From 281f2ca93832d7bc1c3a871a578404a19dc603f3 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Tue, 8 Jul 2025 16:34:35 +0900
Subject: [PATCH] LoongArch: Add test for sincos intrinsic

---
 llvm/test/CodeGen/LoongArch/llvm.sincos.ll | 866 +++++++++++++++++++++
 1 file changed, 866 insertions(+)
 create mode 100644 llvm/test/CodeGen/LoongArch/llvm.sincos.ll

diff --git a/llvm/test/CodeGen/LoongArch/llvm.sincos.ll b/llvm/test/CodeGen/LoongArch/llvm.sincos.ll
new file mode 100644
index 0000000000000..ffedd7f9e9438
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/llvm.sincos.ll
@@ -0,0 +1,866 @@
+; 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 { half, half } @test_sincos_f16(half %a) #0 {
+; LA32-LABEL: test_sincos_f16:
+; 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:    fst.d $fs0, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    bl __extendhfsf2
+; LA32-NEXT:    fmov.s $fs0, $fa0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    movfr2gr.s $fp, $fs1
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    movfr2gr.s $a0, $fa0
+; LA32-NEXT:    lu12i.w $a1, -16
+; LA32-NEXT:    or $a0, $a0, $a1
+; LA32-NEXT:    movgr2fr.w $fa0, $a0
+; LA32-NEXT:    or $a0, $fp, $a1
+; LA32-NEXT:    movgr2fr.w $fa1, $a0
+; LA32-NEXT:    fld.d $fs1, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 16 # 8-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_sincos_f16:
+; 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:    fst.d $fs1, $sp, 0 # 8-byte Folded Spill
+; LA64-NEXT:    pcaddu18i $ra, %call36(__extendhfsf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs0, $fa0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs1, $fa0
+; LA64-NEXT:    fmov.s $fa0, $fs0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $fp, $fs1
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $a0, $fa0
+; LA64-NEXT:    lu12i.w $a1, -16
+; LA64-NEXT:    or $a0, $a0, $a1
+; LA64-NEXT:    movgr2fr.w $fa0, $a0
+; LA64-NEXT:    or $a0, $fp, $a1
+; LA64-NEXT:    movgr2fr.w $fa1, $a0
+; LA64-NEXT:    fld.d $fs1, $sp, 0 # 8-byte Folded Reload
+; 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
+  %result = call { half, half } @llvm.sincos.f16(half %a)
+  ret { half, half } %result
+}
+
+define half @test_sincos_f16_only_use_sin(half %a) #0 {
+; LA32-LABEL: test_sincos_f16_only_use_sin:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -16
+; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
+; LA32-NEXT:    bl __extendhfsf2
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    movfr2gr.s $a0, $fa0
+; LA32-NEXT:    lu12i.w $a1, -16
+; LA32-NEXT:    or $a0, $a0, $a1
+; LA32-NEXT:    movgr2fr.w $fa0, $a0
+; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 16
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_f16_only_use_sin:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -16
+; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    pcaddu18i $ra, %call36(__extendhfsf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $a0, $fa0
+; LA64-NEXT:    lu12i.w $a1, -16
+; LA64-NEXT:    or $a0, $a0, $a1
+; LA64-NEXT:    movgr2fr.w $fa0, $a0
+; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 16
+; LA64-NEXT:    ret
+  %result = call { half, half } @llvm.sincos.f16(half %a)
+  %result.0 = extractvalue { half, half } %result, 0
+  ret half %result.0
+}
+
+define half @test_sincos_f16_only_use_cos(half %a) #0 {
+; LA32-LABEL: test_sincos_f16_only_use_cos:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -16
+; LA32-NEXT:    st.w $ra, $sp, 12 # 4-byte Folded Spill
+; LA32-NEXT:    bl __extendhfsf2
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    movfr2gr.s $a0, $fa0
+; LA32-NEXT:    lu12i.w $a1, -16
+; LA32-NEXT:    or $a0, $a0, $a1
+; LA32-NEXT:    movgr2fr.w $fa0, $a0
+; LA32-NEXT:    ld.w $ra, $sp, 12 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 16
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_f16_only_use_cos:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -16
+; LA64-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    pcaddu18i $ra, %call36(__extendhfsf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $a0, $fa0
+; LA64-NEXT:    lu12i.w $a1, -16
+; LA64-NEXT:    or $a0, $a0, $a1
