llvm/llvm/test/CodeGen/AArch64/sve-splat-one-and-ptrue.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s

target triple = "aarch64-unknown-linux-gnu"

; Ensure that a no-op 'and' get removed with vector splat of 1 or ptrue with proper constant

define <vscale x 16 x i1> @fold_away_ptrue_and_ptrue() #0 {
; CHECK-LABEL: fold_away_ptrue_and_ptrue:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ret
  %1 = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
  %2 = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %1)
  %3 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %and = and <vscale x 16 x i1> %3, %2
  ret <vscale x 16 x i1> %and
}

define <vscale x 16 x i1> @fold_away_ptrue_and_splat_predicate() #0 {
; CHECK-LABEL: fold_away_ptrue_and_splat_predicate:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ret
  %1 = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> splat(i1 true))
  %2 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %and = and <vscale x 16 x i1> %1, %2
  ret <vscale x 16 x i1> %and
}

; Ensure that one AND operation remain for inactive lanes zeroing with 2 x i1 type (llvm.aarch64.sve.convert.to.svbool.nxv2i1).
define <vscale x 16 x i1> @fold_away_ptrue_and_convert_to() #0 {
; CHECK-LABEL: fold_away_ptrue_and_convert_to:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ptrue p1.d
; CHECK-NEXT:    and p0.b, p1/z, p1.b, p0.b
; CHECK-NEXT:    ret
  %1 = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
  %2 = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %1)
  %3 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %4 = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %3)
  %5 = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> %4)
  %and = and <vscale x 16 x i1> %5, %2
  ret <vscale x 16 x i1> %and
}

define <vscale x 16 x i1> @fold_away_two_similar() #0 {
; CHECK-LABEL: fold_away_two_similar:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.b
; CHECK-NEXT:    ret
  %1 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %2 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %and = and <vscale x 16 x i1> %1, %2
  ret <vscale x 16 x i1> %and
}

declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 immarg)

declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1>)

declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 immarg)

declare <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1>)

declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1>)


attributes #0 = { "target-features"="+sve" }