2014-05-30 18:09:59 +08:00
|
|
|
; RUN: llc -mtriple=arm-eabi -arm-atomic-cfg-tidy=0 %s -o - | FileCheck -check-prefix=ARM %s
|
|
|
|
|
; RUN: llc -mtriple=thumb-eabi -arm-atomic-cfg-tidy=0 %s -o - | FileCheck -check-prefix=THUMB %s
|
|
|
|
|
; RUN: llc -mtriple=thumb-eabi -arm-atomic-cfg-tidy=0 -mcpu=arm1156t2-s -mattr=+thumb2 %s -o - \
|
2013-12-13 19:16:00 +08:00
|
|
|
; RUN: | FileCheck -check-prefix=T2 %s
|
2014-05-30 18:09:59 +08:00
|
|
|
; RUN: llc -mtriple=thumbv8-eabi -arm-atomic-cfg-tidy=0 %s -o - | FileCheck -check-prefix=V8 %s
|
When we look at instructions to convert to setting the 's' flag, we need to look
at more than those which define CPSR. You can have this situation:
(1) subs ...
(2) sub r6, r5, r4
(3) movge ...
(4) cmp r6, 0
(5) movge ...
We cannot convert (2) to "subs" because (3) is using the CPSR set by
(1). There's an analogous situation here:
(1) sub r1, r2, r3
(2) sub r4, r5, r6
(3) cmp r4, ...
(5) movge ...
(6) cmp r1, ...
(7) movge ...
We cannot convert (1) to "subs" because of the intervening use of CPSR.
llvm-svn: 117950
2010-11-02 04:41:43 +08:00
|
|
|
|
|
|
|
|
; FIXME: The -march=thumb test doesn't change if -disable-peephole is specified.
|
2010-09-14 16:50:43 +08:00
|
|
|
|
|
|
|
|
%struct.Foo = type { i8* }
|
|
|
|
|
|
2015-04-29 06:03:55 +08:00
|
|
|
; ARM-LABEL: foo:
|
|
|
|
|
; THUMB-LABEL: foo:
|
|
|
|
|
; T2-LABEL: foo:
|
When we look at instructions to convert to setting the 's' flag, we need to look
at more than those which define CPSR. You can have this situation:
(1) subs ...
(2) sub r6, r5, r4
(3) movge ...
(4) cmp r6, 0
(5) movge ...
We cannot convert (2) to "subs" because (3) is using the CPSR set by
(1). There's an analogous situation here:
(1) sub r1, r2, r3
(2) sub r4, r5, r6
(3) cmp r4, ...
(5) movge ...
(6) cmp r1, ...
(7) movge ...
We cannot convert (1) to "subs" because of the intervening use of CPSR.
llvm-svn: 117950
2010-11-02 04:41:43 +08:00
|
|
|
define %struct.Foo* @foo(%struct.Foo* %this, i32 %acc) nounwind readonly align 2 {
|
2010-09-14 16:50:43 +08:00
|
|
|
entry:
|
[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
|
|
|
%scevgep = getelementptr %struct.Foo, %struct.Foo* %this, i32 1
|
2010-09-14 16:50:43 +08:00
|
|
|
br label %tailrecurse
|
|
|
|
|
|
|
|
|
|
tailrecurse: ; preds = %sw.bb, %entry
|
|
|
|
|
%lsr.iv2 = phi %struct.Foo* [ %scevgep3, %sw.bb ], [ %scevgep, %entry ]
|
|
|
|
|
%lsr.iv = phi i32 [ %lsr.iv.next, %sw.bb ], [ 1, %entry ]
|
|
|
|
|
%acc.tr = phi i32 [ %or, %sw.bb ], [ %acc, %entry ]
|
|
|
|
|
%lsr.iv24 = bitcast %struct.Foo* %lsr.iv2 to i8**
|
[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
|
|
|
%scevgep5 = getelementptr i8*, i8** %lsr.iv24, i32 -1
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp2 = load i8*, i8** %scevgep5
|
2010-09-14 16:50:43 +08:00
|
|
|
%0 = ptrtoint i8* %tmp2 to i32
|
|
|
|
|
|
2011-04-30 09:37:52 +08:00
|
|
|
; ARM: ands {{r[0-9]+}}, {{r[0-9]+}}, #3
|
When we look at instructions to convert to setting the 's' flag, we need to look
at more than those which define CPSR. You can have this situation:
(1) subs ...
