| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc --mtriple=loongarch32 --mattr=+f,-d < %s | FileCheck %s --check-prefix=LA32F |
| ; RUN: llc --mtriple=loongarch32 --mattr=+d < %s | FileCheck %s --check-prefix=LA32D |
| ; RUN: llc --mtriple=loongarch64 --mattr=+f,-d < %s | FileCheck %s --check-prefix=LA64F |
| ; RUN: llc --mtriple=loongarch64 --mattr=+d < %s | FileCheck %s --check-prefix=LA64D |
| |
| ;; TODO: Merge the offset of address calculation into the offset field of instructions. |
| |
| %f2 = type <2 x float> |
| %f4 = type <4 x float> |
| %f8 = type <8 x float> |
| %d2 = type <2 x double> |
| %d4 = type <4 x double> |
| %d8 = type <8 x double> |
| |
| define void @test_zero(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_zero: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: fld.s $fa0, $a0, 12 |
| ; LA32F-NEXT: fld.s $fa1, $a0, 0 |
| ; LA32F-NEXT: fld.s $fa2, $a0, 4 |
| ; LA32F-NEXT: fld.s $fa3, $a0, 8 |
| ; LA32F-NEXT: movgr2fr.w $fa4, $zero |
| ; LA32F-NEXT: fadd.s $fa1, $fa1, $fa4 |
| ; LA32F-NEXT: fadd.s $fa2, $fa2, $fa4 |
| ; LA32F-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA32F-NEXT: fadd.s $fa0, $fa0, $fa4 |
| ; LA32F-NEXT: fst.s $fa0, $a1, 12 |
| ; LA32F-NEXT: fst.s $fa3, $a1, 8 |
| ; LA32F-NEXT: fst.s $fa2, $a1, 4 |
| ; LA32F-NEXT: fst.s $fa1, $a1, 0 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_zero: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: fld.s $fa0, $a0, 12 |
| ; LA32D-NEXT: fld.s $fa1, $a0, 0 |
| ; LA32D-NEXT: fld.s $fa2, $a0, 4 |
| ; LA32D-NEXT: fld.s $fa3, $a0, 8 |
| ; LA32D-NEXT: movgr2fr.w $fa4, $zero |
| ; LA32D-NEXT: fadd.s $fa1, $fa1, $fa4 |
| ; LA32D-NEXT: fadd.s $fa2, $fa2, $fa4 |
| ; LA32D-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA32D-NEXT: fadd.s $fa0, $fa0, $fa4 |
| ; LA32D-NEXT: fst.s $fa0, $a1, 12 |
| ; LA32D-NEXT: fst.s $fa3, $a1, 8 |
| ; LA32D-NEXT: fst.s $fa2, $a1, 4 |
| ; LA32D-NEXT: fst.s $fa1, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_zero: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: fld.s $fa0, $a0, 12 |
| ; LA64F-NEXT: fld.s $fa1, $a0, 0 |
| ; LA64F-NEXT: fld.s $fa2, $a0, 4 |
| ; LA64F-NEXT: fld.s $fa3, $a0, 8 |
| ; LA64F-NEXT: movgr2fr.w $fa4, $zero |
| ; LA64F-NEXT: fadd.s $fa1, $fa1, $fa4 |
| ; LA64F-NEXT: fadd.s $fa2, $fa2, $fa4 |
| ; LA64F-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA64F-NEXT: fadd.s $fa0, $fa0, $fa4 |
| ; LA64F-NEXT: fst.s $fa0, $a1, 12 |
| ; LA64F-NEXT: fst.s $fa3, $a1, 8 |
| ; LA64F-NEXT: fst.s $fa2, $a1, 4 |
| ; LA64F-NEXT: fst.s $fa1, $a1, 0 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_zero: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: vld $vr0, $a0, 0 |
| ; LA64D-NEXT: vrepli.b $vr1, 0 |
| ; LA64D-NEXT: vfadd.s $vr0, $vr0, $vr1 |
| ; LA64D-NEXT: vst $vr0, $a1, 0 |
| ; LA64D-NEXT: ret |
| %p = load %f4, ptr %P |
| %R = fadd %f4 %p, zeroinitializer |
| store %f4 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_f2(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_f2: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: fld.s $fa0, $a0, 4 |
| ; LA32F-NEXT: fld.s $fa1, $a0, 0 |
| ; LA32F-NEXT: addi.w $a0, $zero, 1 |
| ; LA32F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI1_0) |
| ; LA32F-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI1_0) |
| ; LA32F-NEXT: movgr2fr.w $fa3, $a0 |
| ; LA32F-NEXT: ffint.s.w $fa3, $fa3 |
| ; LA32F-NEXT: fadd.s $fa1, $fa1, $fa3 |
| ; LA32F-NEXT: fadd.s $fa0, $fa0, $fa2 |
| ; LA32F-NEXT: fst.s $fa0, $a1, 4 |
| ; LA32F-NEXT: fst.s $fa1, $a1, 0 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_f2: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: fld.s $fa0, $a0, 4 |
| ; LA32D-NEXT: fld.s $fa1, $a0, 0 |
| ; LA32D-NEXT: addi.w $a0, $zero, 1 |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI1_0) |
| ; LA32D-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI1_0) |
| ; LA32D-NEXT: movgr2fr.w $fa3, $a0 |
| ; LA32D-NEXT: ffint.s.w $fa3, $fa3 |
| ; LA32D-NEXT: fadd.s $fa1, $fa1, $fa3 |
| ; LA32D-NEXT: fadd.s $fa0, $fa0, $fa2 |
| ; LA32D-NEXT: fst.s $fa0, $a1, 4 |
| ; LA32D-NEXT: fst.s $fa1, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_f2: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: fld.s $fa0, $a0, 4 |
| ; LA64F-NEXT: fld.s $fa1, $a0, 0 |
| ; LA64F-NEXT: addi.w $a0, $zero, 1 |
| ; LA64F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI1_0) |
| ; LA64F-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI1_0) |
| ; LA64F-NEXT: movgr2fr.w $fa3, $a0 |