+; LA64-NEXT:    movgr2fr.w $fa0, $a0
+; LA64-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 16
+; LA64-NEXT:    ret
+  %result = call { half, half } @llvm.sincos.f16(half %a)
+  %result.1 = extractvalue { half, half } %result, 1
+  ret half %result.1
+}
+
+define { <2 x half>, <2 x half> } @test_sincos_v2f16(<2 x half> %a) #0 {
+; LA32-LABEL: test_sincos_v2f16:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -64
+; LA32-NEXT:    st.w $ra, $sp, 60 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 56 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s0, $sp, 52 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s1, $sp, 48 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s2, $sp, 44 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 32 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 24 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs2, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs3, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    movgr2fr.w $fs0, $a2
+; LA32-NEXT:    movgr2fr.w $fa0, $a1
+; LA32-NEXT:    bl __extendhfsf2
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    fmov.s $fs2, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl __extendhfsf2
+; LA32-NEXT:    fmov.s $fs0, $fa0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    fmov.s $fs3, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs1
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    movfr2gr.s $s0, $fs1
+; LA32-NEXT:    movfr2gr.s $s1, $fs3
+; LA32-NEXT:    movfr2gr.s $s2, $fs2
+; LA32-NEXT:    bl __truncsfhf2
+; LA32-NEXT:    movfr2gr.s $a0, $fa0
+; LA32-NEXT:    st.h $a0, $fp, 6
+; LA32-NEXT:    st.h $s2, $fp, 4
+; LA32-NEXT:    st.h $s1, $fp, 2
+; LA32-NEXT:    st.h $s0, $fp, 0
+; LA32-NEXT:    fld.d $fs3, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs2, $sp, 16 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs1, $sp, 24 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 32 # 8-byte Folded Reload
+; LA32-NEXT:    ld.w $s2, $sp, 44 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s1, $sp, 48 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s0, $sp, 52 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 56 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 60 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 64
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_v2f16:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -80
+; LA64-NEXT:    st.d $ra, $sp, 72 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 64 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s0, $sp, 56 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s1, $sp, 48 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s2, $sp, 40 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs0, $sp, 32 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs1, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs2, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs3, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    move $s0, $a2
+; LA64-NEXT:    move $fp, $a0
+; LA64-NEXT:    movgr2fr.w $fa0, $a1
+; LA64-NEXT:    pcaddu18i $ra, %call36(__extendhfsf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs0, $fa0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs1, $fa0
+; LA64-NEXT:    movgr2fr.w $fa0, $s0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__extendhfsf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs2, $fa0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs3, $fa0
+; LA64-NEXT:    fmov.s $fa0, $fs0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs0, $fa0
+; LA64-NEXT:    fmov.s $fa0, $fs2
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $s0, $fs0
+; LA64-NEXT:    movfr2gr.s $s1, $fs3
+; LA64-NEXT:    movfr2gr.s $s2, $fs1
+; LA64-NEXT:    pcaddu18i $ra, %call36(__truncsfhf2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.s $a0, $fa0
+; LA64-NEXT:    st.h $a0, $fp, 6
+; LA64-NEXT:    st.h $s2, $fp, 4
+; LA64-NEXT:    st.h $s1, $fp, 2
+; LA64-NEXT:    st.h $s0, $fp, 0
+; LA64-NEXT:    fld.d $fs3, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    fld.d $fs2, $sp, 16 # 8-byte Folded Reload
+; LA64-NEXT:    fld.d $fs1, $sp, 24 # 8-byte Folded Reload
