test/CodeGen/AArch64/sve-i1-add-reduce.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s

define i8 @uaddv_zexti8_nxv16i1(<vscale x 16 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv16i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.b
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 16 x i1> %v to <vscale x 16 x i8>
  %4 = tail call i8 @llvm.vector.reduce.add.nxv16i8(<vscale x 16 x i8> %3)
  ret i8 %4
}

define i8 @uaddv_zexti8_nxv8i1(<vscale x 8 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv8i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.h
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 8 x i1> %v to <vscale x 8 x i8>
  %4 = tail call i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8> %3)
  ret i8 %4
}

define i16 @uaddv_zexti16_nxv8i1(<vscale x 8 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv8i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.h
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 8 x i1> %v to <vscale x 8 x i16>
  %4 = tail call i16 @llvm.vector.reduce.add.nxv8i16(<vscale x 8 x i16> %3)
  ret i16 %4
}

define i8 @uaddv_zexti8_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv4i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.s
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i8>
  %4 = tail call i8 @llvm.vector.reduce.add.nxv4i8(<vscale x 4 x i8> %3)
  ret i8 %4
}

define i16 @uaddv_zexti16_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv4i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.s
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i16>
  %4 = tail call i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16> %3)
  ret i16 %4
}

define i32 @uaddv_zexti32_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti32_nxv4i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.s
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i32>
  %4 = tail call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %3)
  ret i32 %4
}

define i8 @uaddv_zexti8_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv2i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.d
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i8>
  %4 = tail call i8 @llvm.vector.reduce.add.nxv2i8(<vscale x 2 x i8> %3)
  ret i8 %4
}

define i16 @uaddv_zexti16_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv2i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.d
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i16>
  %4 = tail call i16 @llvm.vector.reduce.add.nxv2i16(<vscale x 2 x i16> %3)
  ret i16 %4
}

define i32 @uaddv_zexti32_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti32_nxv2i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.d
; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i32>
  %4 = tail call i32 @llvm.vector.reduce.add.nxv2i32(<vscale x 2 x i32> %3)
  ret i32 %4
}

define i64 @uaddv_zexti64_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti64_nxv2i1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cntp x0, p0, p0.d
; CHECK-NEXT:    ret
entry:
  %3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i64>
  %4 = tail call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> %3)
  ret i64 %4
}

declare i8 @llvm.vector.reduce.add.nxv16i8(<vscale x 16 x i8>)
declare i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8>)
declare i16 @llvm.vector.reduce.add.nxv8i16(<vscale x 8 x i16>)
declare i8 @llvm.vector.reduce.add.nxv4i8(<vscale x 4 x i8>)
declare i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16>)
declare i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32>)
declare i8 @llvm.vector.reduce.add.nxv2i8(<vscale x 2 x i8>)
declare i16 @llvm.vector.reduce.add.nxv2i16(<vscale x 2 x i16>)
declare i32 @llvm.vector.reduce.add.nxv2i32(<vscale x 2 x i32>)
declare i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64>)