Revert "r226086 - Revert "r226071 - [RegisterCoalescer] Remove copies to reserved registers""
Reapply r226071 with fixes. Two fixes:
1. We need to manually remove the old and create the new 'deaf defs'
associated with physical register definitions when we move the definition of
the physical register from the copy point to the point of the original vreg def.
This problem was picked up by the machinstr verifier, and could trigger a
verification failure on test/CodeGen/X86/2009-02-12-DebugInfoVLA.ll, so I've
turned on the verifier in the tests.
2. When moving the def point of the phys reg up, we need to make sure that it
is neither defined nor read in between the two instructions. We don't, however,
extend the live ranges of phys reg defs to cover uses, so just checking for
live-range overlap between the pair interval and the phys reg aliases won't
pick up reads. As a result, we manually iterate over the range and check for
reads.
A test soon to be committed to the PowerPC backend will test this change.
Original commit message:
[RegisterCoalescer] Remove copies to reserved registers
This allows the RegisterCoalescer to join "non-flipped" range pairs with a
physical destination register -- which allows the RegisterCoalescer to remove
copies like this:
<vreg> = something (maybe a load, for example)
... (things that don't use PHYSREG)
PHYSREG = COPY <vreg>
(with all of the restrictions normally applied by the RegisterCoalescer: having
compatible register classes, etc. )
Previously, the RegisterCoalescer handled only the opposite case (copying
*from* a physical register). I don't handle the problem fully here, but try to
get the common case where there is only one use of <vreg> (the COPY).
An upcoming commit to the PowerPC backend will make this pattern much more
common on PPC64/ELF systems.
llvm-svn: 226200
2015-01-16 04:32:09 +08:00
|
|
|
; RUN: llc -mcpu=generic -mtriple=arm-eabi -verify-machineinstrs < %s | FileCheck %s
|
2007-02-06 15:18:27 +08:00
|
|
|
|
2011-06-18 14:05:24 +08:00
|
|
|
%struct.comment = type { i8**, i32*, i32, i8* }
|
|
|
|
|
%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
|
|
|
|
|
%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
|
|
|
|
|
|
|
|
|
|
@str215 = external global [2 x i8]
|
2007-02-06 15:18:27 +08:00
|
|
|
|
2007-02-07 17:24:03 +08:00
|
|
|
define void @t1(%struct.state* %v) {
|
Revert "r226086 - Revert "r226071 - [RegisterCoalescer] Remove copies to reserved registers""
Reapply r226071 with fixes. Two fixes:
1. We need to manually remove the old and create the new 'deaf defs'
associated with physical register definitions when we move the definition of
the physical register from the copy point to the point of the original vreg def.
This problem was picked up by the machinstr verifier, and could trigger a
verification failure on test/CodeGen/X86/2009-02-12-DebugInfoVLA.ll, so I've
turned on the verifier in the tests.
2. When moving the def point of the phys reg up, we need to make sure that it
is neither defined nor read in between the two instructions. We don't, however,
extend the live ranges of phys reg defs to cover uses, so just checking for
live-range overlap between the pair interval and the phys reg aliases won't
pick up reads. As a result, we manually iterate over the range and check for
reads.
A test soon to be committed to the PowerPC backend will test this change.
Original commit message:
[RegisterCoalescer] Remove copies to reserved registers
This allows the RegisterCoalescer to join "non-flipped" range pairs with a
physical destination register -- which allows the RegisterCoalescer to remove
copies like this:
<vreg> = something (maybe a load, for example)
... (things that don't use PHYSREG)
PHYSREG = COPY <vreg>
(with all of the restrictions normally applied by the RegisterCoalescer: having
compatible register classes, etc. )
Previously, the RegisterCoalescer handled only the opposite case (copying
*from* a physical register). I don't handle the problem fully here, but try to
get the common case where there is only one use of <vreg> (the COPY).
An upcoming commit to the PowerPC backend will make this pattern much more
common on PPC64/ELF systems.
llvm-svn: 226200
2015-01-16 04:32:09 +08:00
|
|
|
|
|
|
|
|
; Make sure we generate:
|
|
|
|
|
; sub sp, sp, r1
|
|
|
|
|
; instead of:
|
|
|
|
|
; sub r1, sp, r1
|
|
|
|
|
; mov sp, r1
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @t1
|
|
|
|
|
; CHECK: bic [[REG1:r[0-9]+]],
|
|
|
|
|
; CHECK-NOT: sub r{{[0-9]+}}, sp, [[REG1]]
|
|
|
|
|
; CHECK: sub sp, sp, [[REG1]]
|
|
|
|
|
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp6 = load i32, i32* null
|
2011-06-18 14:05:24 +08:00
|
|
|
%tmp8 = alloca float, i32 %tmp6
|
|
|
|
|
store i32 1, i32* null
|
|
|
|
|
br i1 false, label %bb123.preheader, label %return
|
|
|
|
|
|
|
|
|
|
bb123.preheader: ; preds = %0
|
|
|
|
|
br i1 false, label %bb43, label %return
|
|
|
|
|
|
|
|
|
|
bb43: ; preds = %bb123.preheader
|
|
|
|
|
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
|
2011-06-18 14:05:24 +08:00
|
|
|
call fastcc void @f2(float* null, float* null, float* %tmp85, i32 %tmp70)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
return: ; preds = %bb123.preheader, %0
|
|
|
|
|
ret void
|
2007-02-06 15:18:27 +08:00
|
|
|
}
|
|
|
|
|
|
2007-02-07 17:24:03 +08:00
|
|
|
declare fastcc void @f1(float*, float*, i32)
|
2007-02-06 15:18:27 +08:00
|
|
|
|
2007-02-07 17:24:03 +08:00
|
|
|
declare fastcc void @f2(float*, float*, float*, i32)
|
|
|
|
|
|
|
|
|
|
define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
|
2011-06-18 14:05:24 +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)
|
2011-06-18 14:05:24 +08:00
|
|
|
%tmp15 = call i8* @strcat(i8* %tmp6, i8* %contents)
|
|
|
|
|
call fastcc void @comment_add(%struct.comment* %vc, i8* %tmp6)
|
|
|
|
|
ret void
|
2007-02-07 17:24:03 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i32 @strlen(i8*)
|
|
|
|
|
|
|
|
|
|
declare i8* @strcat(i8*, i8*)
|
|
|
|
|
|
|
|
|
|
declare fastcc void @comment_add(%struct.comment*, i8*)
|
|
|
|
|
|
|
|
|
|
declare i8* @strcpy(i8*, i8*)
|
2011-06-18 14:05:24 +08:00
|
|
|
|
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
|