+; LA64-NEXT:    fld.d $fs0, $sp, 32 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s2, $sp, 40 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s1, $sp, 48 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s0, $sp, 56 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $fp, $sp, 64 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 72 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 80
+; LA64-NEXT:    ret
+  %result = call { <2 x half>, <2 x half> } @llvm.sincos.v2f16(<2 x half> %a)
+  ret { <2 x half>, <2 x half> } %result
+}
+
+define { float, float } @test_sincos_f32(float %a) #0 {
+; LA32-LABEL: test_sincos_f32:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -32
+; LA32-NEXT:    st.w $ra, $sp, 28 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    fmov.s $fs0, $fa0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fmov.s $fa1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs1
+; LA32-NEXT:    fld.d $fs1, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 16 # 8-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_sincos_f32:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -32
+; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs0, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs1, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    fmov.s $fs0, $fa0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fs1, $fa0
+; LA64-NEXT:    fmov.s $fa0, $fs0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.s $fa1, $fa0
+; LA64-NEXT:    fmov.s $fa0, $fs1
+; LA64-NEXT:    fld.d $fs1, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    fld.d $fs0, $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
+  %result = call { float, float } @llvm.sincos.f32(float %a)
+  ret { float, float } %result
+}
+
+define { <2 x float>, <2 x float> } @test_sincos_v2f32(<2 x float> %a) #0 {
+; LA32-LABEL: test_sincos_v2f32:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -48
+; LA32-NEXT:    st.w $ra, $sp, 44 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 40 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 32 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 24 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs2, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs3, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    fmov.s $fs0, $fa1
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs2, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs3, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs1
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fst.s $fa0, $fp, 12
+; LA32-NEXT:    fst.s $fs1, $fp, 8
+; LA32-NEXT:    fst.s $fs3, $fp, 4
+; LA32-NEXT:    fst.s $fs2, $fp, 0
+; LA32-NEXT:    fld.d $fs3, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs2, $sp, 16 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs1, $sp, 24 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 32 # 8-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 40 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 44 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 48
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_v2f32:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -64
+; LA64-NEXT:    st.d $ra, $sp, 56 # 8-byte Folded Spill
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vpackev.w $vr0, $vr0, $vr1
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    vpackev.w $vr1, $vr0, $vr1
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 56 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 64
+; LA64-NEXT:    ret
+  %result = call { <2 x float>, <2 x float> } @llvm.sincos.v2f32(<2 x float> %a)
+  ret { <2 x float>, <2 x float> } %result
+}
+
+define { <3 x float>, <3 x float> } @test_sincos_v3f32(<3 x float> %a) #0 {
+; LA32-LABEL: test_sincos_v3f32:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -64
+; LA32-NEXT:    st.w $ra, $sp, 60 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 56 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 48 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 40 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs2, $sp, 32 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs3, $sp, 24 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs4, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs5, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    fmov.s $fs0, $fa2
