llvm/llvm/test/Transforms/LoopStrengthReduce/AArch64/lsr-memcpy.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=arm64-unknown-unknown -mcpu=cyclone -pre-RA-sched=list-hybrid < %s | FileCheck %s
; rdar://10232252
; Prevent LSR of doing poor choice that cannot be folded in addressing mode

; Remove the -pre-RA-sched=list-hybrid option after fixing:
; <rdar://problem/12702735> [ARM64][coalescer] need better register
; coalescing for simple unit tests.

define i32 @test_inttoptr() nounwind {
; CHECK-LABEL: test_inttoptr:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    mov w8, #1288 // =0x508
; CHECK-NEXT:    mov x9, #4294967296 // =0x100000000
; CHECK-NEXT:    mov x10, #6442450944 // =0x180000000
; CHECK-NEXT:  .LBB0_1: // %while.body
; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr x11, [x9], #8
; CHECK-NEXT:    str x11, [x10], #8
; CHECK-NEXT:    subs x8, x8, #8
; CHECK-NEXT:    b.pl .LBB0_1
; CHECK-NEXT:  // %bb.2: // %while.end
; CHECK-NEXT:    mov x8, #6442450944 // =0x180000000
; CHECK-NEXT:    blr x8
; CHECK-NEXT:    mov w0, #0 // =0x0
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
entry:
  br label %while.body

while.body:                                       ; preds = %while.body, %entry
  %len.06 = phi i64 [ 1288, %entry ], [ %sub, %while.body ]
  %pDst.05 = phi ptr [ inttoptr (i64 6442450944 to ptr), %entry ], [ %incdec.ptr1, %while.body ]
  %pSrc.04 = phi ptr [ inttoptr (i64 4294967296 to ptr), %entry ], [ %incdec.ptr, %while.body ]
  %incdec.ptr = getelementptr inbounds i64, ptr %pSrc.04, i64 1
  %tmp = load volatile i64, ptr %pSrc.04, align 8
  %incdec.ptr1 = getelementptr inbounds i64, ptr %pDst.05, i64 1
  store volatile i64 %tmp, ptr %pDst.05, align 8
  %sub = add i64 %len.06, -8
  %cmp = icmp sgt i64 %sub, -1
  br i1 %cmp, label %while.body, label %while.end

while.end:                                        ; preds = %while.body
  tail call void inttoptr (i64 6442450944 to ptr)() nounwind
  ret i32 0
}

@g1 = external dso_local global i8
@g2 = external dso_local global i8

define ptr @test_globals() nounwind {
; CHECK-LABEL: test_globals:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov w8, #1288 // =0x508
; CHECK-NEXT:    adrp x9, g2
; CHECK-NEXT:    add x9, x9, :lo12:g2
; CHECK-NEXT:    adrp x10, g1
; CHECK-NEXT:    add x10, x10, :lo12:g1
; CHECK-NEXT:  .LBB1_1: // %while.body
; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr x11, [x9], #8
; CHECK-NEXT:    str x11, [x10], #8
; CHECK-NEXT:    subs x8, x8, #8
; CHECK-NEXT:    b.pl .LBB1_1
; CHECK-NEXT:  // %bb.2: // %while.end
; CHECK-NEXT:    adrp x0, g1
; CHECK-NEXT:    add x0, x0, :lo12:g1
; CHECK-NEXT:    ret
entry:
  br label %while.body

while.body:                                       ; preds = %while.body, %entry
  %len.06 = phi i64 [ 1288, %entry ], [ %sub, %while.body ]
  %pDst.05 = phi ptr [ @g1, %entry ], [ %incdec.ptr1, %while.body ]
  %pSrc.04 = phi ptr [ @g2, %entry ], [ %incdec.ptr, %while.body ]
  %incdec.ptr = getelementptr inbounds i64, ptr %pSrc.04, i64 1
  %tmp = load volatile i64, ptr %pSrc.04, align 8
  %incdec.ptr1 = getelementptr inbounds i64, ptr %pDst.05, i64 1
  store volatile i64 %tmp, ptr %pDst.05, align 8
  %sub = add i64 %len.06, -8
  %cmp = icmp sgt i64 %sub, -1
  br i1 %cmp, label %while.body, label %while.end

while.end:                                        ; preds = %while.body
  ret ptr @g1
}