| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc --mtriple=loongarch32 --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA32S |
| ; RUN: llc --mtriple=loongarch32 --mattr=+f -target-abi=ilp32s --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA32F-ILP32S |
| ; RUN: llc --mtriple=loongarch32 --mattr=+f -target-abi=ilp32d --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA32F-ILP32D |
| ; RUN: llc --mtriple=loongarch32 --mattr=+d -target-abi=ilp32s --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA32D-ILP32S |
| ; RUN: llc --mtriple=loongarch32 --mattr=+d -target-abi=ilp32d --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA32D-ILP32D |
| ; RUN: llc --mtriple=loongarch64 --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA64S |
| ; RUN: llc --mtriple=loongarch64 --mattr=+f -target-abi=lp64s --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA64F-LP64S |
| ; RUN: llc --mtriple=loongarch64 --mattr=+f -target-abi=lp64d --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA64F-LP64D |
| ; RUN: llc --mtriple=loongarch64 --mattr=+d -target-abi=lp64s --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA64D-LP64S |
| ; RUN: llc --mtriple=loongarch64 --mattr=+d -target-abi=lp64d --verify-machineinstrs < %s | FileCheck %s --check-prefix=LA64D-LP64D |
| |
| define half @f(half %a, half %b, half %c) { |
| ; LA32S-LABEL: f: |
| ; LA32S: # %bb.0: |
| ; LA32S-NEXT: addi.w $sp, $sp, -32 |
| ; LA32S-NEXT: .cfi_def_cfa_offset 32 |
| ; LA32S-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill |
| ; LA32S-NEXT: st.w $fp, $sp, 24 # 4-byte Folded Spill |
| ; LA32S-NEXT: st.w $s0, $sp, 20 # 4-byte Folded Spill |
| ; LA32S-NEXT: st.w $s1, $sp, 16 # 4-byte Folded Spill |
| ; LA32S-NEXT: st.w $s2, $sp, 12 # 4-byte Folded Spill |
| ; LA32S-NEXT: .cfi_offset 1, -4 |
| ; LA32S-NEXT: .cfi_offset 22, -8 |
| ; LA32S-NEXT: .cfi_offset 23, -12 |
| ; LA32S-NEXT: .cfi_offset 24, -16 |
| ; LA32S-NEXT: .cfi_offset 25, -20 |
| ; LA32S-NEXT: move $fp, $a2 |
| ; LA32S-NEXT: move $s0, $a1 |
| ; LA32S-NEXT: lu12i.w $a1, 15 |
| ; LA32S-NEXT: ori $s2, $a1, 4095 |
| ; LA32S-NEXT: and $a0, $a0, $s2 |
| ; LA32S-NEXT: bl __extendhfsf2 |
| ; LA32S-NEXT: move $s1, $a0 |
| ; LA32S-NEXT: and $a0, $s0, $s2 |
| ; LA32S-NEXT: bl __extendhfsf2 |
| ; LA32S-NEXT: move $a1, $a0 |
| ; LA32S-NEXT: move $a0, $s1 |
| ; LA32S-NEXT: bl __addsf3 |
| ; LA32S-NEXT: bl __truncsfhf2 |
| ; LA32S-NEXT: move $s0, $a0 |
| ; LA32S-NEXT: and $a0, $fp, $s2 |
| ; LA32S-NEXT: bl __extendhfsf2 |
| ; LA32S-NEXT: move $fp, $a0 |
| ; LA32S-NEXT: and $a0, $s0, $s2 |
| ; LA32S-NEXT: bl __extendhfsf2 |
| ; LA32S-NEXT: move $a1, $fp |
| ; LA32S-NEXT: bl __addsf3 |
| ; LA32S-NEXT: bl __truncsfhf2 |
| ; LA32S-NEXT: ld.w $s2, $sp, 12 # 4-byte Folded Reload |
| ; LA32S-NEXT: ld.w $s1, $sp, 16 # 4-byte Folded Reload |
| ; LA32S-NEXT: ld.w $s0, $sp, 20 # 4-byte Folded Reload |
| ; LA32S-NEXT: ld.w $fp, $sp, 24 # 4-byte Folded Reload |
| ; LA32S-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload |
| ; LA32S-NEXT: addi.w $sp, $sp, 32 |
| ; LA32S-NEXT: ret |
| ; |
| ; LA32F-ILP32S-LABEL: f: |
| ; LA32F-ILP32S: # %bb.0: |
| ; LA32F-ILP32S-NEXT: addi.w $sp, $sp, -16 |
