2012-09-27 21:21:31 +00:00
|
|
|
; Test lib call simplification of __strncpy_chk calls with various values
|
|
|
|
|
; for len and dstlen.
|
|
|
|
|
;
|
|
|
|
|
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
|
|
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
|
|
|
|
|
|
|
|
|
|
@a = common global [60 x i8] zeroinitializer, align 1
|
|
|
|
|
@b = common global [60 x i8] zeroinitializer, align 1
|
2012-10-31 03:33:00 +00:00
|
|
|
@.str = private constant [12 x i8] c"abcdefghijk\00"
|
2012-09-27 21:21:31 +00:00
|
|
|
|
|
|
|
|
; Check cases where dstlen >= len
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
define i8* @test_simplify1() {
|
2013-07-14 01:42:54 +00:00
|
|
|
; CHECK-LABEL: @test_simplify1(
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
|
|
|
%dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
|
|
|
|
|
%src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
|
2012-09-27 21:21:31 +00:00
|
|
|
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false)
|
|
|
|
|
; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
%ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 60)
|
|
|
|
|
ret i8* %ret
|
2012-09-27 21:21:31 +00:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
define i8* @test_simplify2() {
|
2013-07-14 01:42:54 +00:00
|
|
|
; CHECK-LABEL: @test_simplify2(
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
|
|
|
%dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
|
|
|
|
|
%src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
|
2012-09-27 21:21:31 +00:00
|
|
|
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false)
|
|
|
|
|
; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
%ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 12)
|
|
|
|
|
ret i8* %ret
|
2012-09-27 21:21:31 +00:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
define i8* @test_simplify3() {
|
2013-07-14 01:42:54 +00:00
|
|
|
; CHECK-LABEL: @test_simplify3(
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
|
|
|
%dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
|
|
|
|
|
%src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
|
2012-09-27 21:21:31 +00:00
|
|
|
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK-NEXT: %strncpy = call i8* @strncpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 12)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
; CHECK-NEXT: ret i8* %strncpy
|
|
|
|
|
%ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 60)
|
|
|
|
|
ret i8* %ret
|
2012-09-27 21:21:31 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Check cases where dstlen < len
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
define i8* @test_no_simplify1() {
|
2013-07-14 01:42:54 +00:00
|
|
|
; CHECK-LABEL: @test_no_simplify1(
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
|
|
|
%dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
|
|
|
|
|
%src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
|
2012-09-27 21:21:31 +00:00
|
|
|
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK-NEXT: %ret = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 8, i32 4)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
; CHECK-NEXT: ret i8* %ret
|
|
|
|
|
%ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 8, i32 4)
|
|
|
|
|
ret i8* %ret
|
2012-09-27 21:21:31 +00:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
define i8* @test_no_simplify2() {
|
2013-07-14 01:42:54 +00:00
|
|
|
; CHECK-LABEL: @test_no_simplify2(
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
|
|
|
%dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
|
|
|
|
|
%src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
|
2012-09-27 21:21:31 +00:00
|
|
|
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK-NEXT: %ret = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8, i32 0)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227250 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-27 21:52:16 +00:00
|
|
|
; CHECK-NEXT: ret i8* %ret
|
|
|
|
|
%ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 8, i32 0)
|
|
|
|
|
ret i8* %ret
|
2012-09-27 21:21:31 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i8* @__strncpy_chk(i8*, i8*, i32, i32)
|
