2012-10-13 16:45:37 +00:00
|
|
|
; Test that the strchr library call simplifier works correctly.
|
|
|
|
|
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
|
|
[SimplifyLibCalls] Turn memchr(const, C, const) into a bitfield check.
strchr("123!", C) != nullptr is a common pattern to check if C is one
of 1, 2, 3 or !. If the largest element of the string is smaller than
the target's register size we can easily create a bitfield and just
do a simple test for set membership.
int foo(char C) { return strchr("123!", C) != nullptr; } now becomes
cmpl $64, %edi ## range check
sbbb %al, %al
movabsq $0xE000200000001, %rcx
btq %rdi, %rcx ## bit test
sbbb %cl, %cl
andb %al, %cl ## and the two conditions
andb $1, %cl
movzbl %cl, %eax ## returning an int
ret
(imho the backend should expand this into a series of branches, but
that's a different story)
The code is currently limited to bit fields that fit in a register, so
usually 64 or 32 bits. Sadly, this misses anything using alpha chars
or {}. This could be fixed by just emitting a i128 bit field, but that
can generate really ugly code so we have to find a better way. To some
degree this is also recreating switch lowering logic, but we can't
simply emit a switch instruction and thus change the CFG within
instcombine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232902 91177308-0d34-0410-b5e6-96231b3b80d8
2015-03-21 21:09:33 +00:00
|
|
|
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-n8:16:32"
|
2012-10-13 16:45:37 +00:00
|
|
|
|
|
|
|
|
@hello = constant [14 x i8] c"hello world\5Cn\00"
|
|
|
|
|
@null = constant [1 x i8] zeroinitializer
|
[SimplifyLibCalls] Turn memchr(const, C, const) into a bitfield check.
strchr("123!", C) != nullptr is a common pattern to check if C is one
of 1, 2, 3 or !. If the largest element of the string is smaller than
the target's register size we can easily create a bitfield and just
do a simple test for set membership.
int foo(char C) { return strchr("123!", C) != nullptr; } now becomes
cmpl $64, %edi ## range check
sbbb %al, %al
movabsq $0xE000200000001, %rcx
btq %rdi, %rcx ## bit test
sbbb %cl, %cl
andb %al, %cl ## and the two conditions
andb $1, %cl
movzbl %cl, %eax ## returning an int
ret
(imho the backend should expand this into a series of branches, but
that's a different story)
The code is currently limited to bit fields that fit in a register, so
usually 64 or 32 bits. Sadly, this misses anything using alpha chars
or {}. This could be fixed by just emitting a i128 bit field, but that
can generate really ugly code so we have to find a better way. To some
degree this is also recreating switch lowering logic, but we can't
simply emit a switch instruction and thus change the CFG within
instcombine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232902 91177308-0d34-0410-b5e6-96231b3b80d8
2015-03-21 21:09:33 +00:00
|
|
|
@newlines = constant [3 x i8] c"\0D\0A\00"
|
2012-10-13 16:45:37 +00:00
|
|
|
@chp = global i8* zeroinitializer
|
|
|
|
|
|
|
|
|
|
declare i8* @strchr(i8*, i32)
|
|
|
|
|
|
|
|
|
|
define void @test_simplify1() {
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK: store i8* getelementptr inbounds ([14 x i8], [14 x i8]* @hello, i32 0, i32 6)
|
2012-10-13 16:45:37 +00:00
|
|
|
; CHECK-NOT: call i8* @strchr
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
[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
|
|
|
%str = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
|
2012-10-13 16:45:37 +00:00
|
|
|
%dst = call i8* @strchr(i8* %str, i32 119)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test_simplify2() {
|
|
|
|
|
; CHECK: store i8* null, i8** @chp, align 4
|
|
|
|
|
; CHECK-NOT: call i8* @strchr
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
[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
|
|
|
%str = getelementptr [1 x i8], [1 x i8]* @null, i32 0, i32 0
|
2012-10-13 16:45:37 +00:00
|
|
|
%dst = call i8* @strchr(i8* %str, i32 119)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test_simplify3() {
