; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -dse -enable-dse-memoryssa=false -enable-dse-partial-store-merging -S < %s | FileCheck %s
target datalayout = "E-m:e-i64:64-i128:128-n32:64-S128"

define void @byte_by_byte_replacement(i32 *%ptr) {
; CHECK-LABEL: @byte_by_byte_replacement(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store i32 151653132, i32* [[PTR:%.*]]
; CHECK-NEXT:    ret void
;
entry:
  ;; This store's value should be modified as it should be better to use one
  ;; larger store than several smaller ones.
  ;; store will turn into 0x090A0B0C == 151653132
  store i32 305419896, i32* %ptr  ; 0x12345678
  %bptr = bitcast i32* %ptr to i8*
  %bptr1 = getelementptr inbounds i8, i8* %bptr, i64 1
  %bptr2 = getelementptr inbounds i8, i8* %bptr, i64 2
  %bptr3 = getelementptr inbounds i8, i8* %bptr, i64 3

  ;; We should be able to merge these four stores with the i32 above
  ; value (and bytes) stored before  ; 0x12345678
  store i8 9, i8* %bptr              ;   09
  store i8 10, i8* %bptr1            ;     0A
  store i8 11, i8* %bptr2            ;       0B
  store i8 12, i8* %bptr3            ;         0C
  ;                                    0x090A0B0C

  ret void
}

define void @word_replacement(i64 *%ptr) {
; CHECK-LABEL: @word_replacement(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store i64 72638273700655232, i64* [[PTR:%.*]]
; CHECK-NEXT:    ret void
;
entry:
  store i64 72623859790382856, i64* %ptr  ; 0x0102030405060708

  %wptr = bitcast i64* %ptr to i16*
  %wptr1 = getelementptr inbounds i16, i16* %wptr, i64 1
  %wptr3 = getelementptr inbounds i16, i16* %wptr, i64 3

  ;; We should be able to merge these two stores with the i64 one above
  ; value (and bytes) stored before  ; 0x0102030405060708
  store i16  4128, i16* %wptr1       ;       1020
  store i16 28800, i16* %wptr3       ;               7080
  ;                                    0x0102102005067080

  ret void
}


define void @differently_sized_replacements(i64 *%ptr) {
; CHECK-LABEL: @differently_sized_replacements(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store i64 289077004501059343, i64* [[PTR:%.*]]
; CHECK-NEXT:    ret void
;
entry:
  store i64 579005069656919567, i64* %ptr  ; 0x08090a0b0c0d0e0f

  %bptr = bitcast i64* %ptr to i8*
  %bptr6 = getelementptr inbounds i8, i8* %bptr, i64 6
  %wptr = bitcast i64* %ptr to i16*
  %wptr2 = getelementptr inbounds i16, i16* %wptr, i64 2
  %dptr = bitcast i64* %ptr to i32*

  ;; We should be able to merge all these stores with the i64 one above
  ; value (and bytes) stored before  ; 0x08090a0b0c0d0e0f
  store i8         7, i8*  %bptr6    ;               07
  store i16     1541, i16* %wptr2    ;           0605
  store i32 67305985, i32* %dptr     ;   04030201
  ;                                    0x040302010605070f
  ret void
}


define void @multiple_replacements_to_same_byte(i64 *%ptr) {
; CHECK-LABEL: @multiple_replacements_to_same_byte(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store i64 289077004602248719, i64* [[PTR:%.*]]
; CHECK-NEXT:    ret void
;
entry:
  store i64 579005069656919567, i64* %ptr  ; 0x08090a0b0c0d0e0f

  %bptr = bitcast i64* %ptr to i8*
  %bptr3 = getelementptr inbounds i8, i8* %bptr, i64 3
  %wptr = bitcast i64* %ptr to i16*
  %wptr1 = getelementptr inbounds i16, i16* %wptr, i64 1
  %dptr = bitcast i64* %ptr to i32*

  ;; We should be able to merge all these stores with the i64 one above
  ; value (and bytes) stored before  ; 0x08090a0b0c0d0e0f
  store i8         7, i8*  %bptr3    ;         07
  store i16     1541, i16* %wptr1    ;       0605
  store i32 67305985, i32* %dptr     ;   04030201
  ;                                    0x040302010c0d0e0f
  ret void
}

define void @merged_merges(i64 *%ptr) {
; CHECK-LABEL: @merged_merges(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    store i64 289081428418563599, i64* [[PTR:%.*]]
; CHECK-NEXT:    ret void
;
entry:
  store i64 579005069656919567, i64* %ptr  ; 0x08090a0b0c0d0e0f

  %bptr = bitcast i64* %ptr to i8*
  %bptr3 = getelementptr inbounds i8, i8* %bptr, i64 3
  %wptr = bitcast i64* %ptr to i16*
  %wptr1 = getelementptr inbounds i16, i16* %wptr, i64 1
  %dptr = bitcast i64* %ptr to i32*

  ;; We should be able to merge all these stores with the i64 one above
  ; value (not bytes) stored before  ; 0x08090a0b0c0d0e0f
  store i32 67305985, i32* %dptr     ;   04030201
  store i16     1541, i16* %wptr1    ;       0605
  store i8         7, i8*  %bptr3    ;         07
  ;                                    0x040306070c0d0e0f
  ret void
}

define signext i8 @shouldnt_merge_since_theres_a_full_overlap(i64 *%ptr) {
; CHECK-LABEL: @shouldnt_merge_since_theres_a_full_overlap(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[BPTR:%.*]] = bitcast i64* [[PTR:%.*]] to i8*
; CHECK-NEXT:    [[BPTRM1:%.*]] = getelementptr inbounds i8, i8* [[BPTR]], i64 -1
; CHECK-NEXT:    [[BPTR3:%.*]] = getelementptr inbounds i8, i8* [[BPTR]], i64 3
; CHECK-NEXT:    [[DPTR:%.*]] = bitcast i8* [[BPTRM1]] to i32*
; CHECK-NEXT:    [[QPTR:%.*]] = bitcast i8* [[BPTR3]] to i64*
; CHECK-NEXT:    store i32 1234, i32* [[DPTR]], align 1
; CHECK-NEXT:    store i64 5678, i64* [[QPTR]], align 1
; CHECK-NEXT:    ret i8 0
;
entry:

  store i64 0, i64* %ptr

  %bptr = bitcast i64* %ptr to i8*
  %bptrm1 = getelementptr inbounds i8, i8* %bptr, i64 -1
  %bptr3 = getelementptr inbounds i8, i8* %bptr, i64 3
  %dptr = bitcast i8* %bptrm1 to i32*
  %qptr = bitcast i8* %bptr3 to i64*

  store i32 1234, i32* %dptr, align 1
  store i64 5678, i64* %qptr, align 1

  ret i8 0
}

;; Test case from PR31777
%union.U = type { i64 }

define void @foo(%union.U* nocapture %u) {
; CHECK-LABEL: @foo(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[I:%.*]] = getelementptr inbounds [[UNION_U:%.*]], %union.U* [[U:%.*]], i64 0, i32 0
; CHECK-NEXT:    store i64 11821949021847552, i64* [[I]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %i = getelementptr inbounds %union.U, %union.U* %u, i64 0, i32 0
  store i64 0, i64* %i, align 8
  %s = bitcast %union.U* %u to i16*
  store i16 42, i16* %s, align 8
  ret void
}