 0
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmov.s $fs0, $fa0
; LA32-NEXT:    move $a0, $s0
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fmul.s $fa0, $fa0, $fs0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    st.h $a0, $fp, 0
; LA32-NEXT:    fld.d $fs0, $sp, 8 # 8-byte Folded Reload
; LA32-NEXT:    ld.w $s0, $sp, 20 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $fp, $sp, 24 # 4-byte Folded Reload
; LA32-NEXT:    ld.w $ra, $sp, 28 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 32
; LA32-NEXT:    ret
;
; LA64-LABEL: test_fmul_mem:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -32
; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
; LA64-NEXT:    st.d $fp, $sp, 16 # 8-byte Folded Spill
; LA64-NEXT:    st.d $s0, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    fst.d $fs0, $sp, 0 # 8-byte Folded Spill
; LA64-NEXT:    move $fp, $a0
; LA64-NEXT:    ld.hu $s0, $a0, 0
; LA64-NEXT:    ld.hu $a0, $a1, 0
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmov.s $fs0, $fa0
; LA64-NEXT:    move $a0, $s0
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fmul.s $fa0, $fa0, $fs0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    st.h $a0, $fp, 0
; LA64-NEXT:    fld.d $fs0, $sp, 0 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $s0, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $fp, $sp, 16 # 8-byte Folded Reload
; LA64-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 32
; LA64-NEXT:    ret
  %a = load half, ptr %p
  %b = load half, ptr %q
  %r = fmul half %a, %b
  store half %r, ptr %p
  ret void
}

define half @freeze_half_undef() nounwind {
; LA32-LABEL: freeze_half_undef:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    movgr2fr.w $fa0, $zero
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fadd.s $fa0, $fa0, $fa0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: freeze_half_undef:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -16
; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    movgr2fr.w $fa0, $zero
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fadd.s $fa0, $fa0, $fa0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 16
; LA64-NEXT:    ret
  %y1 = freeze half undef
  %t1 = fadd half %y1, %y1
  ret half %t1
}

define half @freeze_half_poison(half %maybe.poison) nounwind {
; LA32-LABEL: freeze_half_poison:
; LA32:       # %bb.0:
; LA32-NEXT:    addi.w $sp, $sp, -16
; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA32-NEXT:    fadd.s $fa0, $fa0, $fa0
; LA32-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32-NEXT:    addi.w $sp, $sp, 16
; LA32-NEXT:    ret
;
; LA64-LABEL: freeze_half_poison:
; LA64:       # %bb.0:
; LA64-NEXT:    addi.d $sp, $sp, -16
; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64-NEXT:    bl %plt(__gnu_h2f_ieee)
; LA64-NEXT:    fadd.s $fa0, $fa0, $fa0
; LA64-NEXT:    bl %plt(__gnu_f2h_ieee)
; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64-NEXT:    addi.d $sp, $sp, 16
; LA64-NEXT:    ret
  %y1 = freeze half %maybe.poison
  %t1 = fadd half %y1, %y1
  ret half %t1
}