| ; LA32F-ILP32S-NEXT: .cfi_def_cfa_offset 16 |
| ; LA32F-ILP32S-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill |
| ; LA32F-ILP32S-NEXT: st.w $fp, $sp, 8 # 4-byte Folded Spill |
| ; LA32F-ILP32S-NEXT: st.w $s0, $sp, 4 # 4-byte Folded Spill |
| ; LA32F-ILP32S-NEXT: .cfi_offset 1, -4 |
| ; LA32F-ILP32S-NEXT: .cfi_offset 22, -8 |
| ; LA32F-ILP32S-NEXT: .cfi_offset 23, -12 |
| ; LA32F-ILP32S-NEXT: move $fp, $a2 |
| ; LA32F-ILP32S-NEXT: move $s0, $a0 |
| ; LA32F-ILP32S-NEXT: move $a0, $a1 |
| ; LA32F-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32F-ILP32S-NEXT: fst.s $fa0, $sp, 0 # 4-byte Folded Spill |
| ; LA32F-ILP32S-NEXT: move $a0, $s0 |
| ; LA32F-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32F-ILP32S-NEXT: fld.s $fa1, $sp, 0 # 4-byte Folded Reload |
| ; LA32F-ILP32S-NEXT: fadd.s $fa0, $fa0, $fa1 |
| ; LA32F-ILP32S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32F-ILP32S-NEXT: bl __truncsfhf2 |
| ; LA32F-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32F-ILP32S-NEXT: fst.s $fa0, $sp, 0 # 4-byte Folded Spill |
| ; LA32F-ILP32S-NEXT: move $a0, $fp |
| ; LA32F-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32F-ILP32S-NEXT: fld.s $fa1, $sp, 0 # 4-byte Folded Reload |
| ; LA32F-ILP32S-NEXT: fadd.s $fa0, $fa1, $fa0 |
| ; LA32F-ILP32S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32F-ILP32S-NEXT: bl __truncsfhf2 |
| ; LA32F-ILP32S-NEXT: lu12i.w $a1, -16 |
| ; LA32F-ILP32S-NEXT: or $a0, $a0, $a1 |
| ; LA32F-ILP32S-NEXT: ld.w $s0, $sp, 4 # 4-byte Folded Reload |
| ; LA32F-ILP32S-NEXT: ld.w $fp, $sp, 8 # 4-byte Folded Reload |
| ; LA32F-ILP32S-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload |
| ; LA32F-ILP32S-NEXT: addi.w $sp, $sp, 16 |
| ; LA32F-ILP32S-NEXT: ret |
| ; |
| ; LA32F-ILP32D-LABEL: f: |
| ; LA32F-ILP32D: # %bb.0: |
| ; LA32F-ILP32D-NEXT: addi.w $sp, $sp, -16 |
| ; LA32F-ILP32D-NEXT: .cfi_def_cfa_offset 16 |
| ; LA32F-ILP32D-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill |
| ; LA32F-ILP32D-NEXT: fst.s $fs0, $sp, 8 # 4-byte Folded Spill |
| ; LA32F-ILP32D-NEXT: fst.s $fs1, $sp, 4 # 4-byte Folded Spill |
| ; LA32F-ILP32D-NEXT: fst.s $fs2, $sp, 0 # 4-byte Folded Spill |
| ; LA32F-ILP32D-NEXT: .cfi_offset 1, -4 |
| ; LA32F-ILP32D-NEXT: .cfi_offset 56, -8 |
| ; LA32F-ILP32D-NEXT: .cfi_offset 57, -12 |
| ; LA32F-ILP32D-NEXT: .cfi_offset 58, -16 |
| ; LA32F-ILP32D-NEXT: fmov.s $fs0, $fa2 |
| ; LA32F-ILP32D-NEXT: fmov.s $fs1, $fa0 |
| ; LA32F-ILP32D-NEXT: fmov.s $fa0, $fa1 |
| ; LA32F-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32D-NEXT: fmov.s $fs2, $fa0 |
| ; LA32F-ILP32D-NEXT: fmov.s $fa0, $fs1 |
| ; LA32F-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32D-NEXT: fadd.s $fa0, $fa0, $fs2 |
| ; LA32F-ILP32D-NEXT: bl __truncsfhf2 |
| ; LA32F-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32D-NEXT: fmov.s $fs1, $fa0 |
| ; LA32F-ILP32D-NEXT: fmov.s $fa0, $fs0 |
| ; LA32F-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32F-ILP32D-NEXT: fadd.s $fa0, $fs1, $fa0 |
| ; LA32F-ILP32D-NEXT: bl __truncsfhf2 |
| ; LA32F-ILP32D-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32F-ILP32D-NEXT: lu12i.w $a1, -16 |
| ; LA32F-ILP32D-NEXT: or $a0, $a0, $a1 |