| ; LA64F-NEXT: ffint.s.w $fa3, $fa3 |
| ; LA64F-NEXT: fadd.s $fa1, $fa1, $fa3 |
| ; LA64F-NEXT: fadd.s $fa0, $fa0, $fa2 |
| ; LA64F-NEXT: fst.s $fa0, $a1, 4 |
| ; LA64F-NEXT: fst.s $fa1, $a1, 0 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_f2: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: ld.d $a0, $a0, 0 |
| ; LA64D-NEXT: vinsgr2vr.d $vr0, $a0, 0 |
| ; LA64D-NEXT: lu12i.w $a0, 260096 |
| ; LA64D-NEXT: lu52i.d $a0, $a0, 1024 |
| ; LA64D-NEXT: vreplgr2vr.d $vr1, $a0 |
| ; LA64D-NEXT: vfadd.s $vr0, $vr0, $vr1 |
| ; LA64D-NEXT: vpickve2gr.d $a0, $vr0, 0 |
| ; LA64D-NEXT: st.d $a0, $a1, 0 |
| ; LA64D-NEXT: ret |
| %p = load %f2, ptr %P |
| %R = fadd %f2 %p, < float 1.000000e+00, float 2.000000e+00 > |
| store %f2 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_f4(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_f4: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: fld.s $fa0, $a0, 12 |
| ; LA32F-NEXT: fld.s $fa1, $a0, 8 |
| ; LA32F-NEXT: fld.s $fa2, $a0, 4 |
| ; LA32F-NEXT: fld.s $fa3, $a0, 0 |
| ; LA32F-NEXT: addi.w $a0, $zero, 1 |
| ; LA32F-NEXT: movgr2fr.w $fa4, $a0 |
| ; LA32F-NEXT: ffint.s.w $fa4, $fa4 |
| ; LA32F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0) |
| ; LA32F-NEXT: fld.s $fa5, $a0, %pc_lo12(.LCPI2_0) |
| ; LA32F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_1) |
| ; LA32F-NEXT: fld.s $fa6, $a0, %pc_lo12(.LCPI2_1) |
| ; LA32F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_2) |
| ; LA32F-NEXT: fld.s $fa7, $a0, %pc_lo12(.LCPI2_2) |
| ; LA32F-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA32F-NEXT: fadd.s $fa2, $fa2, $fa5 |
| ; LA32F-NEXT: fadd.s $fa1, $fa1, $fa6 |
| ; LA32F-NEXT: fadd.s $fa0, $fa0, $fa7 |
| ; LA32F-NEXT: fst.s $fa0, $a1, 12 |
| ; LA32F-NEXT: fst.s $fa1, $a1, 8 |
| ; LA32F-NEXT: fst.s $fa2, $a1, 4 |
| ; LA32F-NEXT: fst.s $fa3, $a1, 0 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_f4: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: fld.s $fa0, $a0, 12 |
| ; LA32D-NEXT: fld.s $fa1, $a0, 8 |
| ; LA32D-NEXT: fld.s $fa2, $a0, 4 |
| ; LA32D-NEXT: fld.s $fa3, $a0, 0 |
| ; LA32D-NEXT: addi.w $a0, $zero, 1 |
| ; LA32D-NEXT: movgr2fr.w $fa4, $a0 |
| ; LA32D-NEXT: ffint.s.w $fa4, $fa4 |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0) |
| ; LA32D-NEXT: fld.s $fa5, $a0, %pc_lo12(.LCPI2_0) |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_1) |
| ; LA32D-NEXT: fld.s $fa6, $a0, %pc_lo12(.LCPI2_1) |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_2) |
| ; LA32D-NEXT: fld.s $fa7, $a0, %pc_lo12(.LCPI2_2) |
| ; LA32D-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA32D-NEXT: fadd.s $fa2, $fa2, $fa5 |
| ; LA32D-NEXT: fadd.s $fa1, $fa1, $fa6 |
| ; LA32D-NEXT: fadd.s $fa0, $fa0, $fa7 |
| ; LA32D-NEXT: fst.s $fa0, $a1, 12 |
| ; LA32D-NEXT: fst.s $fa1, $a1, 8 |
| ; LA32D-NEXT: fst.s $fa2, $a1, 4 |
| ; LA32D-NEXT: fst.s $fa3, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_f4: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: fld.s $fa0, $a0, 12 |
| ; LA64F-NEXT: fld.s $fa1, $a0, 8 |
| ; LA64F-NEXT: fld.s $fa2, $a0, 4 |
| ; LA64F-NEXT: fld.s $fa3, $a0, 0 |
| ; LA64F-NEXT: addi.w $a0, $zero, 1 |
| ; LA64F-NEXT: movgr2fr.w $fa4, $a0 |
| ; LA64F-NEXT: ffint.s.w $fa4, $fa4 |
| ; LA64F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0) |
| ; LA64F-NEXT: fld.s $fa5, $a0, %pc_lo12(.LCPI2_0) |
| ; LA64F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_1) |
| ; LA64F-NEXT: fld.s $fa6, $a0, %pc_lo12(.LCPI2_1) |
| ; LA64F-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_2) |
| ; LA64F-NEXT: fld.s $fa7, $a0, %pc_lo12(.LCPI2_2) |
| ; LA64F-NEXT: fadd.s $fa3, $fa3, $fa4 |
| ; LA64F-NEXT: fadd.s $fa2, $fa2, $fa5 |
| ; LA64F-NEXT: fadd.s $fa1, $fa1, $fa6 |
| ; LA64F-NEXT: fadd.s $fa0, $fa0, $fa7 |
| ; LA64F-NEXT: fst.s $fa0, $a1, 12 |
| ; LA64F-NEXT: fst.s $fa1, $a1, 8 |
| ; LA64F-NEXT: fst.s $fa2, $a1, 4 |
| ; LA64F-NEXT: fst.s $fa3, $a1, 0 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_f4: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: vld $vr0, $a0, 0 |
| ; LA64D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0) |
| ; LA64D-NEXT: vld $vr1, $a0, %pc_lo12(.LCPI2_0) |
| ; LA64D-NEXT: vfadd.s $vr0, $vr0, $vr1 |
| ; LA64D-NEXT: vst $vr0, $a1, 0 |
| ; LA64D-NEXT: ret |
| %p = load %f4, ptr %P |
| %R = fadd %f4 %p, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 > |
| store %f4 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_f8(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_f8: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: addi.w $a2, $zero, 1 |
