llvm/test/CodeGen/Thumb2/thumb2-cbnz.ll
Tim Northover d0dbe02fd2 ARM & AArch64: make use of common cmpxchg idioms after expansion
The C and C++ semantics for compare_exchange require it to return a bool
indicating success. This gets mapped to LLVM IR which follows each cmpxchg with
an icmp of the value loaded against the desired value.

When lowered to ldxr/stxr loops, this extra comparison is redundant: its
results are implicit in the control-flow of the function.

This commit makes two changes: it replaces that icmp with appropriate PHI
nodes, and then makes sure earlyCSE is called after expansion to actually make
use of the opportunities revealed.

I've also added -{arm,aarch64}-enable-atomic-tidy options, so that
existing fragile tests aren't perturbed too much by the change. Many
of them either rely on undef/unreachable too pervasively to be
restored to something well-defined (particularly while making sure
they test the same obscure assert from many years ago), or depend on a
particular CFG shape, which is disrupted by SimplifyCFG.

rdar://problem/16227836

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209883 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-30 10:09:59 +00:00

36 lines
1.0 KiB
LLVM

; RUN: llc < %s -mtriple=thumbv7-apple-darwin -mcpu=cortex-a8 -arm-atomic-cfg-tidy=0 | FileCheck %s
; rdar://7354379
declare double @foo(double) nounwind readnone
define void @t(i32 %c, double %b) {
entry:
%cmp1 = icmp ne i32 %c, 0
br i1 %cmp1, label %bb3, label %bb1
bb1: ; preds = %entry
unreachable
bb3: ; preds = %entry
%cmp2 = icmp ne i32 %c, 0
br i1 %cmp2, label %bb7, label %bb5
bb5: ; preds = %bb3
unreachable
bb7: ; preds = %bb3
%cmp3 = icmp ne i32 %c, 0
br i1 %cmp3, label %bb11, label %bb9
bb9: ; preds = %bb7
; CHECK: cmp r0, #0
; CHECK-NEXT: cbnz
%0 = tail call double @foo(double %b) nounwind readnone ; <double> [#uses=0]
br label %bb11
bb11: ; preds = %bb9, %bb7
%1 = getelementptr i32* undef, i32 0
store i32 0, i32* %1
ret void
}