| ; LA32F-ILP32D-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32F-ILP32D-NEXT: fld.s $fs2, $sp, 0 # 4-byte Folded Reload |
| ; LA32F-ILP32D-NEXT: fld.s $fs1, $sp, 4 # 4-byte Folded Reload |
| ; LA32F-ILP32D-NEXT: fld.s $fs0, $sp, 8 # 4-byte Folded Reload |
| ; LA32F-ILP32D-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload |
| ; LA32F-ILP32D-NEXT: addi.w $sp, $sp, 16 |
| ; LA32F-ILP32D-NEXT: ret |
| ; |
| ; LA32D-ILP32S-LABEL: f: |
| ; LA32D-ILP32S: # %bb.0: |
| ; LA32D-ILP32S-NEXT: addi.w $sp, $sp, -16 |
| ; LA32D-ILP32S-NEXT: .cfi_def_cfa_offset 16 |
| ; LA32D-ILP32S-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill |
| ; LA32D-ILP32S-NEXT: st.w $fp, $sp, 8 # 4-byte Folded Spill |
| ; LA32D-ILP32S-NEXT: st.w $s0, $sp, 4 # 4-byte Folded Spill |
| ; LA32D-ILP32S-NEXT: .cfi_offset 1, -4 |
| ; LA32D-ILP32S-NEXT: .cfi_offset 22, -8 |
| ; LA32D-ILP32S-NEXT: .cfi_offset 23, -12 |
| ; LA32D-ILP32S-NEXT: move $fp, $a2 |
| ; LA32D-ILP32S-NEXT: move $s0, $a0 |
| ; LA32D-ILP32S-NEXT: move $a0, $a1 |
| ; LA32D-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32D-ILP32S-NEXT: fst.s $fa0, $sp, 0 # 4-byte Folded Spill |
| ; LA32D-ILP32S-NEXT: move $a0, $s0 |
| ; LA32D-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32D-ILP32S-NEXT: fld.s $fa1, $sp, 0 # 4-byte Folded Reload |
| ; LA32D-ILP32S-NEXT: fadd.s $fa0, $fa0, $fa1 |
| ; LA32D-ILP32S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32D-ILP32S-NEXT: bl __truncsfhf2 |
| ; LA32D-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32D-ILP32S-NEXT: fst.s $fa0, $sp, 0 # 4-byte Folded Spill |
| ; LA32D-ILP32S-NEXT: move $a0, $fp |
| ; LA32D-ILP32S-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32D-ILP32S-NEXT: fld.s $fa1, $sp, 0 # 4-byte Folded Reload |
| ; LA32D-ILP32S-NEXT: fadd.s $fa0, $fa1, $fa0 |
| ; LA32D-ILP32S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32D-ILP32S-NEXT: bl __truncsfhf2 |
| ; LA32D-ILP32S-NEXT: lu12i.w $a1, -16 |
| ; LA32D-ILP32S-NEXT: or $a0, $a0, $a1 |
| ; LA32D-ILP32S-NEXT: ld.w $s0, $sp, 4 # 4-byte Folded Reload |
| ; LA32D-ILP32S-NEXT: ld.w $fp, $sp, 8 # 4-byte Folded Reload |
| ; LA32D-ILP32S-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload |
| ; LA32D-ILP32S-NEXT: addi.w $sp, $sp, 16 |
| ; LA32D-ILP32S-NEXT: ret |
| ; |
| ; LA32D-ILP32D-LABEL: f: |
| ; LA32D-ILP32D: # %bb.0: |
| ; LA32D-ILP32D-NEXT: addi.w $sp, $sp, -32 |
| ; LA32D-ILP32D-NEXT: .cfi_def_cfa_offset 32 |
| ; LA32D-ILP32D-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill |
| ; LA32D-ILP32D-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill |
| ; LA32D-ILP32D-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill |
| ; LA32D-ILP32D-NEXT: fst.d $fs2, $sp, 0 # 8-byte Folded Spill |
| ; LA32D-ILP32D-NEXT: .cfi_offset 1, -4 |
| ; LA32D-ILP32D-NEXT: .cfi_offset 56, -16 |
| ; LA32D-ILP32D-NEXT: .cfi_offset 57, -24 |
| ; LA32D-ILP32D-NEXT: .cfi_offset 58, -32 |
| ; LA32D-ILP32D-NEXT: fmov.s $fs0, $fa2 |
| ; LA32D-ILP32D-NEXT: fmov.s $fs1, $fa0 |
| ; LA32D-ILP32D-NEXT: fmov.s $fa0, $fa1 |
| ; LA32D-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32D-NEXT: fmov.s $fs2, $fa0 |
| ; LA32D-ILP32D-NEXT: fmov.s $fa0, $fs1 |
| ; LA32D-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32D-NEXT: fadd.s $fa0, $fa0, $fs2 |