| ; LA32F-NEXT: movgr2fr.w $fa0, $a2 |
| ; LA32F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_0) |
| ; LA32F-NEXT: fld.s $fa1, $a2, %pc_lo12(.LCPI3_0) |
| ; LA32F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_1) |
| ; LA32F-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI3_1) |
| ; LA32F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_2) |
| ; LA32F-NEXT: fld.s $fa3, $a2, %pc_lo12(.LCPI3_2) |
| ; LA32F-NEXT: fld.s $fa4, $a0, 28 |
| ; LA32F-NEXT: fld.s $fa5, $a0, 24 |
| ; LA32F-NEXT: fld.s $fa6, $a0, 12 |
| ; LA32F-NEXT: fld.s $fa7, $a0, 8 |
| ; LA32F-NEXT: fld.s $ft0, $a0, 0 |
| ; LA32F-NEXT: fld.s $ft1, $a0, 16 |
| ; LA32F-NEXT: fld.s $ft2, $a0, 4 |
| ; LA32F-NEXT: ffint.s.w $fa0, $fa0 |
| ; LA32F-NEXT: fadd.s $ft0, $ft0, $fa0 |
| ; LA32F-NEXT: fadd.s $fa0, $ft1, $fa0 |
| ; LA32F-NEXT: fld.s $ft1, $a0, 20 |
| ; LA32F-NEXT: fadd.s $ft2, $ft2, $fa1 |
| ; LA32F-NEXT: fadd.s $fa7, $fa7, $fa2 |
| ; LA32F-NEXT: fadd.s $fa6, $fa6, $fa3 |
| ; LA32F-NEXT: fadd.s $fa1, $ft1, $fa1 |
| ; LA32F-NEXT: fadd.s $fa2, $fa5, $fa2 |
| ; LA32F-NEXT: fadd.s $fa3, $fa4, $fa3 |
| ; LA32F-NEXT: fst.s $fa3, $a1, 28 |
| ; LA32F-NEXT: fst.s $fa2, $a1, 24 |
| ; LA32F-NEXT: fst.s $fa1, $a1, 20 |
| ; LA32F-NEXT: fst.s $fa6, $a1, 12 |
| ; LA32F-NEXT: fst.s $fa7, $a1, 8 |
| ; LA32F-NEXT: fst.s $ft2, $a1, 4 |
| ; LA32F-NEXT: fst.s $fa0, $a1, 16 |
| ; LA32F-NEXT: fst.s $ft0, $a1, 0 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_f8: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: addi.w $a2, $zero, 1 |
| ; LA32D-NEXT: movgr2fr.w $fa0, $a2 |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_0) |
| ; LA32D-NEXT: fld.s $fa1, $a2, %pc_lo12(.LCPI3_0) |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_1) |
| ; LA32D-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI3_1) |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_2) |
| ; LA32D-NEXT: fld.s $fa3, $a2, %pc_lo12(.LCPI3_2) |
| ; LA32D-NEXT: fld.s $fa4, $a0, 28 |
| ; LA32D-NEXT: fld.s $fa5, $a0, 24 |
| ; LA32D-NEXT: fld.s $fa6, $a0, 12 |
| ; LA32D-NEXT: fld.s $fa7, $a0, 8 |
| ; LA32D-NEXT: fld.s $ft0, $a0, 0 |
| ; LA32D-NEXT: fld.s $ft1, $a0, 16 |
| ; LA32D-NEXT: fld.s $ft2, $a0, 4 |
| ; LA32D-NEXT: ffint.s.w $fa0, $fa0 |
| ; LA32D-NEXT: fadd.s $ft0, $ft0, $fa0 |
| ; LA32D-NEXT: fadd.s $fa0, $ft1, $fa0 |
| ; LA32D-NEXT: fld.s $ft1, $a0, 20 |
| ; LA32D-NEXT: fadd.s $ft2, $ft2, $fa1 |
| ; LA32D-NEXT: fadd.s $fa7, $fa7, $fa2 |
| ; LA32D-NEXT: fadd.s $fa6, $fa6, $fa3 |
| ; LA32D-NEXT: fadd.s $fa1, $ft1, $fa1 |
| ; LA32D-NEXT: fadd.s $fa2, $fa5, $fa2 |
| ; LA32D-NEXT: fadd.s $fa3, $fa4, $fa3 |
| ; LA32D-NEXT: fst.s $fa3, $a1, 28 |
| ; LA32D-NEXT: fst.s $fa2, $a1, 24 |
| ; LA32D-NEXT: fst.s $fa1, $a1, 20 |
| ; LA32D-NEXT: fst.s $fa6, $a1, 12 |
| ; LA32D-NEXT: fst.s $fa7, $a1, 8 |
| ; LA32D-NEXT: fst.s $ft2, $a1, 4 |
| ; LA32D-NEXT: fst.s $fa0, $a1, 16 |
| ; LA32D-NEXT: fst.s $ft0, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_f8: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: addi.w $a2, $zero, 1 |
| ; LA64F-NEXT: movgr2fr.w $fa0, $a2 |
| ; LA64F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_0) |
| ; LA64F-NEXT: fld.s $fa1, $a2, %pc_lo12(.LCPI3_0) |
| ; LA64F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_1) |
| ; LA64F-NEXT: fld.s $fa2, $a2, %pc_lo12(.LCPI3_1) |
| ; LA64F-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_2) |
| ; LA64F-NEXT: fld.s $fa3, $a2, %pc_lo12(.LCPI3_2) |
| ; LA64F-NEXT: fld.s $fa4, $a0, 28 |
| ; LA64F-NEXT: fld.s $fa5, $a0, 24 |
| ; LA64F-NEXT: fld.s $fa6, $a0, 12 |
| ; LA64F-NEXT: fld.s $fa7, $a0, 8 |
| ; LA64F-NEXT: fld.s $ft0, $a0, 0 |
| ; LA64F-NEXT: fld.s $ft1, $a0, 16 |
| ; LA64F-NEXT: fld.s $ft2, $a0, 4 |
| ; LA64F-NEXT: ffint.s.w $fa0, $fa0 |
| ; LA64F-NEXT: fadd.s $ft0, $ft0, $fa0 |
| ; LA64F-NEXT: fadd.s $fa0, $ft1, $fa0 |
| ; LA64F-NEXT: fld.s $ft1, $a0, 20 |
| ; LA64F-NEXT: fadd.s $ft2, $ft2, $fa1 |
| ; LA64F-NEXT: fadd.s $fa7, $fa7, $fa2 |
| ; LA64F-NEXT: fadd.s $fa6, $fa6, $fa3 |
| ; LA64F-NEXT: fadd.s $fa1, $ft1, $fa1 |
| ; LA64F-NEXT: fadd.s $fa2, $fa5, $fa2 |
| ; LA64F-NEXT: fadd.s $fa3, $fa4, $fa3 |
| ; LA64F-NEXT: fst.s $fa3, $a1, 28 |
| ; LA64F-NEXT: fst.s $fa2, $a1, 24 |
| ; LA64F-NEXT: fst.s $fa1, $a1, 20 |
| ; LA64F-NEXT: fst.s $fa6, $a1, 12 |
| ; LA64F-NEXT: fst.s $fa7, $a1, 8 |
| ; LA64F-NEXT: fst.s $ft2, $a1, 4 |
| ; LA64F-NEXT: fst.s $fa0, $a1, 16 |
