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

; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64le-unknown-linux-gnu \
; RUN:   -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWER10-LE

; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64-ibm-aix-xcoff \
; RUN:   -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWER10-BE

; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc-ibm-aix-xcoff \
; RUN:   -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWER3210-BE

; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64le-unknown-linux-gnu \
; RUN:   -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWER9-LE

; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64-ibm-aix-xcoff \
; RUN:   -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWER9-BE

; Test VSRO + VSR peephole optimization to VSRQ on Power10+
; This should combine consecutive VSRO (Vector Shift Right Octet) and VSR (Vector Shift Right)
; instructions using the same shift amount into a single VSRQ (Vector Shift Right Quadword)
; instruction when targeting Power10 or later processors.
declare <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32>, <4 x i32>)
declare <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32>, <4 x i32>)

define <16 x i8> @shiftright128_v16i8(<16 x i8> %in, i8 zeroext %sh) {
; POWER10-LE-LABEL: shiftright128_v16i8:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vsrq v2, v2, v3
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: shiftright128_v16i8:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vsrq v2, v2, v3
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: shiftright128_v16i8:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vsrq v2, v2, v3
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: shiftright128_v16i8:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v2, v2, v3
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: shiftright128_v16i8:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v2, v2, v3
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %in to <4 x i32>
  %1 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %0, <4 x i32> %1)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %2, <4 x i32> %1)
  %4 = bitcast <4 x i32> %3 to <16 x i8>
  ret <16 x i8> %4
}

define <4 x i32> @shiftright128_v4i32(<4 x i32> %in, i8 zeroext %sh) {
; POWER10-LE-LABEL: shiftright128_v4i32:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vsrq v2, v2, v3
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: shiftright128_v4i32:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vsrq v2, v2, v3
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: shiftright128_v4i32:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vsrq v2, v2, v3
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: shiftright128_v4i32:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v2, v2, v3
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: shiftright128_v4i32:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v2, v2, v3
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %1 = tail call  <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %in, <4 x i32> %0)
  %2 = tail call  <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %1, <4 x i32> %0)
  ret <4 x i32> %2
}

define <2 x i64> @shiftright128_v2i64(<2 x i64> %in, i8 zeroext %sh) {
; POWER10-LE-LABEL: shiftright128_v2i64:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vsrq v2, v2, v3
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: shiftright128_v2i64:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vsrq v2, v2, v3
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: shiftright128_v2i64:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vsrq v2, v2, v3
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: shiftright128_v2i64:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v2, v2, v3
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: shiftright128_v2i64:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v2, v2, v3
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <2 x i64> %in to <4 x i32>
  %1 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %0, <4 x i32> %1)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %2, <4 x i32> %1)
  %4 = bitcast <4 x i32> %3 to <2 x i64>
  ret <2 x i64> %4
}

define <8 x i16> @shiftright128_v8i16(<8 x i16> %in, i8 zeroext %sh) {
; POWER10-LE-LABEL: shiftright128_v8i16:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vsrq v2, v2, v3
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: shiftright128_v8i16:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vsrq v2, v2, v3
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: shiftright128_v8i16:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vsrq v2, v2, v3
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: shiftright128_v8i16:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v2, v2, v3
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: shiftright128_v8i16:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v2, v2, v3
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <8 x i16> %in to <4 x i32>
  %1 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %0, <4 x i32> %1)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %2, <4 x i32> %1)
  %4 = bitcast <4 x i32> %3 to <8 x i16>
  ret <8 x i16> %4
}

; Test case with different vectors (should not optimize - different shift amount registers)
define <16 x i8> @no_optimization_different_shifts(<16 x i8> %in, i8 zeroext %sh1, i8 zeroext %sh2)  {
; POWER10-LE-LABEL: no_optimization_different_shifts:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    mtvsrd v4, r6
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vspltb v4, v4, 7
; POWER10-LE-NEXT:    vsro v2, v2, v3
; POWER10-LE-NEXT:    vsr v2, v2, v4
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: no_optimization_different_shifts:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    mtvsrwz v4, r4
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vspltb v4, v4, 7
; POWER10-BE-NEXT:    vsro v2, v2, v3
; POWER10-BE-NEXT:    vsr v2, v2, v4
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: no_optimization_different_shifts:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    mtvsrwz v4, r4
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vspltb v4, v4, 7
; POWER3210-BE-NEXT:    vsro v2, v2, v3
; POWER3210-BE-NEXT:    vsr v2, v2, v4
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: no_optimization_different_shifts:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    mtvsrd v4, r6
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vspltb v4, v4, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v2, v2, v4
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: no_optimization_different_shifts:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    mtvsrwz v4, r4
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vspltb v4, v4, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v2, v2, v4
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh1, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %splat.splatinsert.i2 = insertelement <16 x i8> poison, i8 %sh2, i64 0
  %splat.splat.i2 = shufflevector <16 x i8> %splat.splatinsert.i2, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %in to <4 x i32>
  %1 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %2 = bitcast <16 x i8> %splat.splat.i2 to <4 x i32>
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %0, <4 x i32> %1)
  %4 = tail call <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %3, <4 x i32> %2)
  %5 = bitcast <4 x i32> %4 to <16 x i8>
  ret <16 x i8> %5
}