| ; LA32D-ILP32D-NEXT: bl __truncsfhf2 |
| ; LA32D-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32D-NEXT: fmov.s $fs1, $fa0 |
| ; LA32D-ILP32D-NEXT: fmov.s $fa0, $fs0 |
| ; LA32D-ILP32D-NEXT: bl __extendhfsf2 |
| ; LA32D-ILP32D-NEXT: fadd.s $fa0, $fs1, $fa0 |
| ; LA32D-ILP32D-NEXT: bl __truncsfhf2 |
| ; LA32D-ILP32D-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA32D-ILP32D-NEXT: lu12i.w $a1, -16 |
| ; LA32D-ILP32D-NEXT: or $a0, $a0, $a1 |
| ; LA32D-ILP32D-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA32D-ILP32D-NEXT: fld.d $fs2, $sp, 0 # 8-byte Folded Reload |
| ; LA32D-ILP32D-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload |
| ; LA32D-ILP32D-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload |
| ; LA32D-ILP32D-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload |
| ; LA32D-ILP32D-NEXT: addi.w $sp, $sp, 32 |
| ; LA32D-ILP32D-NEXT: ret |
| ; |
| ; LA64S-LABEL: f: |
| ; LA64S: # %bb.0: |
| ; LA64S-NEXT: addi.d $sp, $sp, -32 |
| ; LA64S-NEXT: .cfi_def_cfa_offset 32 |
| ; LA64S-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64S-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill |
| ; LA64S-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill |
| ; LA64S-NEXT: fst.d $fs2, $sp, 0 # 8-byte Folded Spill |
| ; LA64S-NEXT: .cfi_offset 1, -8 |
| ; LA64S-NEXT: .cfi_offset 56, -16 |
| ; LA64S-NEXT: .cfi_offset 57, -24 |
| ; LA64S-NEXT: .cfi_offset 58, -32 |
| ; LA64S-NEXT: fmov.s $fs0, $fa2 |
| ; LA64S-NEXT: fmov.s $fs1, $fa0 |
| ; LA64S-NEXT: fmov.s $fa0, $fa1 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: fmov.s $fs2, $fa0 |
| ; LA64S-NEXT: fmov.s $fa0, $fs1 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: fadd.s $fa0, $fa0, $fs2 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: fmov.s $fs1, $fa0 |
| ; LA64S-NEXT: fmov.s $fa0, $fs0 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: fadd.s $fa0, $fs1, $fa0 |
| ; LA64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64S-NEXT: lu12i.w $a1, -16 |
| ; LA64S-NEXT: or $a0, $a0, $a1 |
| ; LA64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64S-NEXT: fld.d $fs2, $sp, 0 # 8-byte Folded Reload |
| ; LA64S-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload |
| ; LA64S-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload |
| ; LA64S-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64S-NEXT: addi.d $sp, $sp, 32 |
| ; LA64S-NEXT: ret |
| ; |
| ; LA64F-LP64S-LABEL: f: |
| ; LA64F-LP64S: # %bb.0: |
| ; LA64F-LP64S-NEXT: addi.d $sp, $sp, -32 |
| ; LA64F-LP64S-NEXT: .cfi_def_cfa_offset 32 |
| ; LA64F-LP64S-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64F-LP64S-NEXT: st.d $fp, $sp, 16 # 8-byte Folded Spill |
| ; LA64F-LP64S-NEXT: st.d $s0, $sp, 8 # 8-byte Folded Spill |
| ; LA64F-LP64S-NEXT: .cfi_offset 1, -8 |
| ; LA64F-LP64S-NEXT: .cfi_offset 22, -16 |
| ; LA64F-LP64S-NEXT: .cfi_offset 23, -24 |
| ; LA64F-LP64S-NEXT: move $fp, $a2 |
| ; LA64F-LP64S-NEXT: move $s0, $a0 |
| ; LA64F-LP64S-NEXT: move $a0, $a1 |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64F-LP64S-NEXT: fst.s $fa0, $sp, 4 # 4-byte Folded Spill |
