From d9ff90cc19c4d0714aca4e394784b21d29a0c8f1 Mon Sep 17 00:00:00 2001
From: yangzhaoxin <yangzhaoxin@loongson.cn>
Date: Sat, 11 Oct 2025 11:53:01 +0800
Subject: [PATCH] [LoongArch][NFC] Pre-commit tests for flog2

---
 .../CodeGen/LoongArch/ir-instruction/flog2.ll |  32 +++
 .../LoongArch/lasx/ir-instruction/flog2.ll    | 264 ++++++++++++++++++
 .../LoongArch/lsx/ir-instruction/flog2.ll     | 162 +++++++++++
 3 files changed, 458 insertions(+)
 create mode 100644 llvm/test/CodeGen/LoongArch/ir-instruction/flog2.ll
 create mode 100644 llvm/test/CodeGen/LoongArch/lasx/ir-instruction/flog2.ll
 create mode 100644 llvm/test/CodeGen/LoongArch/lsx/ir-instruction/flog2.ll

diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/flog2.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/flog2.ll
new file mode 100644
index 0000000000000..93fcd421e4bd7
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/ir-instruction/flog2.ll
@@ -0,0 +1,32 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --mtriple=loongarch32 --mattr=+d < %s | FileCheck %s --check-prefix=LA32
+; RUN: llc --mtriple=loongarch64 --mattr=+d < %s | FileCheck %s --check-prefix=LA64
+
+declare float @llvm.log2.f32(float)
+declare double @llvm.log2.f64(double)
+
+define float @flog2_s(float %x) nounwind {
+; LA32-LABEL: flog2_s:
+; LA32:       # %bb.0:
+; LA32-NEXT:    b log2f
+;
+; LA64-LABEL: flog2_s:
+; LA64:       # %bb.0:
+; LA64-NEXT:    pcaddu18i $t8, %call36(log2f)
+; LA64-NEXT:    jr $t8
+  %y = call float @llvm.log2.f32(float %x)
+  ret float %y
+}
+
+define double @flog2_d(double %x) nounwind {
+; LA32-LABEL: flog2_d:
+; LA32:       # %bb.0:
+; LA32-NEXT:    b log2
+;
+; LA64-LABEL: flog2_d:
+; LA64:       # %bb.0:
+; LA64-NEXT:    pcaddu18i $t8, %call36(log2)
+; LA64-NEXT:    jr $t8
+  %y = call double @llvm.log2.f64(double %x)
+  ret double %y
+}
diff --git a/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/flog2.ll b/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/flog2.ll
new file mode 100644
index 0000000000000..68f2e3ab488e1
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/flog2.ll
@@ -0,0 +1,264 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s --check-prefix=LA32
+; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s --check-prefix=LA64
+
+declare <8 x float> @llvm.log2.v8f32(<8 x float>)
+declare <4 x double> @llvm.log2.v4f64(<4 x double>)
+
+define void @flog2_v8f32(ptr %res, ptr %a) nounwind {
+; LA32-LABEL: flog2_v8f32:
+; LA32:       # %bb.0: # %entry
+; LA32-NEXT:    addi.w $sp, $sp, -128
+; LA32-NEXT:    st.w $ra, $sp, 124 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 120 # 4-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $a1, 0
+; LA32-NEXT:    xvst $xr0, $sp, 80 # 32-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 5
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 48 # 16-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 4
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $xr0
+; LA32-NEXT:    vld $vr1, $sp, 48 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA32-NEXT:    xvst $xr0, $sp, 48 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 6
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    xvld $xr1, $sp, 48 # 32-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA32-NEXT:    xvst $xr1, $sp, 48 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 7
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    xvld $xr1, $sp, 48 # 32-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA32-NEXT:    xvst $xr1, $sp, 48 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 1
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 0
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $xr0
+; LA32-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA32-NEXT:    xvst $xr0, $sp, 16 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 2
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    xvld $xr1, $sp, 16 # 32-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA32-NEXT:    xvst $xr1, $sp, 16 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.w $xr0, $xr0, 3
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    xvld $xr1, $sp, 16 # 32-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA32-NEXT:    xvld $xr0, $sp, 48 # 32-byte Folded Reload
+; LA32-NEXT:    xvpermi.q $xr1, $xr0, 2
+; LA32-NEXT:    xvst $xr1, $fp, 0
+; LA32-NEXT:    ld.w $fp, $sp, 120 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 124 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 128
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: flog2_v8f32:
+; LA64:       # %bb.0: # %entry
