2014-09-25 00:35:50 +08:00
|
|
|
; RUN: llc < %s -mtriple=thumb-apple-darwin -disable-cgp-branch-opts -disable-post-ra -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=RA_GREEDY
|
|
|
|
|
; RUN: llc < %s -mtriple=thumb-apple-darwin -disable-cgp-branch-opts -disable-post-ra -regalloc=basic -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=RA_BASIC
|
2009-06-24 14:36:07 +08:00
|
|
|
|
|
|
|
|
%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
|
|
|
|
|
%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
|
|
|
|
|
|
|
|
|
|
define void @t1(%struct.state* %v) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: t1:
|
Fix epilogue codegen to avoid leaving the stack pointer in an invalid
state. Previously Thumb2 would restore sp from fp like this:
mov sp, r7
sub, sp, #4
If an interrupt is taken after the 'mov' but before the 'sub', callee-saved
registers might be clobbered by the interrupt handler. Instead, try
restoring directly from sp:
add sp, #4
Or, if necessary (with VLA, etc.) use a scratch register to compute sp and
then restore it:
sub.w r4, r7, #8
mov sp, r7
rdar://8465407
llvm-svn: 119977
2010-11-23 02:12:04 +08:00
|
|
|
; CHECK: push
|
|
|
|
|
; CHECK: add r7, sp, #12
|
2011-04-01 07:31:50 +08:00
|
|
|
; CHECK: lsls r[[R0:[0-9]+]]
|
|
|
|
|
; CHECK: mov r[[R1:[0-9]+]], sp
|
|
|
|
|
; CHECK: subs r[[R2:[0-9]+]], r[[R1]], r[[R0]]
|
|
|
|
|
; CHECK: mov sp, r[[R2]]
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp6 = load i32, i32* null
|
2009-06-24 14:36:07 +08:00
|
|
|
%tmp8 = alloca float, i32 %tmp6
|
|
|
|
|
store i32 1, i32* null
|
|
|
|
|
br i1 false, label %bb123.preheader, label %return
|
|
|
|
|
|
|
|
|
|
bb123.preheader:
|
|
|
|
|
br i1 false, label %bb43, label %return
|
|
|
|
|
|
|
|
|
|
bb43:
|
|
|
|
|
call fastcc void @f1( float* %tmp8, float* null, i32 0 )
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp70 = load i32, i32* null
|
[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
|
|
|
%tmp85 = getelementptr float, float* %tmp8, i32 0
|
2009-06-24 14:36:07 +08:00
|
|
|
call fastcc void @f2( float* null, float* null, float* %tmp85, i32 %tmp70 )
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
return:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare fastcc void @f1(float*, float*, i32)
|
|
|
|
|
|
|
|
|
|
declare fastcc void @f2(float*, float*, float*, i32)
|
|
|
|
|
|
|
|
|
|
%struct.comment = type { i8**, i32*, i32, i8* }
|
|
|
|
|
@str215 = external global [2 x i8]
|
|
|
|
|
|
|
|
|
|
define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: t2:
|
Fix epilogue codegen to avoid leaving the stack pointer in an invalid
state. Previously Thumb2 would restore sp from fp like this:
mov sp, r7
sub, sp, #4
If an interrupt is taken after the 'mov' but before the 'sub', callee-saved
registers might be clobbered by the interrupt handler. Instead, try
restoring directly from sp:
add sp, #4
Or, if necessary (with VLA, etc.) use a scratch register to compute sp and
then restore it:
sub.w r4, r7, #8
mov sp, r7
rdar://8465407
llvm-svn: 119977
2010-11-23 02:12:04 +08:00
|
|
|
; CHECK: push
|
|
|
|
|
; CHECK: add r7, sp, #12
|
2011-04-01 07:31:50 +08:00
|
|
|
; CHECK: sub sp, #
|
|
|
|
|
; CHECK: mov r[[R0:[0-9]+]], sp
|
|
|
|
|
; CHECK: str r{{[0-9+]}}, [r[[R0]]
|
2014-09-25 00:35:50 +08:00
|
|
|
; RA_GREEDY: str r{{[0-9+]}}, [r[[R0]]
|
|
|
|
|
; RA_BASIC: stm r[[R0]]!
|
Fix epilogue codegen to avoid leaving the stack pointer in an invalid
state. Previously Thumb2 would restore sp from fp like this:
mov sp, r7
sub, sp, #4
If an interrupt is taken after the 'mov' but before the 'sub', callee-saved
registers might be clobbered by the interrupt handler. Instead, try
restoring directly from sp:
add sp, #4
Or, if necessary (with VLA, etc.) use a scratch register to compute sp and
then restore it:
sub.w r4, r7, #8
mov sp, r7
rdar://8465407
llvm-svn: 119977
2010-11-23 02:12:04 +08:00
|
|
|
; CHECK-NOT: ldr r0, [sp
|
2011-04-01 07:31:50 +08:00
|
|
|
; CHECK: mov r[[R1:[0-9]+]], sp
|
|
|
|
|
; CHECK: subs r[[R2:[0-9]+]], r[[R1]], r{{[0-9]+}}
|
|
|
|
|
; CHECK: mov sp, r[[R2]]
|
|
|
|
|
; CHECK-NOT: ldr r0, [sp
|
|
|
|
|
; CHECK: bx
|
2009-06-24 14:36:07 +08:00
|
|
|
%tmp1 = call i32 @strlen( i8* %tag )
|
|
|
|
|
%tmp3 = call i32 @strlen( i8* %contents )
|
|
|
|
|
%tmp4 = add i32 %tmp1, 2
|
|
|
|
|
%tmp5 = add i32 %tmp4, %tmp3
|
|
|
|
|
%tmp6 = alloca i8, i32 %tmp5
|
|
|
|
|
%tmp9 = call i8* @strcpy( i8* %tmp6, i8* %tag )
|
|
|
|
|
%tmp6.len = call i32 @strlen( i8* %tmp6 )
|
[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
|
|
|
%tmp6.indexed = getelementptr i8, i8* %tmp6, i32 %tmp6.len
|
2015-03-14 02:20:45 +08:00
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp6.indexed, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @str215, i32 0, i32 0), i32 2, i32 1, i1 false)
|
2009-06-24 14:36:07 +08:00
|
|
|
%tmp15 = call i8* @strcat( i8* %tmp6, i8* %contents )
|
|
|
|
|
call fastcc void @comment_add( %struct.comment* %vc, i8* %tmp6 )
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i32 @strlen(i8*)
|
|
|
|
|
|
|
|
|
|
declare i8* @strcat(i8*, i8*)
|
|
|
|
|
|
|
|
|
|
declare fastcc void @comment_add(%struct.comment*, i8*)
|
|
|
|
|
|
2011-06-18 14:05:24 +08:00
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
|
2009-06-24 14:36:07 +08:00
|
|
|
|
|
|
|
|
declare i8* @strcpy(i8*, i8*)
|