| ; LA64F-LP64S-NEXT: move $a0, $s0 |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64F-LP64S-NEXT: fld.s $fa1, $sp, 4 # 4-byte Folded Reload |
| ; LA64F-LP64S-NEXT: fadd.s $fa0, $fa0, $fa1 |
| ; LA64F-LP64S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64F-LP64S-NEXT: fst.s $fa0, $sp, 4 # 4-byte Folded Spill |
| ; LA64F-LP64S-NEXT: move $a0, $fp |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64F-LP64S-NEXT: fld.s $fa1, $sp, 4 # 4-byte Folded Reload |
| ; LA64F-LP64S-NEXT: fadd.s $fa0, $fa1, $fa0 |
| ; LA64F-LP64S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64F-LP64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64F-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64S-NEXT: lu12i.w $a1, -16 |
| ; LA64F-LP64S-NEXT: or $a0, $a0, $a1 |
| ; LA64F-LP64S-NEXT: ld.d $s0, $sp, 8 # 8-byte Folded Reload |
| ; LA64F-LP64S-NEXT: ld.d $fp, $sp, 16 # 8-byte Folded Reload |
| ; LA64F-LP64S-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64F-LP64S-NEXT: addi.d $sp, $sp, 32 |
| ; LA64F-LP64S-NEXT: ret |
| ; |
| ; LA64F-LP64D-LABEL: f: |
| ; LA64F-LP64D: # %bb.0: |
| ; LA64F-LP64D-NEXT: addi.d $sp, $sp, -32 |
| ; LA64F-LP64D-NEXT: .cfi_def_cfa_offset 32 |
| ; LA64F-LP64D-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64F-LP64D-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill |
| ; LA64F-LP64D-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill |
| ; LA64F-LP64D-NEXT: fst.d $fs2, $sp, 0 # 8-byte Folded Spill |
| ; LA64F-LP64D-NEXT: .cfi_offset 1, -8 |
| ; LA64F-LP64D-NEXT: .cfi_offset 56, -16 |
| ; LA64F-LP64D-NEXT: .cfi_offset 57, -24 |
| ; LA64F-LP64D-NEXT: .cfi_offset 58, -32 |
| ; LA64F-LP64D-NEXT: fmov.s $fs0, $fa2 |
| ; LA64F-LP64D-NEXT: fmov.s $fs1, $fa0 |
| ; LA64F-LP64D-NEXT: fmov.s $fa0, $fa1 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: fmov.s $fs2, $fa0 |
| ; LA64F-LP64D-NEXT: fmov.s $fa0, $fs1 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: fadd.s $fa0, $fa0, $fs2 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: fmov.s $fs1, $fa0 |
| ; LA64F-LP64D-NEXT: fmov.s $fa0, $fs0 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: fadd.s $fa0, $fs1, $fa0 |
| ; LA64F-LP64D-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64F-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64F-LP64D-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64F-LP64D-NEXT: lu12i.w $a1, -16 |
| ; LA64F-LP64D-NEXT: or $a0, $a0, $a1 |
| ; LA64F-LP64D-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64F-LP64D-NEXT: fld.d $fs2, $sp, 0 # 8-byte Folded Reload |
| ; LA64F-LP64D-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload |
| ; LA64F-LP64D-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload |
| ; LA64F-LP64D-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64F-LP64D-NEXT: addi.d $sp, $sp, 32 |
| ; LA64F-LP64D-NEXT: ret |
| ; |
| ; LA64D-LP64S-LABEL: f: |
| ; LA64D-LP64S: # %bb.0: |
| ; LA64D-LP64S-NEXT: addi.d $sp, $sp, -32 |
| ; LA64D-LP64S-NEXT: .cfi_def_cfa_offset 32 |
| ; LA64D-LP64S-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64D-LP64S-NEXT: st.d $fp, $sp, 16 # 8-byte Folded Spill |
| ; LA64D-LP64S-NEXT: st.d $s0, $sp, 8 # 8-byte Folded Spill |
| ; LA64D-LP64S-NEXT: .cfi_offset 1, -8 |
| ; LA64D-LP64S-NEXT: .cfi_offset 22, -16 |