; Test case with multiple uses of VSRO result (should not optimize)
define <16 x i8> @no_optimization_multiple_uses(<16 x i8> %in, i8 zeroext %sh)  {
; POWER10-LE-LABEL: no_optimization_multiple_uses:
; POWER10-LE:       # %bb.0: # %entry
; POWER10-LE-NEXT:    mtvsrd v3, r5
; POWER10-LE-NEXT:    vspltb v3, v3, 7
; POWER10-LE-NEXT:    vsro v2, v2, v3
; POWER10-LE-NEXT:    vsr v3, v2, v3
; POWER10-LE-NEXT:    vaddubm v2, v2, v3
; POWER10-LE-NEXT:    blr
;
; POWER10-BE-LABEL: no_optimization_multiple_uses:
; POWER10-BE:       # %bb.0: # %entry
; POWER10-BE-NEXT:    mtvsrwz v3, r3
; POWER10-BE-NEXT:    vspltb v3, v3, 7
; POWER10-BE-NEXT:    vsro v2, v2, v3
; POWER10-BE-NEXT:    vsr v3, v2, v3
; POWER10-BE-NEXT:    vaddubm v2, v2, v3
; POWER10-BE-NEXT:    blr
;
; POWER3210-BE-LABEL: no_optimization_multiple_uses:
; POWER3210-BE:       # %bb.0: # %entry
; POWER3210-BE-NEXT:    mtvsrwz v3, r3
; POWER3210-BE-NEXT:    vspltb v3, v3, 7
; POWER3210-BE-NEXT:    vsro v2, v2, v3
; POWER3210-BE-NEXT:    vsr v3, v2, v3
; POWER3210-BE-NEXT:    vaddubm v2, v2, v3
; POWER3210-BE-NEXT:    blr
;
; POWER9-LE-LABEL: no_optimization_multiple_uses:
; POWER9-LE:       # %bb.0: # %entry
; POWER9-LE-NEXT:    mtvsrd v3, r5
; POWER9-LE-NEXT:    vspltb v3, v3, 7
; POWER9-LE-NEXT:    vsro v2, v2, v3
; POWER9-LE-NEXT:    vsr v3, v2, v3
; POWER9-LE-NEXT:    vaddubm v2, v2, v3
; POWER9-LE-NEXT:    blr
;
; POWER9-BE-LABEL: no_optimization_multiple_uses:
; POWER9-BE:       # %bb.0: # %entry
; POWER9-BE-NEXT:    mtvsrwz v3, r3
; POWER9-BE-NEXT:    vspltb v3, v3, 7
; POWER9-BE-NEXT:    vsro v2, v2, v3
; POWER9-BE-NEXT:    vsr v3, v2, v3
; POWER9-BE-NEXT:    vaddubm v2, v2, v3
; POWER9-BE-NEXT:    blr
entry:
  %splat.splatinsert.i = insertelement <16 x i8> poison, i8 %sh, i64 0
  %splat.splat.i = shufflevector <16 x i8> %splat.splatinsert.i, <16 x i8> poison, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %in to <4 x i32>
  %1 = bitcast <16 x i8> %splat.splat.i to <4 x i32>
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsro(<4 x i32> %0, <4 x i32> %1)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsr(<4 x i32> %2, <4 x i32> %1)
  %4 = bitcast <4 x i32> %3 to <16 x i8>
  %5 = bitcast <4 x i32> %2 to <16 x i8>
  %6 = add <16 x i8> %5, %4
  ret <16 x i8> %6
}