| ; LA64F-NEXT: fst.s $ft0, $a1, 0 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_f8: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: vld $vr0, $a0, 16 |
| ; LA64D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI3_0) |
| ; LA64D-NEXT: vld $vr1, $a2, %pc_lo12(.LCPI3_0) |
| ; LA64D-NEXT: vld $vr2, $a0, 0 |
| ; LA64D-NEXT: vfadd.s $vr0, $vr0, $vr1 |
| ; LA64D-NEXT: vfadd.s $vr1, $vr2, $vr1 |
| ; LA64D-NEXT: vst $vr1, $a1, 0 |
| ; LA64D-NEXT: vst $vr0, $a1, 16 |
| ; LA64D-NEXT: ret |
| %p = load %f8, ptr %P |
| %R = fadd %f8 %p, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 > |
| store %f8 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_d2(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_d2: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: addi.w $sp, $sp, -32 |
| ; LA32F-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $fp, $sp, 24 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s0, $sp, 20 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s1, $sp, 16 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s2, $sp, 12 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s3, $sp, 8 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $fp, $a0, 8 |
| ; LA32F-NEXT: ld.w $s0, $a0, 12 |
| ; LA32F-NEXT: ld.w $a2, $a0, 0 |
| ; LA32F-NEXT: ld.w $a4, $a0, 4 |
| ; LA32F-NEXT: move $s1, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 261888 |
| ; LA32F-NEXT: move $a0, $a2 |
| ; LA32F-NEXT: move $a1, $a4 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s2, $a0 |
| ; LA32F-NEXT: move $s3, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 262144 |
| ; LA32F-NEXT: move $a0, $fp |
| ; LA32F-NEXT: move $a1, $s0 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $s1, 8 |
| ; LA32F-NEXT: st.w $a1, $s1, 12 |
| ; LA32F-NEXT: st.w $s2, $s1, 0 |
| ; LA32F-NEXT: st.w $s3, $s1, 4 |
| ; LA32F-NEXT: ld.w $s3, $sp, 8 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s2, $sp, 12 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s1, $sp, 16 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s0, $sp, 20 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $fp, $sp, 24 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload |
| ; LA32F-NEXT: addi.w $sp, $sp, 32 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_d2: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: fld.d $fa0, $a0, 8 |
| ; LA32D-NEXT: fld.d $fa1, $a0, 0 |
| ; LA32D-NEXT: addi.w $a0, $zero, 1 |
| ; LA32D-NEXT: movgr2fr.w $fa2, $a0 |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI4_0) |
| ; LA32D-NEXT: fld.d $fa3, $a0, %pc_lo12(.LCPI4_0) |
| ; LA32D-NEXT: ffint.s.w $fa2, $fa2 |
| ; LA32D-NEXT: fcvt.d.s $fa2, $fa2 |
| ; LA32D-NEXT: fadd.d $fa1, $fa1, $fa2 |
| ; LA32D-NEXT: fadd.d $fa0, $fa0, $fa3 |
| ; LA32D-NEXT: fst.d $fa0, $a1, 8 |
| ; LA32D-NEXT: fst.d $fa1, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_d2: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: addi.d $sp, $sp, -32 |
| ; LA64F-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $fp, $sp, 16 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s0, $sp, 8 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s1, $sp, 0 # 8-byte Folded Spill |
| ; LA64F-NEXT: ld.d $fp, $a0, 8 |
| ; LA64F-NEXT: ld.d $a0, $a0, 0 |
| ; LA64F-NEXT: move $s0, $a1 |
| ; LA64F-NEXT: lu52i.d $a1, $zero, 1023 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s1, $a0 |
| ; LA64F-NEXT: lu52i.d $a1, $zero, 1024 |
| ; LA64F-NEXT: move $a0, $fp |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: st.d $a0, $s0, 8 |
| ; LA64F-NEXT: st.d $s1, $s0, 0 |
| ; LA64F-NEXT: ld.d $s1, $sp, 0 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s0, $sp, 8 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $fp, $sp, 16 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload |
| ; LA64F-NEXT: addi.d $sp, $sp, 32 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_d2: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: vld $vr0, $a0, 0 |
| ; LA64D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI4_0) |
| ; LA64D-NEXT: vld $vr1, $a0, %pc_lo12(.LCPI4_0) |
| ; LA64D-NEXT: vfadd.d $vr0, $vr0, $vr1 |
| ; LA64D-NEXT: vst $vr0, $a1, 0 |
| ; LA64D-NEXT: ret |
| %p = load %d2, ptr %P |
| %R = fadd %d2 %p, < double 1.000000e+00, double 2.000000e+00 > |
| store %d2 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_d4(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_d4: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: addi.w $sp, $sp, -48 |
