test/Transforms/RewriteStatepointsForGC/unordered-atomic-memcpy.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
; Use instcombine to cleanup offset computation.
; RUN: opt -passes=rewrite-statepoints-for-gc,instcombine -S < %s | FileCheck %s

target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128-p1:64:64"
target triple = "x86_64-apple-macosx10.11.0"

declare void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)*, i8 addrspace(1)*, i32, i32 immarg)
declare void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)*, i8 addrspace(1)*, i32, i32 immarg)

define void @test_memcpy_gc_leaf_function(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_gc_leaf_function
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SRC_DERIVED:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]]
; CHECK-NEXT:    [[DEST_DERIVED:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]]
; CHECK-NEXT:    call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 1) [[ATTR2:#.*]]
; CHECK-NEXT:    call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 2) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 4) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 8) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 16) [[ATTR2]]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset

  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 1) "gc-leaf-function"
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 2) "gc-leaf-function"
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 4) "gc-leaf-function"
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 8) "gc-leaf-function"
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 16) "gc-leaf-function"
  ret void
}

define void @test_memcpy_element_atomic_1(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_element_atomic_1
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memcpy_element_unordered_atomic_safepoint_1, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 1)
  ret void
}

define void @test_memcpy_element_atomic_2(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_element_atomic_2
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memcpy_element_unordered_atomic_safepoint_2, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 2)
  ret void
}

define void @test_memcpy_element_atomic_4(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_element_atomic_4
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memcpy_element_unordered_atomic_safepoint_4, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 4)
  ret void
}

define void @test_memcpy_element_atomic_8(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_element_atomic_8
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memcpy_element_unordered_atomic_safepoint_8, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 8)
  ret void
}

define void @test_memcpy_element_atomic_16(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memcpy_element_atomic_16
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memcpy_element_unordered_atomic_safepoint_16, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memcpy.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 16)
  ret void
}

define void @test_memmove_gc_leaf_function(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_gc_leaf_function
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SRC_DERIVED:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]]
; CHECK-NEXT:    [[DEST_DERIVED:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]]
; CHECK-NEXT:    call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 1) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 2) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 4) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 8) [[ATTR2]]
; CHECK-NEXT:    call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 [[SRC_DERIVED]], i8 addrspace(1)* align 16 [[DEST_DERIVED]], i32 [[LEN]], i32 16) [[ATTR2]]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset

  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 1) "gc-leaf-function"
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 2) "gc-leaf-function"
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 4) "gc-leaf-function"
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 8) "gc-leaf-function"
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 16) "gc-leaf-function"
  ret void
}

define void @test_memmove_element_atomic_1(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_element_atomic_1
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memmove_element_unordered_atomic_safepoint_1, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 1)
  ret void
}

define void @test_memmove_element_atomic_2(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_element_atomic_2
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memmove_element_unordered_atomic_safepoint_2, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 2)
  ret void
}

define void @test_memmove_element_atomic_4(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_element_atomic_4
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memmove_element_unordered_atomic_safepoint_4, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 4)
  ret void
}

define void @test_memmove_element_atomic_8(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_element_atomic_8
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memmove_element_unordered_atomic_safepoint_8, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 8)
  ret void
}

define void @test_memmove_element_atomic_16(i8 addrspace(1)* %src, i64 %src_offset, i8 addrspace(1)* %dest, i64 %dest_offset, i32 %len) gc "statepoint-example" {
; CHECK-LABEL: define {{[^@]+}}@test_memmove_element_atomic_16
; CHECK-SAME: (i8 addrspace(1)* [[SRC:%.*]], i64 [[SRC_OFFSET:%.*]], i8 addrspace(1)* [[DEST:%.*]], i64 [[DEST_OFFSET:%.*]], i32 [[LEN:%.*]]) gc "statepoint-example" {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STATEPOINT_TOKEN:%.*]] = call token (i64, i32, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidp1i8i64p1i8i64i32f(i64 2882400000, i32 0, void (i8 addrspace(1)*, i64, i8 addrspace(1)*, i64, i32)* nonnull @__llvm_memmove_element_unordered_atomic_safepoint_16, i32 5, i32 0, i8 addrspace(1)* [[SRC]], i64 [[SRC_OFFSET]], i8 addrspace(1)* [[DEST]], i64 [[DEST_OFFSET]], i32 [[LEN]], i32 0, i32 0) [ "gc-live"() ]
; CHECK-NEXT:    ret void
;
entry:
  %src_derived = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %src_offset
  %dest_derived = getelementptr inbounds i8, i8 addrspace(1)* %dest, i64 %dest_offset
  call void @llvm.memmove.element.unordered.atomic.p1i8.p1i8.i32(i8 addrspace(1)* align 16 %src_derived, i8 addrspace(1)* align 16 %dest_derived, i32 %len, i32 16)
  ret void
}