+; LA64-NEXT:    addi.d $sp, $sp, -128
+; LA64-NEXT:    st.d $ra, $sp, 120 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 112 # 8-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $a1, 0
+; LA64-NEXT:    xvst $xr0, $sp, 80 # 32-byte Folded Spill
+; LA64-NEXT:    move $fp, $a0
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 5
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 48 # 16-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 4
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $xr0
+; LA64-NEXT:    vld $vr1, $sp, 48 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA64-NEXT:    xvst $xr0, $sp, 48 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 6
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    xvld $xr1, $sp, 48 # 32-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA64-NEXT:    xvst $xr1, $sp, 48 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 7
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    xvld $xr1, $sp, 48 # 32-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA64-NEXT:    xvst $xr1, $sp, 48 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 1
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; 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:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $xr0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA64-NEXT:    xvst $xr0, $sp, 16 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 2
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    xvld $xr1, $sp, 16 # 32-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA64-NEXT:    xvst $xr1, $sp, 16 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 80 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.w $xr0, $xr0, 3
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    xvld $xr1, $sp, 16 # 32-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA64-NEXT:    xvld $xr0, $sp, 48 # 32-byte Folded Reload
+; LA64-NEXT:    xvpermi.q $xr1, $xr0, 2
+; LA64-NEXT:    xvst $xr1, $fp, 0
+; LA64-NEXT:    ld.d $fp, $sp, 112 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 120 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 128
+; LA64-NEXT:    ret
+entry:
+  %v = load <8 x float>, ptr %a
+  %r = call <8 x float> @llvm.log2.v8f32(<8 x float> %v)
+  store <8 x float> %r, ptr %res
+  ret void
+}
+
+define void @flog2_v4f64(ptr %res, ptr %a) nounwind {
+; LA32-LABEL: flog2_v4f64:
+; LA32:       # %bb.0: # %entry
+; LA32-NEXT:    addi.w $sp, $sp, -112
+; LA32-NEXT:    st.w $ra, $sp, 108 # 4-byte Folded Spill
+; LA32-NEXT:    st.w $fp, $sp, 104 # 4-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $a1, 0
+; LA32-NEXT:    xvst $xr0, $sp, 64 # 32-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    xvpickve.d $xr0, $xr0, 3
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.d $xr0, $xr0, 2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $xr0
+; LA32-NEXT:    vld $vr1, $sp, 32 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA32-NEXT:    xvst $xr0, $sp, 32 # 32-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.d $xr0, $xr0, 1
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA32-NEXT:    xvpickve.d $xr0, $xr0, 0
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $xr0
+; LA32-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA32-NEXT:    xvld $xr1, $sp, 32 # 32-byte Folded Reload
+; LA32-NEXT:    xvpermi.q $xr0, $xr1, 2
+; LA32-NEXT:    xvst $xr0, $fp, 0
+; LA32-NEXT:    ld.w $fp, $sp, 104 # 4-byte Folded Reload
+; LA32-NEXT:    ld.w $ra, $sp, 108 # 4-byte Folded Reload
+; LA32-NEXT:    addi.w $sp, $sp, 112
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: flog2_v4f64:
+; LA64:       # %bb.0: # %entry
+; LA64-NEXT:    addi.d $sp, $sp, -112
+; LA64-NEXT:    st.d $ra, $sp, 104 # 8-byte Folded Spill
+; LA64-NEXT:    st.d $fp, $sp, 96 # 8-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $a1, 0
+; LA64-NEXT:    xvst $xr0, $sp, 64 # 32-byte Folded Spill
+; LA64-NEXT:    move $fp, $a0
+; LA64-NEXT:    xvpickve.d $xr0, $xr0, 3
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 32 # 16-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.d $xr0, $xr0, 2
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $xr0
+; LA64-NEXT:    vld $vr1, $sp, 32 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA64-NEXT:    xvst $xr0, $sp, 32 # 32-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.d $xr0, $xr0, 1
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    xvld $xr0, $sp, 64 # 32-byte Folded Reload
+; LA64-NEXT:    xvpickve.d $xr0, $xr0, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $xr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $xr0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA64-NEXT:    xvld $xr1, $sp, 32 # 32-byte Folded Reload