+; LA32-NEXT:    fmov.s $fs1, $fa1
+; LA32-NEXT:    fmov.s $fs2, $fa0
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs3, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs1
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs4, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl sinf
+; LA32-NEXT:    fmov.s $fs5, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs2
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fmov.s $fs2, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs1
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fmov.s $fs1, $fa0
+; LA32-NEXT:    fmov.s $fa0, $fs0
+; LA32-NEXT:    bl cosf
+; LA32-NEXT:    fst.s $fa0, $fp, 24
+; LA32-NEXT:    fst.s $fs1, $fp, 20
+; LA32-NEXT:    fst.s $fs2, $fp, 16
+; LA32-NEXT:    fst.s $fs5, $fp, 8
+; LA32-NEXT:    fst.s $fs4, $fp, 4
+; LA32-NEXT:    fst.s $fs3, $fp, 0
+; LA32-NEXT:    fld.d $fs5, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs4, $sp, 16 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs3, $sp, 24 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs2, $sp, 32 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs1, $sp, 40 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 48 # 8-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 56 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 60 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 64
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_v3f32:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -96
+; LA64-NEXT:    st.d $ra, $sp, 88 # 8-byte Folded Spill
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 2
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 72
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 68
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 64
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 56
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 52
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosf)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fst.s $fa0, $sp, 48
+; LA64-NEXT:    vld $vr0, $sp, 64
+; LA64-NEXT:    vld $vr1, $sp, 48
+; LA64-NEXT:    ld.d $ra, $sp, 88 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 96
+; LA64-NEXT:    ret
+  %result = call { <3 x float>, <3 x float> } @llvm.sincos.v3f32(<3 x float> %a)
+  ret { <3 x float>, <3 x float> } %result
+}
+
+define { double, double } @test_sincos_f64(double %a) #0 {
+; LA32-LABEL: test_sincos_f64:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -32
+; LA32-NEXT:    st.w $ra, $sp, 28 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    fmov.d $fs0, $fa0
+; LA32-NEXT:    bl sin
+; LA32-NEXT:    fmov.d $fs1, $fa0
+; LA32-NEXT:    fmov.d $fa0, $fs0
+; LA32-NEXT:    bl cos
+; LA32-NEXT:    fmov.d $fa1, $fa0
+; LA32-NEXT:    fmov.d $fa0, $fs1
+; LA32-NEXT:    fld.d $fs1, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 16 # 8-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_sincos_f64:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -32
+; LA64-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs0, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    fst.d $fs1, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    fmov.d $fs0, $fa0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sin)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.d $fs1, $fa0
+; LA64-NEXT:    fmov.d $fa0, $fs0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cos)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    fmov.d $fa1, $fa0
+; LA64-NEXT:    fmov.d $fa0, $fs1
+; LA64-NEXT:    fld.d $fs1, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    fld.d $fs0, $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
+  %result = call { double, double } @llvm.sincos.f64(double %a)
+  ret { double, double } %result
+}
+
+define { <2 x double>, <2 x double> } @test_sincos_v2f64(<2 x double> %a) #0 {
+; LA32-LABEL: test_sincos_v2f64:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -48
+; LA32-NEXT:    st.w $ra, $sp, 44 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 40 # 4-byte Folded Spill