| ; LA32F-NEXT: st.w $ra, $sp, 44 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $fp, $sp, 40 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s0, $sp, 36 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s1, $sp, 32 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s2, $sp, 28 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s3, $sp, 24 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s4, $sp, 20 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s5, $sp, 16 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s6, $sp, 12 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s7, $sp, 8 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $fp, $a0, 24 |
| ; LA32F-NEXT: ld.w $s0, $a0, 28 |
| ; LA32F-NEXT: ld.w $s1, $a0, 16 |
| ; LA32F-NEXT: ld.w $s2, $a0, 20 |
| ; LA32F-NEXT: ld.w $s3, $a0, 8 |
| ; LA32F-NEXT: ld.w $s4, $a0, 12 |
| ; LA32F-NEXT: ld.w $a2, $a0, 0 |
| ; LA32F-NEXT: ld.w $a4, $a0, 4 |
| ; LA32F-NEXT: move $s5, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 261888 |
| ; LA32F-NEXT: move $a0, $a2 |
| ; LA32F-NEXT: move $a1, $a4 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s6, $a0 |
| ; LA32F-NEXT: move $s7, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 262144 |
| ; LA32F-NEXT: move $a0, $s3 |
| ; LA32F-NEXT: move $a1, $s4 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s3, $a0 |
| ; LA32F-NEXT: move $s4, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 262272 |
| ; LA32F-NEXT: move $a0, $s1 |
| ; LA32F-NEXT: move $a1, $s2 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s1, $a0 |
| ; LA32F-NEXT: move $s2, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 262400 |
| ; LA32F-NEXT: move $a0, $fp |
| ; LA32F-NEXT: move $a1, $s0 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $s5, 24 |
| ; LA32F-NEXT: st.w $a1, $s5, 28 |
| ; LA32F-NEXT: st.w $s1, $s5, 16 |
| ; LA32F-NEXT: st.w $s2, $s5, 20 |
| ; LA32F-NEXT: st.w $s3, $s5, 8 |
| ; LA32F-NEXT: st.w $s4, $s5, 12 |
| ; LA32F-NEXT: st.w $s6, $s5, 0 |
| ; LA32F-NEXT: st.w $s7, $s5, 4 |
| ; LA32F-NEXT: ld.w $s7, $sp, 8 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s6, $sp, 12 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s5, $sp, 16 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s4, $sp, 20 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s3, $sp, 24 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s2, $sp, 28 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s1, $sp, 32 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s0, $sp, 36 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $fp, $sp, 40 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $ra, $sp, 44 # 4-byte Folded Reload |
| ; LA32F-NEXT: addi.w $sp, $sp, 48 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_d4: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: fld.d $fa0, $a0, 24 |
| ; LA32D-NEXT: fld.d $fa1, $a0, 16 |
| ; LA32D-NEXT: fld.d $fa2, $a0, 8 |
| ; LA32D-NEXT: fld.d $fa3, $a0, 0 |
| ; LA32D-NEXT: addi.w $a0, $zero, 1 |
| ; LA32D-NEXT: movgr2fr.w $fa4, $a0 |
| ; LA32D-NEXT: ffint.s.w $fa4, $fa4 |
| ; LA32D-NEXT: fcvt.d.s $fa4, $fa4 |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_0) |
| ; LA32D-NEXT: fld.d $fa5, $a0, %pc_lo12(.LCPI5_0) |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_1) |
| ; LA32D-NEXT: fld.d $fa6, $a0, %pc_lo12(.LCPI5_1) |
| ; LA32D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_2) |
| ; LA32D-NEXT: fld.d $fa7, $a0, %pc_lo12(.LCPI5_2) |
| ; LA32D-NEXT: fadd.d $fa3, $fa3, $fa4 |
| ; LA32D-NEXT: fadd.d $fa2, $fa2, $fa5 |
| ; LA32D-NEXT: fadd.d $fa1, $fa1, $fa6 |
| ; LA32D-NEXT: fadd.d $fa0, $fa0, $fa7 |
| ; LA32D-NEXT: fst.d $fa0, $a1, 24 |
| ; LA32D-NEXT: fst.d $fa1, $a1, 16 |
| ; LA32D-NEXT: fst.d $fa2, $a1, 8 |
| ; LA32D-NEXT: fst.d $fa3, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_d4: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: addi.d $sp, $sp, -48 |
| ; LA64F-NEXT: st.d $ra, $sp, 40 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $fp, $sp, 32 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s0, $sp, 24 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s1, $sp, 16 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s2, $sp, 8 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s3, $sp, 0 # 8-byte Folded Spill |
| ; LA64F-NEXT: ld.d $fp, $a0, 24 |
| ; LA64F-NEXT: ld.d $s0, $a0, 8 |
| ; LA64F-NEXT: ld.d $s1, $a0, 0 |
| ; LA64F-NEXT: ld.d $a0, $a0, 16 |
| ; LA64F-NEXT: move $s2, $a1 |
| ; LA64F-NEXT: ori $a1, $zero, 0 |
