llvm-6502/test/Transforms/MemCpyOpt/callslot_deref.ll
Bjorn Steinbrink 6eaa62af77 Allow call-slop optzn for destinations with a suitable dereferenceable attribute
Summary:
Currently, call slot optimization requires that if the destination is an
argument, the argument has the sret attribute. This is to ensure that
the memory access won't trap. In addition to sret, we can also allow the
optimization to happen for arguments that have the new dereferenceable
attribute, which gives the same guarantee.

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5832

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219950 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-16 19:43:08 +00:00

30 lines
1.4 KiB
LLVM

; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) unnamed_addr nounwind
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
; all bytes of %dst that are touch by the memset are dereferenceable
define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst) {
; CHECK-LABEL: @must_remove_memcpy(
; CHECK: call void @llvm.memset.p0i8.i64
; CHECK-NOT: call void @llvm.memcpy.p0i8.p0i8.i64
%src = alloca [4096 x i8], align 1
%p = getelementptr inbounds [4096 x i8]* %src, i64 0, i64 0
call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2
ret void
}
; memset touch more bytes than those guaranteed to be dereferenceable
define void @must_not_remove_memcpy(i8* noalias nocapture dereferenceable(1024) %dst) {
; CHECK-LABEL: @must_not_remove_memcpy(
; CHECK: call void @llvm.memset.p0i8.i64
; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64
%src = alloca [4096 x i8], align 1
%p = getelementptr inbounds [4096 x i8]* %src, i64 0, i64 0
call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2
ret void
}