; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt < %s -passes=infer-alignment -S | FileCheck %s

; ------------------------------------------------------------------------------
; Simple test
; ------------------------------------------------------------------------------

define void @simple_forwardpropagate(ptr %a) {
; CHECK-LABEL: define void @simple_forwardpropagate
; CHECK-SAME: (ptr [[A:%.*]]) {
; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    store i32 345, ptr [[A]], align 32
; CHECK-NEXT:    ret void
;
  %ptrint = ptrtoint ptr %a to i64
  %maskedptr = and i64 %ptrint, 31
  %maskcond = icmp eq i64 %maskedptr, 0
  tail call void @llvm.assume(i1 %maskcond)

  %load.a = load i32, ptr %a, align 4
  store i32 345, ptr %a, align 4

  ret void
}

define void @simple_backpropagate(ptr %a) {
; CHECK-LABEL: define void @simple_backpropagate
; CHECK-SAME: (ptr [[A:%.*]]) {
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    store i32 345, ptr [[A]], align 32
; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    ret void
;
  %load.a = load i32, ptr %a, align 4
  store i32 345, ptr %a, align 4

  %ptrint = ptrtoint ptr %a to i64
  %maskedptr = and i64 %ptrint, 31
  %maskcond = icmp eq i64 %maskedptr, 0
  tail call void @llvm.assume(i1 %maskcond)

  ret void
}

define void @simple_forwardpropagate_bundle(ptr %a) {
; CHECK-LABEL: define void @simple_forwardpropagate_bundle
; CHECK-SAME: (ptr [[A:%.*]]) {
; CHECK-NEXT:    call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i32 32) ]
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    store i32 345, ptr [[A]], align 32
; CHECK-NEXT:    ret void
;
  call void @llvm.assume(i1 true) ["align"(ptr %a, i32 32)]
  %load.a = load i32, ptr %a, align 4
  store i32 345, ptr %a, align 4
  ret void
}

define void @simple_backpropagate_bundle(ptr %a) {
; CHECK-LABEL: define void @simple_backpropagate_bundle
; CHECK-SAME: (ptr [[A:%.*]]) {
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    store i32 345, ptr [[A]], align 32
; CHECK-NEXT:    call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i32 32) ]
; CHECK-NEXT:    ret void
;
  %load.a = load i32, ptr %a, align 4
  store i32 345, ptr %a, align 4
  call void @llvm.assume(i1 true) ["align"(ptr %a, i32 32)]
  ret void
}

; ------------------------------------------------------------------------------
; Complex test
; ------------------------------------------------------------------------------

define void @loop_forwardpropagate(ptr %a, ptr %b) {
; CHECK-LABEL: define void @loop_forwardpropagate
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 63
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    [[PTRINT2:%.*]] = ptrtoint ptr [[B]] to i64
; CHECK-NEXT:    [[MASKEDPTR2:%.*]] = and i64 [[PTRINT2]], 63
; CHECK-NEXT:    [[MASKEDCOND2:%.*]] = icmp eq i64 [[MASKEDPTR2]], 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKEDCOND2]])
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[I_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[I]]
; CHECK-NEXT:    [[LOAD_B:%.*]] = load i32, ptr [[GEP_B]], align 64
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[LOAD_B]], 1
; CHECK-NEXT:    [[GEP_A:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[I]]
; CHECK-NEXT:    store i32 [[ADD]], ptr [[GEP_A]], align 64
; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 16
; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i64 [[I_NEXT]], 1648
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  %ptrint = ptrtoint ptr %a to i64
  %maskedptr = and i64 %ptrint, 63
  %maskcond = icmp eq i64 %maskedptr, 0
  tail call void @llvm.assume(i1 %maskcond)

  %ptrint2 = ptrtoint ptr %b to i64
  %maskedptr2 = and i64 %ptrint2, 63
  %maskedcond2 = icmp eq i64 %maskedptr2, 0
  tail call void @llvm.assume(i1 %maskedcond2)

  br label %for.body

for.body:
  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]

  %gep.b = getelementptr inbounds i32, ptr %b, i64 %i
  %load.b = load i32, ptr %gep.b, align 4
  %add = add nsw i32 %load.b, 1

  %gep.a = getelementptr inbounds i32, ptr %a, i64 %i
  store i32 %add, ptr %gep.a, align 4

