TheRock/compiler/amd-llvm/llvm/test/CodeGen/SystemZ/saturating-truncation.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5

; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z17 | FileCheck %s

declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>) #2
declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>) #2

define <16 x i8> @i16_signed(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: i16_signed:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpksh %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <8 x i16> %a, <8 x i16> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
  %1 = tail call <16 x i16> @llvm.smax.v16i16(<16 x i16> %0, <16 x i16> splat (i16 -128))
  %2 = tail call <16 x i16> @llvm.smin.v16i16(<16 x i16> %1, <16 x i16> splat (i16 127))
  %3 = trunc nsw <16 x i16> %2 to <16 x i8>
  ret <16 x i8> %3
  ret <16 x i8> %3
}

define <8 x i16> @i32_signed(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: i32_signed:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpksf %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <4 x i32> %a, <4 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %1 = tail call <8 x i32> @llvm.smax.v8i32(<8 x i32> %0, <8 x i32> splat (i32 -32768))
  %2 = tail call <8 x i32> @llvm.smin.v8i32(<8 x i32> %1, <8 x i32> splat (i32 32767))
  %3 = trunc nsw <8 x i32> %2 to <8 x i16>
  ret <8 x i16> %3
}

define <4 x i32> @i64_signed(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: i64_signed:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpksg %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <2 x i64> %a, <2 x i64> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = tail call <4 x i64> @llvm.smax.v4i64(<4 x i64> %0, <4 x i64> splat (i64 -2147483648))
  %2 = tail call <4 x i64> @llvm.smin.v4i64(<4 x i64> %1, <4 x i64> splat (i64 2147483647))
  %3 = trunc nsw <4 x i64> %2 to <4 x i32>
  ret <4 x i32> %3
}

define <4 x i32> @i64_signed_flipped(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: i64_signed_flipped:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpksg %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <2 x i64> %a, <2 x i64> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = tail call <4 x i64> @llvm.smin.v4i64(<4 x i64> splat (i64 2147483647), <4 x i64> %0)
  %2 = tail call <4 x i64> @llvm.smax.v4i64(<4 x i64> splat (i64 -2147483648), <4 x i64> %1)
  %3 = trunc nsw <4 x i64> %2 to <4 x i32>
  ret <4 x i32> %3
}

define <16 x i8> @i16_unsigned(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: i16_unsigned:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpklsh %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <8 x i16> %a, <8 x i16> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
  %1 = tail call <16 x i16> @llvm.umin.v16i16(<16 x i16> %0, <16 x i16> splat (i16 255))
  %2 = trunc nuw <16 x i16> %1 to <16 x i8>
  ret <16 x i8> %2
}

define <8 x i16> @i32_unsigned(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: i32_unsigned:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpklsf %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <4 x i32> %a, <4 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %1 = tail call <8 x i32> @llvm.umin.v8i32(<8 x i32> %0, <8 x i32> splat (i32 65535))
  %2 = trunc nsw <8 x i32> %1 to <8 x i16>
  ret <8 x i16> %2
}

define <4 x i32> @i64_unsigned(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: i64_unsigned:
; CHECK:       # %bb.0: # %bb2
; CHECK-NEXT:    vpklsg %v24, %v24, %v26
; CHECK-NEXT:    br %r14
bb2:
  %0 = shufflevector <2 x i64> %a, <2 x i64> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = tail call <4 x i64> @llvm.umin.v4i64(<4 x i64> %0, <4 x i64> splat (i64 4294967295))
  %2 = trunc nuw <4 x i64> %1 to <4 x i32>
  ret <4 x i32> %2
}