(2) sub r6, r5, r4
(3) movge ...
(4) cmp r6, 0
(5) movge ...
We cannot convert (2) to "subs" because (3) is using the CPSR set by
(1). There's an analogous situation here:
(1) sub r1, r2, r3
(2) sub r4, r5, r6
(3) cmp r4, ...
(5) movge ...
(6) cmp r1, ...
(7) movge ...
We cannot convert (1) to "subs" because of the intervening use of CPSR.
llvm-svn: 117950
2010-11-02 04:41:43 +08:00
|
|
|
; ARM-NEXT: beq
|
2010-09-14 16:50:43 +08:00
|
|
|
|
2011-04-01 06:14:03 +08:00
|
|
|
; THUMB: movs r[[R0:[0-9]+]], #3
|
|
|
|
|
; THUMB-NEXT: ands r[[R0]], r
|
|
|
|
|
; THUMB-NEXT: cmp r[[R0]], #0
|
2010-09-29 18:45:43 +08:00
|
|
|
; THUMB-NEXT: beq
|
2010-09-29 18:12:08 +08:00
|
|
|
|
2011-04-30 09:37:52 +08:00
|
|
|
; T2: ands {{r[0-9]+}}, {{r[0-9]+}}, #3
|
2010-09-29 18:45:43 +08:00
|
|
|
; T2-NEXT: beq
|
2010-09-14 16:50:43 +08:00
|
|
|
|
|
|
|
|
%and = and i32 %0, 3
|
|
|
|
|
%tst = icmp eq i32 %and, 0
|
|
|
|
|
br i1 %tst, label %sw.bb, label %tailrecurse.switch
|
|
|
|
|
|
|
|
|
|
tailrecurse.switch: ; preds = %tailrecurse
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8-LABEL: %tailrecurse.switch
|
|
|
|
|
; V8: cmp
|
|
|
|
|
; V8-NEXT: beq
|
|
|
|
|
; V8-NEXT: %tailrecurse.switch
|
|
|
|
|
; V8: cmp
|
|
|
|
|
; V8-NEXT: beq
|
|
|
|
|
; V8-NEXT: %tailrecurse.switch
|
|
|
|
|
; V8: cmp
|
2016-06-07 23:17:21 +08:00
|
|
|
; V8-NEXT: bne
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8-NEXT: b
|
|
|
|
|
; The trailing space in the last line checks that the branch is unconditional
|
2010-09-14 16:50:43 +08:00
|
|
|
switch i32 %and, label %sw.epilog [
|
|
|
|
|
i32 1, label %sw.bb
|
|
|
|
|
i32 3, label %sw.bb6
|
|
|
|
|
i32 2, label %sw.bb8
|
2015-04-28 07:35:22 +08:00
|
|
|
], !prof !1
|
2010-09-14 16:50:43 +08:00
|
|
|
|
|
|
|
|
sw.bb: ; preds = %tailrecurse.switch, %tailrecurse
|
|
|
|
|
%shl = shl i32 %acc.tr, 1
|
|
|
|
|
%or = or i32 %and, %shl
|
|
|
|
|
%lsr.iv.next = add i32 %lsr.iv, 1
|
[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
|
|
|
%scevgep3 = getelementptr %struct.Foo, %struct.Foo* %lsr.iv2, i32 1
|
2010-09-14 16:50:43 +08:00
|
|
|
br label %tailrecurse
|
|
|
|
|
|
|
|
|
|
sw.bb6: ; preds = %tailrecurse.switch
|
|
|
|
|
ret %struct.Foo* %lsr.iv2
|
|
|
|
|
|
|
|
|
|
sw.bb8: ; preds = %tailrecurse.switch
|
|
|
|
|
%tmp1 = add i32 %acc.tr, %lsr.iv
|
[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
|
|
|
%add.ptr11 = getelementptr inbounds %struct.Foo, %struct.Foo* %this, i32 %tmp1
|
2010-09-14 16:50:43 +08:00
|
|
|
ret %struct.Foo* %add.ptr11
|
|
|
|
|
|
|
|
|
|
sw.epilog: ; preds = %tailrecurse.switch
|
|
|
|
|
ret %struct.Foo* undef
|
|
|
|
|
}
|
2010-10-15 11:23:44 +08:00
|
|
|
|
|
|
|
|
; Another test that exercises the AND/TST peephole optimization and also
|
|
|
|
|
; generates a predicated ANDS instruction. Check that the predicate is printed
|
|
|
|
|
; after the "S" modifier on the instruction.