+; LA64-NEXT:    xvpermi.q $xr0, $xr1, 2
+; LA64-NEXT:    xvst $xr0, $fp, 0
+; LA64-NEXT:    ld.d $fp, $sp, 96 # 8-byte Folded Reload
+; LA64-NEXT:    ld.d $ra, $sp, 104 # 8-byte Folded Reload
+; LA64-NEXT:    addi.d $sp, $sp, 112
+; LA64-NEXT:    ret
+entry:
+  %v = load <4 x double>, ptr %a
+  %r = call <4 x double> @llvm.log2.v4f64(<4 x double> %v)
+  store <4 x double> %r, ptr %res
+  ret void
+}
diff --git a/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/flog2.ll b/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/flog2.ll
new file mode 100644
index 0000000000000..e5e75ec617b51
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/flog2.ll
@@ -0,0 +1,162 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s --check-prefix=LA32
+; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s --check-prefix=LA64
+
+declare <4 x float> @llvm.log2.v4f32(<4 x float>)
+declare <2 x double> @llvm.log2.v2f64(<2 x double>)
+
+define void @flog2_v4f32(ptr %res, ptr %a) nounwind {
+; LA32-LABEL: flog2_v4f32:
+; LA32:       # %bb.0: # %entry
+; 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:    vld $vr0, $a1, 0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 2
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA32-NEXT:    vst $vr1, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.w $vr0, $vr0, 3
+; LA32-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA32-NEXT:    bl log2f
+; LA32-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA32-NEXT:    vst $vr1, $fp, 0
+; 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: flog2_v4f32:
+; LA64:       # %bb.0: # %entry
+; 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:    vld $vr0, $a1, 0
+; LA64-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA64-NEXT:    move $fp, $a0
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 1
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr0, $vr1, 16
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 2
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 32
+; LA64-NEXT:    vst $vr1, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    vld $vr0, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vreplvei.w $vr0, $vr0, 3
+; LA64-NEXT:    # kill: def $f0 killed $f0 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2f)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0 killed $f0 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 0 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.w $vr1, $vr0, 48
+; LA64-NEXT:    vst $vr1, $fp, 0
+; 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
+entry:
+  %v = load <4 x float>, ptr %a
+  %r = call <4 x float> @llvm.log2.v4f32(<4 x float> %v)
+  store <4 x float> %r, ptr %res
+  ret void
+}
+
+define void @flog2_v2f64(ptr %res, ptr %a) nounwind {
+; LA32-LABEL: flog2_v2f64:
+; LA32:       # %bb.0: # %entry
+; 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:    vld $vr0, $a1, 0
+; LA32-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA32-NEXT:    move $fp, $a0
+; LA32-NEXT:    vreplvei.d $vr0, $vr0, 1
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vst $vr0, $sp, 16 # 16-byte Folded Spill
+; LA32-NEXT:    vld $vr0, $sp, 0 # 16-byte Folded Reload
+; LA32-NEXT:    vreplvei.d $vr0, $vr0, 0
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA32-NEXT:    bl log2
+; LA32-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA32-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA32-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA32-NEXT:    vst $vr0, $fp, 0
+; 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: flog2_v2f64:
+; LA64:       # %bb.0: # %entry
+; 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:    vld $vr0, $a1, 0
+; LA64-NEXT:    vst $vr0, $sp, 0 # 16-byte Folded Spill
+; LA64-NEXT:    move $fp, $a0
+; LA64-NEXT:    vreplvei.d $vr0, $vr0, 1
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 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.d $vr0, $vr0, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 killed $vr0
+; LA64-NEXT:    pcaddu18i $ra, %call36(log2)
+; LA64-NEXT:    jirl $ra, $ra, 0
+; LA64-NEXT:    # kill: def $f0_64 killed $f0_64 def $vr0
+; LA64-NEXT:    vld $vr1, $sp, 16 # 16-byte Folded Reload
+; LA64-NEXT:    vextrins.d $vr0, $vr1, 16
+; LA64-NEXT:    vst $vr0, $fp, 0
+; 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
+entry:
+  %v = load <2 x double>, ptr %a
+  %r = call <2 x double> @llvm.log2.v2f64(<2 x double> %v)
+  store <2 x double> %r, ptr %res
+  ret void
+}