+; LA32-NEXT:    fst.d $fs0, $sp, 32 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs1, $sp, 24 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs2, $sp, 16 # 8-byte Folded Spill
+; LA32-NEXT:    fst.d $fs3, $sp, 8 # 8-byte Folded Spill
+; LA32-NEXT:    fmov.d $fs0, $fa1
+; LA32-NEXT:    fmov.d $fs1, $fa0
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    bl sin
+; LA32-NEXT:    fmov.d $fs2, $fa0
+; LA32-NEXT:    fmov.d $fa0, $fs0
+; LA32-NEXT:    bl sin
+; LA32-NEXT:    fmov.d $fs3, $fa0
+; LA32-NEXT:    fmov.d $fa0, $fs1
+; LA32-NEXT:    bl cos
+; LA32-NEXT:    fmov.d $fs1, $fa0
+; LA32-NEXT:    fmov.d $fa0, $fs0
+; LA32-NEXT:    bl cos
+; LA32-NEXT:    fst.d $fa0, $fp, 24
+; LA32-NEXT:    fst.d $fs1, $fp, 16
+; LA32-NEXT:    fst.d $fs3, $fp, 8
+; LA32-NEXT:    fst.d $fs2, $fp, 0
+; LA32-NEXT:    fld.d $fs3, $sp, 8 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs2, $sp, 16 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs1, $sp, 24 # 8-byte Folded Reload
+; LA32-NEXT:    fld.d $fs0, $sp, 32 # 8-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 40 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 44 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 48
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_v2f64:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -64
+; LA64-NEXT:    st.d $ra, $sp, 56 # 8-byte Folded Spill
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vreplvei.d $vr0, $vr0, 0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sin)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.d $a0, $fa0
+; LA64-NEXT:    vinsgr2vr.d $vr0, $a0, 0
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.d $vr0, $vr0, 1
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sin)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.d $a0, $fa0
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    vinsgr2vr.d $vr0, $a0, 1
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cos)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.d $a0, $fa0
+; LA64-NEXT:    vinsgr2vr.d $vr0, $a0, 0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cos)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    movfr2gr.d $a0, $fa0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vinsgr2vr.d $vr1, $a0, 1
+; LA64-NEXT:    vld $vr0, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 56 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 64
+; LA64-NEXT:    ret
+  %result = call { <2 x double>, <2 x double> } @llvm.sincos.v2f64(<2 x double> %a)
+  ret { <2 x double>, <2 x double> } %result
+}
+
+define { fp128, fp128 } @test_sincos_f128(fp128 %a) #0 {
+; LA32-LABEL: test_sincos_f128:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -96
+; LA32-NEXT:    st.w $ra, $sp, 92 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 88 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s0, $sp, 84 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s1, $sp, 80 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s2, $sp, 76 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s3, $sp, 72 # 4-byte Folded Spill
+; LA32-NEXT:    ld.w $s0, $a1, 0
+; LA32-NEXT:    ld.w $s1, $a1, 4
+; LA32-NEXT:    ld.w $s2, $a1, 8
+; LA32-NEXT:    ld.w $s3, $a1, 12
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    st.w $s3, $sp, 52
+; LA32-NEXT:    st.w $s2, $sp, 48
+; LA32-NEXT:    st.w $s1, $sp, 44
+; LA32-NEXT:    addi.w $a0, $sp, 56
+; LA32-NEXT:    addi.w $a1, $sp, 40
+; LA32-NEXT:    st.w $s0, $sp, 40
+; LA32-NEXT:    bl sinl
+; LA32-NEXT:    st.w $s3, $sp, 20
+; LA32-NEXT:    st.w $s2, $sp, 16
+; LA32-NEXT:    st.w $s1, $sp, 12
+; LA32-NEXT:    addi.w $a0, $sp, 24
+; LA32-NEXT:    addi.w $a1, $sp, 8
+; LA32-NEXT:    st.w $s0, $sp, 8
+; LA32-NEXT:    bl cosl
+; LA32-NEXT:    ld.w $a0, $sp, 56
+; LA32-NEXT:    ld.w $a1, $sp, 60
+; LA32-NEXT:    ld.w $a2, $sp, 64
+; LA32-NEXT:    ld.w $a3, $sp, 68
+; LA32-NEXT:    ld.w $a4, $sp, 36
+; LA32-NEXT:    ld.w $a5, $sp, 32
+; LA32-NEXT:    ld.w $a6, $sp, 28
+; LA32-NEXT:    ld.w $a7, $sp, 24
+; LA32-NEXT:    st.w $a4, $fp, 28
+; LA32-NEXT:    st.w $a5, $fp, 24
+; LA32-NEXT:    st.w $a6, $fp, 20
+; LA32-NEXT:    st.w $a7, $fp, 16
+; LA32-NEXT:    st.w $a3, $fp, 12
+; LA32-NEXT:    st.w $a2, $fp, 8
+; LA32-NEXT:    st.w $a1, $fp, 4
+; LA32-NEXT:    st.w $a0, $fp, 0