|
|
|
|
|
|
|
|
|
|
%struct.S = type { i8* (i8*)*, [1 x i8] }
|
|
|
|
|
|
2015-04-29 06:03:55 +08:00
|
|
|
; ARM-LABEL: bar:
|
|
|
|
|
; THUMB-LABEL: bar:
|
|
|
|
|
; T2-LABEL: bar:
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8-LABEL: bar:
|
2010-10-15 11:23:44 +08:00
|
|
|
define internal zeroext i8 @bar(%struct.S* %x, %struct.S* nocapture %y) nounwind readonly {
|
|
|
|
|
entry:
|
[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
|
|
|
%0 = getelementptr inbounds %struct.S, %struct.S* %x, i32 0, i32 1, i32 0
|
2015-02-28 05:17:42 +08:00
|
|
|
%1 = load i8, i8* %0, align 1
|
2010-10-15 11:23:44 +08:00
|
|
|
%2 = zext i8 %1 to i32
|
When we look at instructions to convert to setting the 's' flag, we need to look
at more than those which define CPSR. You can have this situation:
(1) subs ...
(2) sub r6, r5, r4
(3) movge ...
(4) cmp r6, 0
(5) movge ...
We cannot convert (2) to "subs" because (3) is using the CPSR set by
(1). There's an analogous situation here:
(1) sub r1, r2, r3
(2) sub r4, r5, r6
(3) cmp r4, ...
(5) movge ...
(6) cmp r1, ...
(7) movge ...
We cannot convert (1) to "subs" because of the intervening use of CPSR.
llvm-svn: 117950
2010-11-02 04:41:43 +08:00
|
|
|
; ARM: ands
|
2010-10-15 11:23:44 +08:00
|
|
|
; THUMB: ands
|
|
|
|
|
; T2: ands
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8: ands
|
|
|
|
|
; V8-NEXT: beq
|
2010-10-15 11:23:44 +08:00
|
|
|
%3 = and i32 %2, 112
|
|
|
|
|
%4 = icmp eq i32 %3, 0
|
|
|
|
|
br i1 %4, label %return, label %bb
|
|
|
|
|
|
|
|
|
|
bb: ; preds = %entry
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8-NEXT: %bb
|
[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
|
|
|
%5 = getelementptr inbounds %struct.S, %struct.S* %y, i32 0, i32 1, i32 0
|
2015-02-28 05:17:42 +08:00
|
|
|
%6 = load i8, i8* %5, align 1
|
2010-10-15 11:23:44 +08:00
|
|
|
%7 = zext i8 %6 to i32
|
When we look at instructions to convert to setting the 's' flag, we need to look
at more than those which define CPSR. You can have this situation:
(1) subs ...
(2) sub r6, r5, r4
(3) movge ...