| ; LA64F-NEXT: lu32i.d $a1, -524288 |
| ; LA64F-NEXT: lu52i.d $a1, $a1, 1024 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s3, $a0 |
| ; LA64F-NEXT: lu52i.d $a1, $zero, 1023 |
| ; LA64F-NEXT: move $a0, $s1 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s1, $a0 |
| ; LA64F-NEXT: lu52i.d $a1, $zero, 1024 |
| ; LA64F-NEXT: move $a0, $s0 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s0, $a0 |
| ; LA64F-NEXT: lu52i.d $a1, $zero, 1025 |
| ; LA64F-NEXT: move $a0, $fp |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: st.d $a0, $s2, 24 |
| ; LA64F-NEXT: st.d $s0, $s2, 8 |
| ; LA64F-NEXT: st.d $s1, $s2, 0 |
| ; LA64F-NEXT: st.d $s3, $s2, 16 |
| ; LA64F-NEXT: ld.d $s3, $sp, 0 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s2, $sp, 8 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s1, $sp, 16 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s0, $sp, 24 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $fp, $sp, 32 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $ra, $sp, 40 # 8-byte Folded Reload |
| ; LA64F-NEXT: addi.d $sp, $sp, 48 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_d4: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: vld $vr0, $a0, 0 |
| ; LA64D-NEXT: vld $vr1, $a0, 16 |
| ; LA64D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_0) |
| ; LA64D-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI5_0) |
| ; LA64D-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_1) |
| ; LA64D-NEXT: vld $vr3, $a0, %pc_lo12(.LCPI5_1) |
| ; LA64D-NEXT: vfadd.d $vr1, $vr1, $vr2 |
| ; LA64D-NEXT: vfadd.d $vr0, $vr0, $vr3 |
| ; LA64D-NEXT: vst $vr0, $a1, 0 |
| ; LA64D-NEXT: vst $vr1, $a1, 16 |
| ; LA64D-NEXT: ret |
| %p = load %d4, ptr %P |
| %R = fadd %d4 %p, < double 1.000000e+00, double 2.000000e+00, double 3.000000e+00, double 4.000000e+00 > |
| store %d4 %R, ptr %S |
| ret void |
| } |
| |
| define void @test_d8(ptr %P, ptr %S) nounwind { |
| ; LA32F-LABEL: test_d8: |
| ; LA32F: # %bb.0: |
| ; LA32F-NEXT: addi.w $sp, $sp, -96 |
| ; LA32F-NEXT: st.w $ra, $sp, 92 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $fp, $sp, 88 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s0, $sp, 84 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s1, $sp, 80 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s2, $sp, 76 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s3, $sp, 72 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s4, $sp, 68 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s5, $sp, 64 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s6, $sp, 60 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s7, $sp, 56 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $s8, $sp, 52 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $a2, $a0, 56 |
| ; LA32F-NEXT: st.w $a2, $sp, 48 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $a2, $a0, 60 |
| ; LA32F-NEXT: st.w $a2, $sp, 44 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $a2, $a0, 48 |
| ; LA32F-NEXT: st.w $a2, $sp, 32 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $a2, $a0, 52 |
| ; LA32F-NEXT: st.w $a2, $sp, 28 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $s8, $a0, 40 |
| ; LA32F-NEXT: ld.w $a2, $a0, 44 |
| ; LA32F-NEXT: st.w $a2, $sp, 16 # 4-byte Folded Spill |
| ; LA32F-NEXT: ld.w $s3, $a0, 32 |
| ; LA32F-NEXT: ld.w $s4, $a0, 36 |
| ; LA32F-NEXT: ld.w $s5, $a0, 24 |
| ; LA32F-NEXT: ld.w $s6, $a0, 28 |
| ; LA32F-NEXT: ld.w $s1, $a0, 16 |
| ; LA32F-NEXT: ld.w $s2, $a0, 20 |
| ; LA32F-NEXT: ld.w $s7, $a0, 8 |
| ; LA32F-NEXT: ld.w $s0, $a0, 12 |
| ; LA32F-NEXT: ld.w $a2, $a0, 0 |
| ; LA32F-NEXT: ld.w $a4, $a0, 4 |
| ; LA32F-NEXT: move $fp, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 261888 |
| ; LA32F-NEXT: move $a0, $a2 |
| ; LA32F-NEXT: move $a1, $a4 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $sp, 40 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $a1, $sp, 36 # 4-byte Folded Spill |
| ; LA32F-NEXT: lu12i.w $a3, 262144 |
| ; LA32F-NEXT: move $a0, $s7 |
| ; LA32F-NEXT: move $a1, $s0 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: move $s0, $a3 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $sp, 24 # 4-byte Folded Spill |
| ; LA32F-NEXT: st.w $a1, $sp, 20 # 4-byte Folded Spill |
| ; LA32F-NEXT: lu12i.w $s7, 262272 |
| ; LA32F-NEXT: move $a0, $s1 |
| ; LA32F-NEXT: move $a1, $s2 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: move $a3, $s7 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $sp, 12 # 4-byte Folded Spill |
