1
0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-22 07:32:48 +00:00
llvm-6502/test/CodeGen/AArch64/arm64-cse.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

60 lines
1.4 KiB
LLVM

; RUN: llc -O3 < %s -aarch64-atomic-cfg-tidy=0 | FileCheck %s
target triple = "arm64-apple-ios"
; rdar://12462006
; CSE between "icmp reg reg" and "sub reg reg".
; Both can be in the same basic block or in different basic blocks.
define i8* @t1(i8* %base, i32* nocapture %offset, i32 %size) nounwind {
entry:
; CHECK-LABEL: t1:
; CHECK: subs
; CHECK-NOT: cmp
; CHECK-NOT: sub
; CHECK: b.ge
; CHECK: sub
; CHECK: sub
; CHECK-NOT: sub
; CHECK: ret
%0 = load i32* %offset, align 4
%cmp = icmp slt i32 %0, %size
%s = sub nsw i32 %0, %size
br i1 %cmp, label %return, label %if.end
if.end:
%sub = sub nsw i32 %0, %size
%s2 = sub nsw i32 %s, %size
%s3 = sub nsw i32 %sub, %s2
store i32 %s3, i32* %offset, align 4
%add.ptr = getelementptr inbounds i8* %base, i32 %sub
br label %return
return:
%retval.0 = phi i8* [ %add.ptr, %if.end ], [ null, %entry ]
ret i8* %retval.0
}
; CSE between "icmp reg imm" and "sub reg imm".
define i8* @t2(i8* %base, i32* nocapture %offset) nounwind {
entry:
; CHECK-LABEL: t2:
; CHECK: subs
; CHECK-NOT: cmp
; CHECK-NOT: sub
; CHECK: b.lt
; CHECK-NOT: sub
; CHECK: ret
%0 = load i32* %offset, align 4
%cmp = icmp slt i32 %0, 1
br i1 %cmp, label %return, label %if.end
if.end:
%sub = sub nsw i32 %0, 1
store i32 %sub, i32* %offset, align 4
%add.ptr = getelementptr inbounds i8* %base, i32 %sub
br label %return
return:
%retval.0 = phi i8* [ %add.ptr, %if.end ], [ null, %entry ]
ret i8* %retval.0
}