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK: store i8* getelementptr inbounds ([14 x i8], [14 x i8]* @hello, i32 0, i32 13)
|
2012-10-13 16:45:37 +00:00
|
|
|
; CHECK-NOT: call i8* @strchr
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
[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
|
|
|
%src = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
|
2012-10-13 16:45:37 +00:00
|
|
|
%dst = call i8* @strchr(i8* %src, i32 0)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test_simplify4(i32 %chr) {
|
|
|
|
|
; CHECK: call i8* @memchr
|
|
|
|
|
; CHECK-NOT: call i8* @strchr
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
[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
|
|
|
%src = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
|
2012-10-13 16:45:37 +00:00
|
|
|
%dst = call i8* @strchr(i8* %src, i32 %chr)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2013-08-15 20:58:59 +00:00
|
|
|
|
|
|
|
|
define void @test_simplify5() {
|
2015-03-13 18:20:45 +00:00
|
|
|
; CHECK: store i8* getelementptr inbounds ([14 x i8], [14 x i8]* @hello, i32 0, i32 13)
|
2013-08-15 20:58:59 +00:00
|
|
|
; CHECK-NOT: call i8* @strchr
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
[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
|
|
|
%src = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
|
2013-08-15 20:58:59 +00:00
|
|
|
%dst = call i8* @strchr(i8* %src, i32 65280)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2014-02-04 05:55:16 +00:00
|
|
|
|
|
|
|
|
; Check transformation strchr(p, 0) -> p + strlen(p)
|
|
|
|
|
define void @test_simplify6(i8* %str) {
|
|
|
|
|
; CHECK: %strlen = call i32 @strlen(i8* %str)
|
|
|
|
|
; CHECK-NOT: call i8* @strchr
|
[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
|
|
|
; CHECK: %strchr = getelementptr i8, i8* %str, i32 %strlen
|
2014-02-04 05:55:16 +00:00
|
|
|
; CHECK: store i8* %strchr, i8** @chp, align 4
|
|
|
|
|
; CHECK: ret void
|
|
|
|
|
|
|
|
|
|
%dst = call i8* @strchr(i8* %str, i32 0)
|
|
|
|
|
store i8* %dst, i8** @chp
|
|
|
|
|
ret void
|
|
|
|
|
}
|
[SimplifyLibCalls] Turn memchr(const, C, const) into a bitfield check.
strchr("123!", C) != nullptr is a common pattern to check if C is one
of 1, 2, 3 or !. If the largest element of the string is smaller than
the target's register size we can easily create a bitfield and just
do a simple test for set membership.
int foo(char C) { return strchr("123!", C) != nullptr; } now becomes
cmpl $64, %edi ## range check
sbbb %al, %al
movabsq $0xE000200000001, %rcx
btq %rdi, %rcx ## bit test
sbbb %cl, %cl
andb %al, %cl ## and the two conditions
andb $1, %cl
movzbl %cl, %eax ## returning an int
ret
(imho the backend should expand this into a series of branches, but
that's a different story)
The code is currently limited to bit fields that fit in a register, so
usually 64 or 32 bits. Sadly, this misses anything using alpha chars
or {}. This could be fixed by just emitting a i128 bit field, but that
can generate really ugly code so we have to find a better way. To some
degree this is also recreating switch lowering logic, but we can't
simply emit a switch instruction and thus change the CFG within
instcombine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232902 91177308-0d34-0410-b5e6-96231b3b80d8
2015-03-21 21:09:33 +00:00
|
|
|
|
|
|
|
|
; Check transformation strchr("\r\n", C) != nullptr -> (C & 9217) != 0
|
|
|
|
|
define i1 @test_simplify7(i32 %C) {
|
|
|
|
|
; CHECK-LABEL: @test_simplify7
|
|
|
|
|
; CHECK-NEXT: [[TRUNC:%.*]] = trunc i32 %C to i16
|
|
|
|
|
; CHECK-NEXT: %memchr.bounds = icmp ult i16 [[TRUNC]], 16
|
|
|
|
|
; CHECK-NEXT: [[SHL:%.*]] = shl i16 1, [[TRUNC]]
|
|
|
|
|
; CHECK-NEXT: [[AND:%.*]] = and i16 [[SHL]], 9217
|
|
|
|
|
; CHECK-NEXT: %memchr.bits = icmp ne i16 [[AND]], 0
|
|
|
|
|
; CHECK-NEXT: %memchr1 = and i1 %memchr.bounds, %memchr.bits
|
|
|
|
|
; CHECK-NEXT: ret i1 %memchr1
|
|
|
|
|
|
|
|
|
|
%dst = call i8* @strchr(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @newlines, i64 0, i64 0), i32 %C)
|
|
|
|
|
%cmp = icmp ne i8* %dst, null
|
|
|
|
|
ret i1 %cmp
|
|
|
|
|
}
|