+; LA32-NEXT:    ld.w $s3, $sp, 72 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s2, $sp, 76 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s1, $sp, 80 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s0, $sp, 84 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 88 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 92 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 96
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_f128:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -48
+; LA64-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 32 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s0, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s1, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s2, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s3, $sp, 0 # 8-byte Folded Spill
+; LA64-NEXT:    move $fp, $a2
+; LA64-NEXT:    move $s0, $a1
+; LA64-NEXT:    move $s1, $a0
+; LA64-NEXT:    move $a0, $a1
+; LA64-NEXT:    move $a1, $a2
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    move $s2, $a0
+; LA64-NEXT:    move $s3, $a1
+; LA64-NEXT:    move $a0, $s0
+; LA64-NEXT:    move $a1, $fp
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    st.d $a1, $s1, 24
+; LA64-NEXT:    st.d $a0, $s1, 16
+; LA64-NEXT:    st.d $s3, $s1, 8
+; LA64-NEXT:    st.d $s2, $s1, 0
+; LA64-NEXT:    ld.d $s3, $sp, 0 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s2, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s1, $sp, 16 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s0, $sp, 24 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $fp, $sp, 32 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 48
+; LA64-NEXT:    ret
+  %result = call { fp128, fp128 } @llvm.sincos.f128(fp128 %a)
+  ret { fp128, fp128 } %result
+}
+
+define { <2 x fp128>, <2 x fp128> } @test_sincos_v2f128(<2 x fp128> %a) #0 {
+; LA32-LABEL: test_sincos_v2f128:
+; LA32:       # %bb.0:
+; LA32-NEXT:    addi.w $sp, $sp, -176
+; LA32-NEXT:    st.w $ra, $sp, 172 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 168 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s0, $sp, 164 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s1, $sp, 160 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s2, $sp, 156 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s3, $sp, 152 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s4, $sp, 148 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s5, $sp, 144 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s6, $sp, 140 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $s7, $sp, 136 # 4-byte Folded Spill
+; LA32-NEXT:    ld.w $s0, $a1, 16
+; LA32-NEXT:    ld.w $s1, $a1, 20
+; LA32-NEXT:    ld.w $s2, $a1, 24
+; LA32-NEXT:    ld.w $s3, $a1, 28
+; LA32-NEXT:    ld.w $s4, $a1, 0
+; LA32-NEXT:    ld.w $s5, $a1, 4
+; LA32-NEXT:    ld.w $s6, $a1, 8
+; LA32-NEXT:    ld.w $s7, $a1, 12
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    st.w $s7, $sp, 52
+; LA32-NEXT:    st.w $s6, $sp, 48
+; LA32-NEXT:    st.w $s5, $sp, 44
+; LA32-NEXT:    addi.w $a0, $sp, 56
+; LA32-NEXT:    addi.w $a1, $sp, 40
+; LA32-NEXT:    st.w $s4, $sp, 40
+; LA32-NEXT:    bl sinl
+; LA32-NEXT:    st.w $s3, $sp, 116
+; LA32-NEXT:    st.w $s2, $sp, 112
+; LA32-NEXT:    st.w $s1, $sp, 108
+; LA32-NEXT:    addi.w $a0, $sp, 120
+; LA32-NEXT:    addi.w $a1, $sp, 104
+; LA32-NEXT:    st.w $s0, $sp, 104
+; LA32-NEXT:    bl sinl
+; LA32-NEXT:    st.w $s7, $sp, 20
+; LA32-NEXT:    st.w $s6, $sp, 16
+; LA32-NEXT:    st.w $s5, $sp, 12
+; LA32-NEXT:    addi.w $a0, $sp, 24
+; LA32-NEXT:    addi.w $a1, $sp, 8
+; LA32-NEXT:    st.w $s4, $sp, 8
+; LA32-NEXT:    bl cosl
+; LA32-NEXT:    st.w $s3, $sp, 84
+; LA32-NEXT:    st.w $s2, $sp, 80
+; LA32-NEXT:    st.w $s1, $sp, 76
+; LA32-NEXT:    addi.w $a0, $sp, 88
+; LA32-NEXT:    addi.w $a1, $sp, 72
+; LA32-NEXT:    st.w $s0, $sp, 72
+; LA32-NEXT:    bl cosl
+; LA32-NEXT:    ld.w $a0, $sp, 56
+; LA32-NEXT:    ld.w $a1, $sp, 60
+; LA32-NEXT:    ld.w $a2, $sp, 64
+; LA32-NEXT:    ld.w $a3, $sp, 68
+; LA32-NEXT:    ld.w $a4, $sp, 120
+; LA32-NEXT:    ld.w $a5, $sp, 124
+; LA32-NEXT:    ld.w $a6, $sp, 128
+; LA32-NEXT:    ld.w $a7, $sp, 132
+; LA32-NEXT:    ld.w $t0, $sp, 24