  %i.next = add nuw nsw i64 %i, 16
  %cmp = icmp slt i64 %i.next, 1648

  br i1 %cmp, label %for.body, label %for.end

for.end:
  ret void
}

define void @loop_forwardpropagate_bundle(ptr %a, ptr %b) {
; CHECK-LABEL: define void @loop_forwardpropagate_bundle
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i32 64) ]
; CHECK-NEXT:    tail call void @llvm.assume(i1 true) [ "align"(ptr [[B]], i32 64) ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[I_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[I]]
; CHECK-NEXT:    [[LOAD_B:%.*]] = load i32, ptr [[GEP_B]], align 64
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[LOAD_B]], 1
; CHECK-NEXT:    [[GEP_A:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[I]]
; CHECK-NEXT:    store i32 [[ADD]], ptr [[GEP_A]], align 64
; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 16
; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i64 [[I_NEXT]], 1648
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  tail call void @llvm.assume(i1 true) ["align"(ptr %a, i32 64)]
  tail call void @llvm.assume(i1 true) ["align"(ptr %b, i32 64)]
  br label %for.body

for.body:
  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]

  %gep.b = getelementptr inbounds i32, ptr %b, i64 %i
  %load.b = load i32, ptr %gep.b, align 4
  %add = add nsw i32 %load.b, 1

  %gep.a = getelementptr inbounds i32, ptr %a, i64 %i
  store i32 %add, ptr %gep.a, align 4

  %i.next = add nuw nsw i64 %i, 16
  %cmp = icmp slt i64 %i.next, 1648

  br i1 %cmp, label %for.body, label %for.end

for.end:
  ret void
}

; Check that assume is propagated backwards through all
; operations that are `isGuaranteedToTransferExecutionToSuccessor`
; (it should reach the load and mark it as `align 32`).
define void @complex_backpropagate(ptr %a, ptr %b, ptr %c) {
; CHECK-LABEL: define void @complex_backpropagate
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]], ptr [[C:%.*]]) {
; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i64, align 8
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    [[LOAD_B:%.*]] = load i32, ptr [[B]], align 4
; CHECK-NEXT:    store i32 [[LOAD_B]], ptr [[A]], align 32
; CHECK-NEXT:    [[OBJ_SIZE:%.*]] = call i64 @llvm.objectsize.i64.p0(ptr [[C]], i1 false, i1 false, i1 false)
; CHECK-NEXT:    store i64 [[OBJ_SIZE]], ptr [[ALLOCA]], align 8
; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    ret void
;
  %alloca = alloca i64
  %load.a = load i32, ptr %a, align 4

  %load.b = load i32, ptr %b
  store i32 %load.b, ptr %a

  %obj.size = call i64 @llvm.objectsize.i64.p0(ptr %c, i1 false)
  store i64 %obj.size, ptr %alloca

  %ptrint = ptrtoint ptr %a to i64
  %maskedptr = and i64 %ptrint, 31
  %maskcond = icmp eq i64 %maskedptr, 0
  tail call void @llvm.assume(i1 %maskcond)

  ret void
}

define void @complex_backpropagate_bundle(ptr %a, ptr %b, ptr %c) {
; CHECK-LABEL: define void @complex_backpropagate_bundle
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]], ptr [[C:%.*]]) {
; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i64, align 8
; CHECK-NEXT:    [[LOAD_A:%.*]] = load i32, ptr [[A]], align 32
; CHECK-NEXT:    [[LOAD_B:%.*]] = load i32, ptr [[B]], align 4
; CHECK-NEXT:    store i32 [[LOAD_B]], ptr [[A]], align 32
; CHECK-NEXT:    [[OBJ_SIZE:%.*]] = call i64 @llvm.objectsize.i64.p0(ptr [[C]], i1 false, i1 false, i1 false)
; CHECK-NEXT:    store i64 [[OBJ_SIZE]], ptr [[ALLOCA]], align 8
; CHECK-NEXT:    tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i32 32) ]
; CHECK-NEXT:    ret void
;
  %alloca = alloca i64
  %load.a = load i32, ptr %a, align 4

  %load.b = load i32, ptr %b
  store i32 %load.b, ptr %a

  %obj.size = call i64 @llvm.objectsize.i64.p0(ptr %c, i1 false)
  store i64 %obj.size, ptr %alloca

  tail call void @llvm.assume(i1 true) ["align"(ptr %a, i32 32)]

  ret void
}

declare i64 @llvm.objectsize.i64.p0(ptr, i1)
declare void @llvm.assume(i1)