| ; LA32F-NEXT: move $s2, $a1 |
| ; LA32F-NEXT: lu12i.w $a3, 262400 |
| ; LA32F-NEXT: move $a0, $s5 |
| ; LA32F-NEXT: move $a1, $s6 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s5, $a0 |
| ; LA32F-NEXT: move $s6, $a1 |
| ; LA32F-NEXT: move $a0, $s3 |
| ; LA32F-NEXT: move $a1, $s4 |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: lu12i.w $a3, 261888 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s3, $a0 |
| ; LA32F-NEXT: move $s4, $a1 |
| ; LA32F-NEXT: move $a0, $s8 |
| ; LA32F-NEXT: ld.w $a1, $sp, 16 # 4-byte Folded Reload |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: move $a3, $s0 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s8, $a0 |
| ; LA32F-NEXT: move $s0, $a1 |
| ; LA32F-NEXT: ld.w $a0, $sp, 32 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $a1, $sp, 28 # 4-byte Folded Reload |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: move $a3, $s7 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: move $s7, $a0 |
| ; LA32F-NEXT: move $s1, $a1 |
| ; LA32F-NEXT: ld.w $a0, $sp, 48 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $a1, $sp, 44 # 4-byte Folded Reload |
| ; LA32F-NEXT: move $a2, $zero |
| ; LA32F-NEXT: lu12i.w $a3, 262400 |
| ; LA32F-NEXT: bl %plt(__adddf3) |
| ; LA32F-NEXT: st.w $a0, $fp, 56 |
| ; LA32F-NEXT: st.w $a1, $fp, 60 |
| ; LA32F-NEXT: st.w $s7, $fp, 48 |
| ; LA32F-NEXT: st.w $s1, $fp, 52 |
| ; LA32F-NEXT: st.w $s8, $fp, 40 |
| ; LA32F-NEXT: st.w $s0, $fp, 44 |
| ; LA32F-NEXT: st.w $s3, $fp, 32 |
| ; LA32F-NEXT: st.w $s4, $fp, 36 |
| ; LA32F-NEXT: st.w $s5, $fp, 24 |
| ; LA32F-NEXT: st.w $s6, $fp, 28 |
| ; LA32F-NEXT: ld.w $a0, $sp, 12 # 4-byte Folded Reload |
| ; LA32F-NEXT: st.w $a0, $fp, 16 |
| ; LA32F-NEXT: st.w $s2, $fp, 20 |
| ; LA32F-NEXT: ld.w $a0, $sp, 24 # 4-byte Folded Reload |
| ; LA32F-NEXT: st.w $a0, $fp, 8 |
| ; LA32F-NEXT: ld.w $a0, $sp, 20 # 4-byte Folded Reload |
| ; LA32F-NEXT: st.w $a0, $fp, 12 |
| ; LA32F-NEXT: ld.w $a0, $sp, 40 # 4-byte Folded Reload |
| ; LA32F-NEXT: st.w $a0, $fp, 0 |
| ; LA32F-NEXT: ld.w $a0, $sp, 36 # 4-byte Folded Reload |
| ; LA32F-NEXT: st.w $a0, $fp, 4 |
| ; LA32F-NEXT: ld.w $s8, $sp, 52 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s7, $sp, 56 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s6, $sp, 60 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s5, $sp, 64 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s4, $sp, 68 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s3, $sp, 72 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s2, $sp, 76 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s1, $sp, 80 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $s0, $sp, 84 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $fp, $sp, 88 # 4-byte Folded Reload |
| ; LA32F-NEXT: ld.w $ra, $sp, 92 # 4-byte Folded Reload |
| ; LA32F-NEXT: addi.w $sp, $sp, 96 |
| ; LA32F-NEXT: ret |
| ; |
| ; LA32D-LABEL: test_d8: |
| ; LA32D: # %bb.0: |
| ; LA32D-NEXT: addi.w $a2, $zero, 1 |
| ; LA32D-NEXT: movgr2fr.w $fa0, $a2 |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI6_0) |
| ; LA32D-NEXT: fld.d $fa1, $a2, %pc_lo12(.LCPI6_0) |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI6_1) |
| ; LA32D-NEXT: fld.d $fa2, $a2, %pc_lo12(.LCPI6_1) |
| ; LA32D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI6_2) |
| ; LA32D-NEXT: fld.d $fa3, $a2, %pc_lo12(.LCPI6_2) |
| ; LA32D-NEXT: fld.d $fa4, $a0, 56 |
| ; LA32D-NEXT: fld.d $fa5, $a0, 48 |
| ; LA32D-NEXT: fld.d $fa6, $a0, 24 |
| ; LA32D-NEXT: fld.d $fa7, $a0, 16 |
| ; LA32D-NEXT: fld.d $ft0, $a0, 8 |
| ; LA32D-NEXT: fld.d $ft1, $a0, 0 |
| ; LA32D-NEXT: fld.d $ft2, $a0, 32 |
| ; LA32D-NEXT: ffint.s.w $fa0, $fa0 |
| ; LA32D-NEXT: fcvt.d.s $fa0, $fa0 |
| ; LA32D-NEXT: fadd.d $ft1, $ft1, $fa0 |
| ; LA32D-NEXT: fadd.d $fa0, $ft2, $fa0 |
| ; LA32D-NEXT: fld.d $ft2, $a0, 40 |
| ; LA32D-NEXT: fadd.d $ft0, $ft0, $fa1 |
| ; LA32D-NEXT: fadd.d $fa7, $fa7, $fa2 |
| ; LA32D-NEXT: fadd.d $fa6, $fa6, $fa3 |
| ; LA32D-NEXT: fadd.d $fa1, $ft2, $fa1 |
| ; LA32D-NEXT: fadd.d $fa2, $fa5, $fa2 |
| ; LA32D-NEXT: fadd.d $fa3, $fa4, $fa3 |
| ; LA32D-NEXT: fst.d $fa3, $a1, 56 |
| ; LA32D-NEXT: fst.d $fa2, $a1, 48 |
| ; LA32D-NEXT: fst.d $fa1, $a1, 40 |
| ; LA32D-NEXT: fst.d $fa6, $a1, 24 |
| ; LA32D-NEXT: fst.d $fa7, $a1, 16 |
| ; LA32D-NEXT: fst.d $ft0, $a1, 8 |
| ; LA32D-NEXT: fst.d $fa0, $a1, 32 |
| ; LA32D-NEXT: fst.d $ft1, $a1, 0 |
| ; LA32D-NEXT: ret |
| ; |
| ; LA64F-LABEL: test_d8: |
| ; LA64F: # %bb.0: |
| ; LA64F-NEXT: addi.d $sp, $sp, -112 |
