2014-09-01 06:03:11 +00:00
|
|
|
; RUN: opt -basicaa -memcpyopt -instcombine -S < %s | FileCheck %s
|
|
|
|
|
|
|
|
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
|
2014-09-01 10:09:18 +00:00
|
|
|
define void @foo([8 x i64]* noalias nocapture sret dereferenceable(64) %sret) {
|
2014-09-01 06:03:11 +00:00
|
|
|
entry-block:
|
|
|
|
%a = alloca [8 x i64], align 8
|
2014-09-01 10:09:18 +00:00
|
|
|
%a.cast = bitcast [8 x i64]* %a to i8*
|
|
|
|
call void @llvm.lifetime.start(i64 64, i8* %a.cast)
|
|
|
|
call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false)
|
|
|
|
%sret.cast = bitcast [8 x i64]* %sret to i8*
|
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false)
|
|
|
|
call void @llvm.lifetime.end(i64 64, i8* %a.cast)
|
2014-09-01 06:03:11 +00:00
|
|
|
ret void
|
|
|
|
|
|
|
|
; CHECK-LABEL: @foo(
|
2014-09-01 10:09:18 +00:00
|
|
|
; CHECK: %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
|
|
|
|
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64
|
|
|
|
; CHECK-NOT: call void @llvm.memcpy
|
|
|
|
; CHECK: ret void
|
|
|
|
}
|
|
|
|
|
|
|
|
define void @bar([8 x i64]* noalias nocapture sret dereferenceable(64) %sret, [8 x i64]* noalias nocapture dereferenceable(64) %out) {
|
|
|
|
entry-block:
|
|
|
|
%a = alloca [8 x i64], align 8
|
|
|
|
%a.cast = bitcast [8 x i64]* %a to i8*
|
|
|
|
call void @llvm.lifetime.start(i64 64, i8* %a.cast)
|
|
|
|
call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false)
|
|
|
|
%sret.cast = bitcast [8 x i64]* %sret to i8*
|
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false)
|
|
|
|
call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 42, i64 32, i32 8, i1 false)
|
|
|
|
%out.cast = bitcast [8 x i64]* %out to i8*
|
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out.cast, i8* %a.cast, i64 64, i32 8, i1 false)
|
|
|
|
call void @llvm.lifetime.end(i64 64, i8* %a.cast)
|
|
|
|
ret void
|
|
|
|
|
|
|
|
; CHECK-LABEL: @bar(
|
|
|
|
; CHECK: %[[a:[^=]+]] = alloca [8 x i64]
|
|
|
|
; CHECK: %[[a_cast:[^=]+]] = bitcast [8 x i64]* %[[a]] to i8*
|
|
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 0, i64 64
|
|
|
|
; CHECK: %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
|
[MemCpyOpt] Turn memcpy from just-memset'd source into memset.
There's no point in copying around constants, so, when all else fails,
we can still transform memcpy of memset into two independent memsets.
To quote the example, we can turn:
memset(dst1, c, dst1_size);
memcpy(dst2, dst1, dst2_size);
into:
memset(dst1, c, dst1_size);
memset(dst2, c, dst2_size);
When dst2_size <= dst1_size.
Like r235232 for copy constructors, this can occur in move constructors.
Differential Revision: http://reviews.llvm.org/D9682
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237506 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-16 01:32:26 +00:00
|
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64
|
2014-09-01 10:09:18 +00:00
|
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 42, i64 32
|
|
|
|
; CHECK: %[[out_cast:[^=]+]] = bitcast [8 x i64]* %out to i8*
|
|
|
|
; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %[[out_cast]], i8* %[[a_cast]], i64 64
|
2014-09-01 06:03:11 +00:00
|
|
|
; CHECK-NOT: call void @llvm.memcpy
|
|
|
|
; CHECK: ret void
|
|
|
|
}
|
|
|
|
|
|
|
|
declare void @llvm.lifetime.start(i64, i8* nocapture) nounwind
|
|
|
|
declare void @llvm.lifetime.end(i64, i8* nocapture) nounwind
|
|
|
|
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) nounwind
|
|
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
|