llvm/test/CodeGen/AArch64/sve2-min-max-clamp.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2p1 -mattr=+sve-b16b16 < %s | FileCheck %s

; Replace pattern min(max(v1,v2),v3) by clamp

define <vscale x 16 x i8> @uclampi8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: uclampi8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uclamp z0.b, z1.b, z2.b
; CHECK-NEXT:    ret
  %min = tail call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  %res = tail call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> %min, <vscale x 16 x i8> %c)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @uclampi16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: uclampi16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uclamp z0.h, z1.h, z2.h
; CHECK-NEXT:    ret
  %min = tail call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  %res = tail call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> %min, <vscale x 8 x i16> %c)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @uclampi32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: uclampi32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uclamp z0.s, z1.s, z2.s
; CHECK-NEXT:    ret
  %min = tail call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  %res = tail call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> %min, <vscale x 4 x i32> %c)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @uclampi64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: uclampi64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uclamp z0.d, z1.d, z2.d
; CHECK-NEXT:    ret
  %min = tail call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  %res = tail call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> %min, <vscale x 2 x i64> %c)
  ret <vscale x 2 x i64> %res
}

define <vscale x 16 x i8> @sclampi8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: sclampi8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sclamp z0.b, z1.b, z2.b
; CHECK-NEXT:    ret
  %min = tail call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  %res = tail call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> %min, <vscale x 16 x i8> %c)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @sclampi16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: sclampi16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sclamp z0.h, z1.h, z2.h
; CHECK-NEXT:    ret
  %min = tail call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  %res = tail call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> %min, <vscale x 8 x i16> %c)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @sclampi32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: sclampi32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sclamp z0.s, z1.s, z2.s
; CHECK-NEXT:    ret
  %min = tail call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  %res = tail call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> %min, <vscale x 4 x i32> %c)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @sclampi64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: sclampi64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sclamp z0.d, z1.d, z2.d
; CHECK-NEXT:    ret
  %min = tail call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  %res = tail call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> %min, <vscale x 2 x i64> %c)
  ret <vscale x 2 x i64> %res
}

define <vscale x 8 x bfloat> @fclampbf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b, <vscale x 8 x bfloat> %c) {
; CHECK-LABEL: fclampbf16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bfclamp z0.h, z1.h, z2.h
; CHECK-NEXT:    ret
  %min = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmaxnm.u.nxv8bf16(<vscale x 8 x i1> splat (i1 true), <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b)
  %res = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.fminnm.u.nxv8bf16(<vscale x 8 x i1> splat (i1 true), <vscale x 8 x bfloat> %min, <vscale x 8 x bfloat> %c)
  ret <vscale x 8 x bfloat> %res
}

define <vscale x 8 x half> @fclampf16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fclampf16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fclamp z0.h, z1.h, z2.h
; CHECK-NEXT:    ret
  %min = call <vscale x 8 x half> @llvm.maxnum.nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b)
  %res = call <vscale x 8 x half> @llvm.minnum.nxv8f16(<vscale x 8 x half> %min, <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %res
}

define <vscale x 4 x float> @fclampf32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fclampf32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fclamp z0.s, z1.s, z2.s
; CHECK-NEXT:    ret
  %min = tail call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b)
  %res = tail call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> %min, <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %res
}

define <vscale x 2 x double> @fclampf64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fclampf64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fclamp z0.d, z1.d, z2.d
; CHECK-NEXT:    ret
  %min = tail call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b)
  %res = tail call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> %min, <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %res
}

declare <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 8 x bfloat> @llvm.aarch64.sve.fmaxnm.u.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.fminnm.u.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half>   @llvm.maxnum.nxv8f16 (<vscale x 8 x half>,   <vscale x 8 x half>)
declare <vscale x 8 x half>   @llvm.minnum.nxv8f16 (<vscale x 8 x half>,   <vscale x 8 x half>)
declare <vscale x 4 x float>  @llvm.maxnum.nxv4f32 (<vscale x 4 x float>,  <vscale x 4 x float>)
declare <vscale x 4 x float>  @llvm.minnum.nxv4f32 (<vscale x 4 x float>,  <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.maxnum.nxv2f64 (<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x double> @llvm.minnum.nxv2f64 (<vscale x 2 x double>, <vscale x 2 x double>)