test/CodeGen/AArch64/sve-saturating-arith.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64 -mattr=+sve -verify-machineinstrs %s -o - | FileCheck %s
; RUN: llc -mtriple=aarch64 -mattr=+sve -aarch64-enable-gisel-sve=1 -global-isel -global-isel-abort=2 -verify-machineinstrs %s -o - 2>&1 | FileCheck %s

; SQADD
define <vscale x 16 x i8> @sqadd_i8_low(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sqadd_i8_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqadd z0.b, z0.b, z1.b
; CHECK-NEXT:    ret
  %res =  call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @sqadd_i16_low(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sqadd_i16_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqadd z0.h, z0.h, z1.h
; CHECK-NEXT:    ret
  %res =  call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @sqadd_i32_low(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sqadd_i32_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqadd z0.s, z0.s, z1.s
; CHECK-NEXT:    ret
  %res =  call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @sqadd_i64_low(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sqadd_i64_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqadd z0.d, z0.d, z1.d
; CHECK-NEXT:    ret
  %res =  call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %res
}

; UQADD
define <vscale x 16 x i8> @uqadd_i8_low(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: uqadd_i8_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqadd z0.b, z0.b, z1.b
; CHECK-NEXT:    ret
  %res =  call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @uqadd_i16_low(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: uqadd_i16_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqadd z0.h, z0.h, z1.h
; CHECK-NEXT:    ret
  %res =  call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @uqadd_i32_low(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: uqadd_i32_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqadd z0.s, z0.s, z1.s
; CHECK-NEXT:    ret
  %res =  call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @uqadd_i64_low(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: uqadd_i64_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqadd z0.d, z0.d, z1.d
; CHECK-NEXT:    ret
  %res =  call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %res
}

; SQSUB
define <vscale x 16 x i8> @sqsub_i8_low(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sqsub_i8_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqsub z0.b, z0.b, z1.b
; CHECK-NEXT:    ret
  %res =  call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @sqsub_i16_low(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sqsub_i16_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqsub z0.h, z0.h, z1.h
; CHECK-NEXT:    ret
  %res =  call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @sqsub_i32_low(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sqsub_i32_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqsub z0.s, z0.s, z1.s
; CHECK-NEXT:    ret
  %res =  call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @sqsub_i64_low(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sqsub_i64_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sqsub z0.d, z0.d, z1.d
; CHECK-NEXT:    ret
  %res =  call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %res
}

; UQSUB
define <vscale x 16 x i8> @uqsub_i8_low(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: uqsub_i8_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqsub z0.b, z0.b, z1.b
; CHECK-NEXT:    ret
  %res =  call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @uqsub_i16_low(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: uqsub_i16_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqsub z0.h, z0.h, z1.h
; CHECK-NEXT:    ret
  %res =  call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @uqsub_i32_low(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: uqsub_i32_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqsub z0.s, z0.s, z1.s
; CHECK-NEXT:    ret
  %res =  call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @uqsub_i64_low(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: uqsub_i64_low:
; CHECK:       // %bb.0:
; CHECK-NEXT:    uqsub z0.d, z0.d, z1.d
; CHECK-NEXT:    ret
  %res =  call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %res
}

declare <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)