+; LA32-NEXT:    ld.w $t1, $sp, 28
+; LA32-NEXT:    ld.w $t2, $sp, 32
+; LA32-NEXT:    ld.w $t3, $sp, 36
+; LA32-NEXT:    ld.w $t4, $sp, 100
+; LA32-NEXT:    ld.w $t5, $sp, 96
+; LA32-NEXT:    ld.w $t6, $sp, 92
+; LA32-NEXT:    ld.w $t7, $sp, 88
+; LA32-NEXT:    st.w $t4, $fp, 60
+; LA32-NEXT:    st.w $t5, $fp, 56
+; LA32-NEXT:    st.w $t6, $fp, 52
+; LA32-NEXT:    st.w $t7, $fp, 48
+; LA32-NEXT:    st.w $t3, $fp, 44
+; LA32-NEXT:    st.w $t2, $fp, 40
+; LA32-NEXT:    st.w $t1, $fp, 36
+; LA32-NEXT:    st.w $t0, $fp, 32
+; LA32-NEXT:    st.w $a7, $fp, 28
+; LA32-NEXT:    st.w $a6, $fp, 24
+; LA32-NEXT:    st.w $a5, $fp, 20
+; LA32-NEXT:    st.w $a4, $fp, 16
+; LA32-NEXT:    st.w $a3, $fp, 12
+; LA32-NEXT:    st.w $a2, $fp, 8
+; LA32-NEXT:    st.w $a1, $fp, 4
+; LA32-NEXT:    st.w $a0, $fp, 0
+; LA32-NEXT:    ld.w $s7, $sp, 136 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s6, $sp, 140 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s5, $sp, 144 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s4, $sp, 148 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s3, $sp, 152 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s2, $sp, 156 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s1, $sp, 160 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $s0, $sp, 164 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $fp, $sp, 168 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 172 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 176
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: test_sincos_v2f128:
+; LA64:       # %bb.0:
+; LA64-NEXT:    addi.d $sp, $sp, -80
+; LA64-NEXT:    st.d $ra, $sp, 72 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 64 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s0, $sp, 56 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s1, $sp, 48 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s2, $sp, 40 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s3, $sp, 32 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s4, $sp, 24 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s5, $sp, 16 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s6, $sp, 8 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $s7, $sp, 0 # 8-byte Folded Spill
+; LA64-NEXT:    ld.d $fp, $a1, 16
+; LA64-NEXT:    ld.d $s0, $a1, 24
+; LA64-NEXT:    ld.d $s1, $a1, 0
+; LA64-NEXT:    ld.d $s2, $a1, 8
+; LA64-NEXT:    move $s3, $a0
+; LA64-NEXT:    move $a0, $s1
+; LA64-NEXT:    move $a1, $s2
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    move $s4, $a0
+; LA64-NEXT:    move $s5, $a1
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    move $a1, $s0
+; LA64-NEXT:    pcaddu18i $ra, %call36(sinl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    move $s6, $a0
+; LA64-NEXT:    move $s7, $a1
+; LA64-NEXT:    move $a0, $s1
+; LA64-NEXT:    move $a1, $s2
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    move $s1, $a0
+; LA64-NEXT:    move $s2, $a1
+; LA64-NEXT:    move $a0, $fp
+; LA64-NEXT:    move $a1, $s0
+; LA64-NEXT:    pcaddu18i $ra, %call36(cosl)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    st.d $a1, $s3, 56
+; LA64-NEXT:    st.d $a0, $s3, 48
+; LA64-NEXT:    st.d $s2, $s3, 40
+; LA64-NEXT:    st.d $s1, $s3, 32
+; LA64-NEXT:    st.d $s7, $s3, 24
+; LA64-NEXT:    st.d $s6, $s3, 16
+; LA64-NEXT:    st.d $s5, $s3, 8
+; LA64-NEXT:    st.d $s4, $s3, 0
+; LA64-NEXT:    ld.d $s7, $sp, 0 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s6, $sp, 8 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s5, $sp, 16 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s4, $sp, 24 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s3, $sp, 32 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s2, $sp, 40 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s1, $sp, 48 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $s0, $sp, 56 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $fp, $sp, 64 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 72 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 80
+; LA64-NEXT:    ret
+  %result = call { <2 x fp128>, <2 x fp128> } @llvm.sincos.v2f128(<2 x fp128> %a)
+  ret { <2 x fp128>, <2 x fp128> } %result
+}
+
+attributes #0 = { nounwind }