mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
3ea2df7c7b
Similar to gep (r230786) and load (r230794) changes.
Similar migration script can be used to update test cases, which
successfully migrated all of LLVM and Polly, but about 4 test cases
needed manually changes in Clang.
(this script will read the contents of stdin and massage it into stdout
- wrap it in the 'apply.sh' script shown in previous commits + xargs to
apply it over a large set of test cases)
import fileinput
import sys
import re
rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL)
def conv(match):
line = match.group(1)
line += match.group(4)
line += ", "
line += match.group(2)
return line
line = sys.stdin.read()
off = 0
for match in re.finditer(rep, line):
sys.stdout.write(line[off:match.start()])
sys.stdout.write(conv(match))
off = match.end()
sys.stdout.write(line[off:])
llvm-svn: 232184
41 lines
1.5 KiB
LLVM
41 lines
1.5 KiB
LLVM
; RUN: opt < %s -basicaa -memcpyopt -S | FileCheck %s
|
|
; These memmoves should get optimized to memcpys.
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
|
|
target triple = "x86_64-apple-darwin9.0"
|
|
|
|
declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
|
|
|
|
define i8* @test1(i8* nocapture %src) nounwind {
|
|
entry:
|
|
; CHECK-LABEL: @test1(
|
|
; CHECK: call void @llvm.memcpy
|
|
|
|
%malloccall = tail call i8* @malloc(i32 trunc (i64 mul nuw (i64 ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64), i64 13) to i32))
|
|
%call3 = bitcast i8* %malloccall to [13 x i8]*
|
|
%call3.sub = getelementptr inbounds [13 x i8], [13 x i8]* %call3, i64 0, i64 0
|
|
tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %call3.sub, i8* %src, i64 13, i32 1, i1 false)
|
|
ret i8* %call3.sub
|
|
}
|
|
declare noalias i8* @malloc(i32)
|
|
|
|
|
|
define void @test2(i8* %P) nounwind {
|
|
entry:
|
|
; CHECK-LABEL: @test2(
|
|
; CHECK: call void @llvm.memcpy
|
|
%add.ptr = getelementptr i8, i8* %P, i64 16
|
|
tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 16, i32 1, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; This cannot be optimize because the src/dst really do overlap.
|
|
define void @test3(i8* %P) nounwind {
|
|
entry:
|
|
; CHECK-LABEL: @test3(
|
|
; CHECK: call void @llvm.memmove
|
|
%add.ptr = getelementptr i8, i8* %P, i64 16
|
|
tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 17, i32 1, i1 false)
|
|
ret void
|
|
}
|