| ; LA64D-LP64S-NEXT: .cfi_offset 23, -24 |
| ; LA64D-LP64S-NEXT: move $fp, $a2 |
| ; LA64D-LP64S-NEXT: move $s0, $a0 |
| ; LA64D-LP64S-NEXT: move $a0, $a1 |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64D-LP64S-NEXT: fst.s $fa0, $sp, 4 # 4-byte Folded Spill |
| ; LA64D-LP64S-NEXT: move $a0, $s0 |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64D-LP64S-NEXT: fld.s $fa1, $sp, 4 # 4-byte Folded Reload |
| ; LA64D-LP64S-NEXT: fadd.s $fa0, $fa0, $fa1 |
| ; LA64D-LP64S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64D-LP64S-NEXT: fst.s $fa0, $sp, 4 # 4-byte Folded Spill |
| ; LA64D-LP64S-NEXT: move $a0, $fp |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64D-LP64S-NEXT: fld.s $fa1, $sp, 4 # 4-byte Folded Reload |
| ; LA64D-LP64S-NEXT: fadd.s $fa0, $fa1, $fa0 |
| ; LA64D-LP64S-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64D-LP64S-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64D-LP64S-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64S-NEXT: lu12i.w $a1, -16 |
| ; LA64D-LP64S-NEXT: or $a0, $a0, $a1 |
| ; LA64D-LP64S-NEXT: ld.d $s0, $sp, 8 # 8-byte Folded Reload |
| ; LA64D-LP64S-NEXT: ld.d $fp, $sp, 16 # 8-byte Folded Reload |
| ; LA64D-LP64S-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64D-LP64S-NEXT: addi.d $sp, $sp, 32 |
| ; LA64D-LP64S-NEXT: ret |
| ; |
| ; LA64D-LP64D-LABEL: f: |
| ; LA64D-LP64D: # %bb.0: |
| ; LA64D-LP64D-NEXT: addi.d $sp, $sp, -32 |
| ; LA64D-LP64D-NEXT: .cfi_def_cfa_offset 32 |
| ; LA64D-LP64D-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64D-LP64D-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill |
| ; LA64D-LP64D-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill |
| ; LA64D-LP64D-NEXT: fst.d $fs2, $sp, 0 # 8-byte Folded Spill |
| ; LA64D-LP64D-NEXT: .cfi_offset 1, -8 |
| ; LA64D-LP64D-NEXT: .cfi_offset 56, -16 |
| ; LA64D-LP64D-NEXT: .cfi_offset 57, -24 |
| ; LA64D-LP64D-NEXT: .cfi_offset 58, -32 |
| ; LA64D-LP64D-NEXT: fmov.s $fs0, $fa2 |
| ; LA64D-LP64D-NEXT: fmov.s $fs1, $fa0 |
| ; LA64D-LP64D-NEXT: fmov.s $fa0, $fa1 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: fmov.s $fs2, $fa0 |
| ; LA64D-LP64D-NEXT: fmov.s $fa0, $fs1 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: fadd.s $fa0, $fa0, $fs2 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: fmov.s $fs1, $fa0 |
| ; LA64D-LP64D-NEXT: fmov.s $fa0, $fs0 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__extendhfsf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: fadd.s $fa0, $fs1, $fa0 |
| ; LA64D-LP64D-NEXT: pcaddu18i $ra, %call36(__truncsfhf2) |
| ; LA64D-LP64D-NEXT: jirl $ra, $ra, 0 |
| ; LA64D-LP64D-NEXT: movfr2gr.s $a0, $fa0 |
| ; LA64D-LP64D-NEXT: lu12i.w $a1, -16 |
| ; LA64D-LP64D-NEXT: or $a0, $a0, $a1 |
| ; LA64D-LP64D-NEXT: movgr2fr.w $fa0, $a0 |
| ; LA64D-LP64D-NEXT: fld.d $fs2, $sp, 0 # 8-byte Folded Reload |
| ; LA64D-LP64D-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload |
| ; LA64D-LP64D-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload |
| ; LA64D-LP64D-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64D-LP64D-NEXT: addi.d $sp, $sp, 32 |
| ; LA64D-LP64D-NEXT: ret |
| %d = fadd half %a, %b |
| %e = fadd half %d, %c |
| ret half %e |
| } |