| ; LA64F-NEXT: st.d $ra, $sp, 104 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $fp, $sp, 96 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s0, $sp, 88 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s1, $sp, 80 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s2, $sp, 72 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s3, $sp, 64 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s4, $sp, 56 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s5, $sp, 48 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s6, $sp, 40 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s7, $sp, 32 # 8-byte Folded Spill |
| ; LA64F-NEXT: st.d $s8, $sp, 24 # 8-byte Folded Spill |
| ; LA64F-NEXT: ld.d $a2, $a0, 56 |
| ; LA64F-NEXT: st.d $a2, $sp, 16 # 8-byte Folded Spill |
| ; LA64F-NEXT: ld.d $s1, $a0, 40 |
| ; LA64F-NEXT: ld.d $s2, $a0, 32 |
| ; LA64F-NEXT: ld.d $s3, $a0, 24 |
| ; LA64F-NEXT: ld.d $s4, $a0, 8 |
| ; LA64F-NEXT: ld.d $s5, $a0, 0 |
| ; LA64F-NEXT: ld.d $s6, $a0, 48 |
| ; LA64F-NEXT: ld.d $a0, $a0, 16 |
| ; LA64F-NEXT: move $fp, $a1 |
| ; LA64F-NEXT: ori $a1, $zero, 0 |
| ; LA64F-NEXT: lu32i.d $a1, -524288 |
| ; LA64F-NEXT: lu52i.d $s7, $a1, 1024 |
| ; LA64F-NEXT: move $a1, $s7 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: st.d $a0, $sp, 8 # 8-byte Folded Spill |
| ; LA64F-NEXT: move $a0, $s6 |
| ; LA64F-NEXT: move $a1, $s7 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s6, $a0 |
| ; LA64F-NEXT: lu52i.d $s7, $zero, 1023 |
| ; LA64F-NEXT: move $a0, $s5 |
| ; LA64F-NEXT: move $a1, $s7 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s5, $a0 |
| ; LA64F-NEXT: lu52i.d $s0, $zero, 1024 |
| ; LA64F-NEXT: move $a0, $s4 |
| ; LA64F-NEXT: move $a1, $s0 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s4, $a0 |
| ; LA64F-NEXT: lu52i.d $s8, $zero, 1025 |
| ; LA64F-NEXT: move $a0, $s3 |
| ; LA64F-NEXT: move $a1, $s8 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s3, $a0 |
| ; LA64F-NEXT: move $a0, $s2 |
| ; LA64F-NEXT: move $a1, $s7 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s2, $a0 |
| ; LA64F-NEXT: move $a0, $s1 |
| ; LA64F-NEXT: move $a1, $s0 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: move $s0, $a0 |
| ; LA64F-NEXT: ld.d $a0, $sp, 16 # 8-byte Folded Reload |
| ; LA64F-NEXT: move $a1, $s8 |
| ; LA64F-NEXT: bl %plt(__adddf3) |
| ; LA64F-NEXT: st.d $a0, $fp, 56 |
| ; LA64F-NEXT: st.d $s0, $fp, 40 |
| ; LA64F-NEXT: st.d $s2, $fp, 32 |
| ; LA64F-NEXT: st.d $s3, $fp, 24 |
| ; LA64F-NEXT: st.d $s4, $fp, 8 |
| ; LA64F-NEXT: st.d $s5, $fp, 0 |
| ; LA64F-NEXT: st.d $s6, $fp, 48 |
| ; LA64F-NEXT: ld.d $a0, $sp, 8 # 8-byte Folded Reload |
| ; LA64F-NEXT: st.d $a0, $fp, 16 |
| ; LA64F-NEXT: ld.d $s8, $sp, 24 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s7, $sp, 32 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s6, $sp, 40 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s5, $sp, 48 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s4, $sp, 56 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s3, $sp, 64 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s2, $sp, 72 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s1, $sp, 80 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $s0, $sp, 88 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $fp, $sp, 96 # 8-byte Folded Reload |
| ; LA64F-NEXT: ld.d $ra, $sp, 104 # 8-byte Folded Reload |
| ; LA64F-NEXT: addi.d $sp, $sp, 112 |
| ; LA64F-NEXT: ret |
| ; |
| ; LA64D-LABEL: test_d8: |
| ; LA64D: # %bb.0: |
| ; LA64D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI6_0) |
| ; LA64D-NEXT: vld $vr0, $a2, %pc_lo12(.LCPI6_0) |
| ; LA64D-NEXT: pcalau12i $a2, %pc_hi20(.LCPI6_1) |
| ; LA64D-NEXT: vld $vr1, $a2, %pc_lo12(.LCPI6_1) |
| ; LA64D-NEXT: vld $vr2, $a0, 16 |
| ; LA64D-NEXT: vld $vr3, $a0, 0 |
| ; LA64D-NEXT: vld $vr4, $a0, 48 |
| ; LA64D-NEXT: vld $vr5, $a0, 32 |
| ; LA64D-NEXT: vfadd.d $vr2, $vr2, $vr0 |
| ; LA64D-NEXT: vfadd.d $vr3, $vr3, $vr1 |
| ; LA64D-NEXT: vfadd.d $vr0, $vr4, $vr0 |
| ; LA64D-NEXT: vfadd.d $vr1, $vr5, $vr1 |
| ; LA64D-NEXT: vst $vr1, $a1, 32 |
| ; LA64D-NEXT: vst $vr0, $a1, 48 |
| ; LA64D-NEXT: vst $vr3, $a1, 0 |
| ; LA64D-NEXT: vst $vr2, $a1, 16 |
| ; LA64D-NEXT: ret |
| %p = load %d8, ptr %P |
| %R = fadd %d8 %p, < double 1.000000e+00, double 2.000000e+00, double 3.000000e+00, double 4.000000e+00, double 1.000000e+00, double 2.000000e+00, double 3.000000e+00, double 4.000000e+00 > |
| store %d8 %R, ptr %S |
| ret void |
| } |