(4) cmp r6, 0
(5) movge ...
We cannot convert (2) to "subs" because (3) is using the CPSR set by
(1). There's an analogous situation here:
(1) sub r1, r2, r3
(2) sub r4, r5, r6
(3) cmp r4, ...
(5) movge ...
(6) cmp r1, ...
(7) movge ...
We cannot convert (1) to "subs" because of the intervening use of CPSR.
llvm-svn: 117950
2010-11-02 04:41:43 +08:00
|
|
|
; ARM: andsne
|
2010-10-15 11:23:44 +08:00
|
|
|
; THUMB: ands
|
|
|
|
|
; T2: andsne
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8: ands
|
|
|
|
|
; V8-NEXT: beq
|
2010-10-15 11:23:44 +08:00
|
|
|
%8 = and i32 %7, 112
|
|
|
|
|
%9 = icmp eq i32 %8, 0
|
|
|
|
|
br i1 %9, label %return, label %bb2
|
|
|
|
|
|
|
|
|
|
bb2: ; preds = %bb
|
2013-09-09 22:21:49 +08:00
|
|
|
; V8-NEXT: %bb2
|
|
|
|
|
; V8-NEXT: cmp
|
|
|
|
|
; V8-NEXT: it ne
|
|
|
|
|
; V8-NEXT: cmpne
|
|
|
|
|
; V8-NEXT: bne
|
2010-10-15 11:23:44 +08:00
|
|
|
%10 = icmp eq i32 %3, 16
|
|
|
|
|
%11 = icmp eq i32 %8, 16
|
|
|
|
|
%or.cond = or i1 %10, %11
|
|
|
|
|
br i1 %or.cond, label %bb4, label %return
|
|
|
|
|
|
|
|
|
|
bb4: ; preds = %bb2
|
|
|
|
|
%12 = ptrtoint %struct.S* %x to i32
|
|
|
|
|
%phitmp = trunc i32 %12 to i8
|
|
|
|
|
ret i8 %phitmp
|
|
|
|
|
|
|
|
|
|
return: ; preds = %bb2, %bb, %entry
|
|
|
|
|
ret i8 1
|
|
|
|
|
}
|
2015-04-28 07:35:22 +08:00
|
|
|
|
2015-04-29 06:03:55 +08:00
|
|
|
|
|
|
|
|
; We were looking through multiple COPY instructions to find an AND we might
|
|
|
|
|
; fold into a TST, but in doing so we changed the register being tested allowing
|
|
|
|
|
; folding of unrelated tests (in this case, a TST against r1 was eliminated in
|
|
|
|
|
; favour of an AND of r0).
|
|
|
|
|
|
|
|
|
|
; ARM-LABEL: test_tst_assessment:
|
|
|
|
|
; THUMB-LABEL: test_tst_assessment:
|
|
|
|
|
; T2-LABEL: test_tst_assessment:
|
|
|
|
|
; V8-LABEL: test_tst_assessment:
|
|
|
|
|
define i32 @test_tst_assessment(i1 %lhs, i1 %rhs) {
|
|
|
|
|
%lhs32 = zext i1 %lhs to i32
|
|
|
|
|
%rhs32 = zext i1 %rhs to i32
|
|
|
|
|
%diff = sub nsw i32 %lhs32, %rhs32
|
|
|
|
|
; ARM: tst r1, #1
|
|
|
|
|
; THUMB: movs [[RTMP:r[0-9]+]], #1
|
|
|
|
|
; THUMB: tst r1, [[RTMP]]
|
|
|
|
|
; T2: tst.w r1, #1
|
|
|
|
|
; V8: tst.w r1, #1
|
|
|
|
|
ret i32 %diff
|
|
|
|
|
}
|
|
|
|
|
|
2015-04-28 07:35:22 +08:00
|
|
|
!1 = !{!"branch_weights", i32 1, i32 1, i32 3, i32 2 }
|