1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-29 23:12:55 +01:00
llvm-mirror/test/CodeGen/ARM/ifcvt-branch-weight.ll
Tim Northover 3bb84c9bcc 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

llvm-svn: 209883
2014-05-30 10:09:59 +00:00

43 lines
1.2 KiB
LLVM

; RUN: llc < %s -mtriple=thumbv8 -print-machineinstrs=if-converter -arm-atomic-cfg-tidy=0 -o /dev/null 2>&1 | FileCheck %s
%struct.S = type { i8* (i8*)*, [1 x i8] }
define internal zeroext i8 @bar(%struct.S* %x, %struct.S* nocapture %y) nounwind readonly {
entry:
%0 = getelementptr inbounds %struct.S* %x, i32 0, i32 1, i32 0
%1 = load i8* %0, align 1
%2 = zext i8 %1 to i32
%3 = and i32 %2, 112
%4 = icmp eq i32 %3, 0
br i1 %4, label %return, label %bb
bb:
%5 = getelementptr inbounds %struct.S* %y, i32 0, i32 1, i32 0
%6 = load i8* %5, align 1
%7 = zext i8 %6 to i32
%8 = and i32 %7, 112
%9 = icmp eq i32 %8, 0
br i1 %9, label %return, label %bb2
; CHECK: BB#2: derived from LLVM BB %bb2
; CHECK: Successors according to CFG: BB#3(192) BB#4(192)
bb2:
%v10 = icmp eq i32 %3, 16
br i1 %v10, label %bb4, label %bb3, !prof !0
bb3:
%v11 = icmp eq i32 %8, 16
br i1 %v11, label %bb4, label %return, !prof !1
bb4:
%v12 = ptrtoint %struct.S* %x to i32
%phitmp = trunc i32 %v12 to i8
ret i8 %phitmp
return:
ret i8 1
}
!0 = metadata !{metadata !"branch_weights", i32 4, i32 12}
!1 = metadata !{metadata !"branch_weights", i32 8, i32 16}