2014-08-30 04:50:31 +08:00
|
|
|
; RUN: llc -mtriple=i686-windows -mattr=+sse2 < %s | FileCheck %s
|
|
|
|
|
|
|
|
|
|
target datalayout = "e-m:w-p:32:32-i64:64-f80:32-n8:16:32-S32"
|
|
|
|
|
target triple = "i686-pc-windows-msvc"
|
|
|
|
|
|
|
|
|
|
; There is a conflict between lowering the X86 memory intrinsics and the "base"
|
|
|
|
|
; register used to address stack locals. See X86RegisterInfo::hasBaseRegister
|
|
|
|
|
; for when this is necessary. Typically, we chose ESI for the base register,
|
|
|
|
|
; which all of the X86 string instructions use.
|
|
|
|
|
|
|
|
|
|
; The pattern of vector icmp and extractelement is used in these tests because
|
|
|
|
|
; it forces creation of an aligned stack temporary. Perhaps such temporaries
|
|
|
|
|
; shouldn't be aligned.
|
|
|
|
|
|
|
|
|
|
declare void @escape_vla_and_icmp(i8*, i1 zeroext)
|
2015-11-19 13:56:52 +08:00
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1)
|
|
|
|
|
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1)
|
2014-08-30 04:50:31 +08:00
|
|
|
|
|
|
|
|
define i32 @memcpy_novla_vector(<4 x i32>* %vp0, i8* %a, i8* %b, i32 %n, i1 zeroext %cond) {
|
2015-11-19 13:56:52 +08:00
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %b, i32 128, i32 4, i1 false)
|
2014-08-30 04:50:31 +08:00
|
|
|
br i1 %cond, label %spill_vectors, label %no_vectors
|
|
|
|
|
|
|
|
|
|
no_vectors:
|
|
|
|
|
ret i32 0
|
|
|
|
|
|
|
|
|
|
spill_vectors:
|
[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
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%vp1 = getelementptr <4 x i32>, <4 x i32>* %vp0, i32 1
|
2015-02-28 05:17:42 +08:00
|
|
|
%v0 = load <4 x i32>, <4 x i32>* %vp0
|
|
|
|
|
%v1 = load <4 x i32>, <4 x i32>* %vp1
|
2014-08-30 04:50:31 +08:00
|
|
|
%vicmp = icmp slt <4 x i32> %v0, %v1
|
|
|
|
|
%icmp = extractelement <4 x i1> %vicmp, i32 0
|
|
|
|
|
call void @escape_vla_and_icmp(i8* null, i1 zeroext %icmp)
|
|
|
|
|
%r = extractelement <4 x i32> %v0, i32 0
|
|
|
|
|
ret i32 %r
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: _memcpy_novla_vector:
|
|
|
|
|
; CHECK: andl $-16, %esp
|
|
|
|
|
; CHECK-DAG: movl $32, %ecx
|
|
|
|
|
; CHECK-DAG: movl {{.*}}, %esi
|
|
|
|
|
; CHECK-DAG: movl {{.*}}, %edi
|
|
|
|
|
; CHECK: rep;movsl
|
|
|
|
|
|
|
|
|
|
define i32 @memcpy_vla_vector(<4 x i32>* %vp0, i8* %a, i8* %b, i32 %n, i1 zeroext %cond) {
|
2015-11-19 13:56:52 +08:00
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %b, i32 128, i32 4, i1 false)
|
2014-08-30 04:50:31 +08:00
|
|
|
br i1 %cond, label %spill_vectors, label %no_vectors
|
|
|
|
|
|
|
|
|
|
no_vectors:
|
|
|
|
|
ret i32 0
|
|
|
|
|
|
|
|
|
|
spill_vectors:
|
[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
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%vp1 = getelementptr <4 x i32>, <4 x i32>* %vp0, i32 1
|
2015-02-28 05:17:42 +08:00
|
|
|
%v0 = load <4 x i32>, <4 x i32>* %vp0
|
|
|
|
|
%v1 = load <4 x i32>, <4 x i32>* %vp1
|
2014-08-30 04:50:31 +08:00
|
|
|
%vicmp = icmp slt <4 x i32> %v0, %v1
|
|
|
|
|
%icmp = extractelement <4 x i1> %vicmp, i32 0
|
|
|
|
|
%vla = alloca i8, i32 %n
|
|
|
|
|
call void @escape_vla_and_icmp(i8* %vla, i1 zeroext %icmp)
|
|
|
|
|
%r = extractelement <4 x i32> %v0, i32 0
|
|
|
|
|
ret i32 %r
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: _memcpy_vla_vector:
|
|
|
|
|
; CHECK: andl $-16, %esp
|
|
|
|
|
; CHECK: movl %esp, %esi
|
2014-12-09 14:10:44 +08:00
|
|
|
; CHECK: pushl $128
|
2014-08-30 04:50:31 +08:00
|
|
|
; CHECK: calll _memcpy
|
|
|
|
|
; CHECK: calll __chkstk
|
|
|
|
|
|
|
|
|
|
; stosd doesn't clobber esi, so we can use it.
|
|
|
|
|
|
|
|
|
|
define i32 @memset_vla_vector(<4 x i32>* %vp0, i8* %a, i32 %n, i1 zeroext %cond) {
|
2015-11-19 13:56:52 +08:00
|
|
|
call void @llvm.memset.p0i8.i32(i8* %a, i8 42, i32 128, i32 4, i1 false)
|
2014-08-30 04:50:31 +08:00
|
|
|
br i1 %cond, label %spill_vectors, label %no_vectors
|
|
|
|
|
|
|
|
|
|
no_vectors:
|
|
|
|
|
ret i32 0
|
|
|
|
|
|
|
|
|
|
spill_vectors:
|
[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
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%vp1 = getelementptr <4 x i32>, <4 x i32>* %vp0, i32 1
|
2015-02-28 05:17:42 +08:00
|
|
|
%v0 = load <4 x i32>, <4 x i32>* %vp0
|
|
|
|
|
%v1 = load <4 x i32>, <4 x i32>* %vp1
|
2014-08-30 04:50:31 +08:00
|
|
|
%vicmp = icmp slt <4 x i32> %v0, %v1
|
|
|
|
|
%icmp = extractelement <4 x i1> %vicmp, i32 0
|
|
|
|
|
%vla = alloca i8, i32 %n
|
|
|
|
|
call void @escape_vla_and_icmp(i8* %vla, i1 zeroext %icmp)
|
|
|
|
|
%r = extractelement <4 x i32> %v0, i32 0
|
|
|
|
|
ret i32 %r
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: _memset_vla_vector:
|
|
|
|
|
; CHECK: andl $-16, %esp
|
|
|
|
|
; CHECK: movl %esp, %esi
|
|
|
|
|
; CHECK-DAG: movl $707406378, %eax # imm = 0x2A2A2A2A
|
|
|
|
|
; CHECK-DAG: movl $32, %ecx
|
|
|
|
|
; CHECK-DAG: movl {{.*}}, %edi
|
|
|
|
|
; CHECK-NOT: movl {{.*}}, %esi
|
|
|
|
|
; CHECK: rep;stosl
|
|
|
|
|
|
|
|
|
|
; Add a test for memcmp if we ever add a special lowering for it.
|