mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-17 03:30:28 +00:00
d0dbe02fd2
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
33 lines
1.0 KiB
LLVM
33 lines
1.0 KiB
LLVM
; RUN: llc < %s -mcpu=cortex-a8 -arm-atomic-cfg-tidy=0 | FileCheck %s
|
|
; ModuleID = 'bugpoint-reduced-simplified.bc'
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:64:128-a0:0:64-n32-S64"
|
|
target triple = "armv7--linux-gnueabi"
|
|
|
|
; CHECK-LABEL: function
|
|
define void @function() {
|
|
; CHECK: cmp r0, #0
|
|
; CHECK: bxne lr
|
|
; CHECK: vmov.i32 q8, #0xff0000
|
|
entry:
|
|
br i1 undef, label %vector.body, label %for.end
|
|
|
|
; CHECK: vld1.32 {d18, d19}, [r0]
|
|
; CHECK: vand q10, q9, q8
|
|
; CHECK: vbic.i16 q9, #0xff
|
|
; CHECK: vorr q9, q9, q10
|
|
; CHECK: vst1.32 {d18, d19}, [r0]
|
|
vector.body:
|
|
%wide.load = load <4 x i32>* undef, align 4
|
|
%0 = and <4 x i32> %wide.load, <i32 -16711936, i32 -16711936, i32 -16711936, i32 -16711936>
|
|
%1 = sub <4 x i32> %wide.load, zeroinitializer
|
|
%2 = and <4 x i32> %1, <i32 16711680, i32 16711680, i32 16711680, i32 16711680>
|
|
%3 = or <4 x i32> undef, %0
|
|
%4 = or <4 x i32> %3, %2
|
|
store <4 x i32> %4, <4 x i32>* undef, align 4
|
|
br label %vector.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|