2010-04-13 05:13:43 +08:00
|
|
|
; RUN: opt -indvars -S < %s | FileCheck %s
|
|
|
|
|
|
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
|
|
|
|
|
|
|
|
|
|
@main.flags = internal global [8193 x i8] zeroinitializer, align 1 ; <[8193 x i8]*> [#uses=5]
|
|
|
|
|
@.str = private constant [11 x i8] c"Count: %d\0A\00" ; <[11 x i8]*> [#uses=1]
|
|
|
|
|
|
|
|
|
|
; Indvars shouldn't emit a udiv here, because there's no udiv in the
|
|
|
|
|
; original code. This comes from SingleSource/Benchmarks/Shootout/sieve.c.
|
|
|
|
|
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @main(
|
2010-04-13 05:13:43 +08:00
|
|
|
; CHECK-NOT: div
|
|
|
|
|
|
|
|
|
|
define i32 @main(i32 %argc, i8** nocapture %argv) nounwind {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp = icmp eq i32 %argc, 2 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp, label %cond.true, label %while.cond.preheader
|
|
|
|
|
|
|
|
|
|
cond.true: ; preds = %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
|
|
|
%arrayidx = getelementptr inbounds i8*, i8** %argv, i64 1 ; <i8**> [#uses=1]
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp2 = load i8*, i8** %arrayidx ; <i8*> [#uses=1]
|
2010-04-13 05:13:43 +08:00
|
|
|
%call = tail call i32 @atoi(i8* %tmp2) nounwind readonly ; <i32> [#uses=1]
|
|
|
|
|
br label %while.cond.preheader
|
|
|
|
|
|
|
|
|
|
while.cond.preheader: ; preds = %entry, %cond.true
|
|
|
|
|
%NUM.0.ph = phi i32 [ %call, %cond.true ], [ 170000, %entry ] ; <i32> [#uses=2]
|
|
|
|
|
%tobool18 = icmp eq i32 %NUM.0.ph, 0 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %tobool18, label %while.end, label %bb.nph30
|
|
|
|
|
|
|
|
|
|
while.cond.loopexit: ; preds = %for.cond12.while.cond.loopexit_crit_edge, %for.cond12.loopexit
|
|
|
|
|
%count.2.lcssa = phi i32 [ %count.1.lcssa, %for.cond12.while.cond.loopexit_crit_edge ], [ 0, %for.cond12.loopexit ] ; <i32> [#uses=1]
|
|
|
|
|
br label %while.cond
|
|
|
|
|
|
|
|
|
|
while.cond: ; preds = %while.cond.loopexit
|
|
|
|
|
%tobool = icmp eq i32 %dec19, 0 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %tobool, label %while.cond.while.end_crit_edge, label %for.cond.preheader
|
|
|
|
|
|
|
|
|
|
while.cond.while.end_crit_edge: ; preds = %while.cond
|
|
|
|
|
%count.2.lcssa.lcssa = phi i32 [ %count.2.lcssa, %while.cond ] ; <i32> [#uses=1]
|
|
|
|
|
br label %while.end
|
|
|
|
|
|
|
|
|
|
bb.nph30: ; preds = %while.cond.preheader
|
|
|
|
|
br label %for.cond.preheader
|
|
|
|
|
|
|
|
|
|
for.cond.preheader: ; preds = %bb.nph30, %while.cond
|
|
|
|
|
%dec19.in = phi i32 [ %NUM.0.ph, %bb.nph30 ], [ %dec19, %while.cond ] ; <i32> [#uses=1]
|
|
|
|
|
%dec19 = add i32 %dec19.in, -1 ; <i32> [#uses=2]
|
|
|
|
|
br i1 true, label %bb.nph, label %for.cond12.loopexit
|
|
|
|
|
|
|
|
|
|
for.cond: ; preds = %for.body
|
|
|
|
|
%cmp8 = icmp slt i64 %inc, 8193 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp8, label %for.body, label %for.cond.for.cond12.loopexit_crit_edge
|
|
|
|
|
|
|
|
|
|
for.cond.for.cond12.loopexit_crit_edge: ; preds = %for.cond
|
|
|
|
|
br label %for.cond12.loopexit
|
|
|
|
|
|
|
|
|
|
bb.nph: ; preds = %for.cond.preheader
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %bb.nph, %for.cond
|
|
|
|
|
%i.02 = phi i64 [ 2, %bb.nph ], [ %inc, %for.cond ] ; <i64> [#uses=2]
|
[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
|
|
|
%arrayidx10 = getelementptr inbounds [8193 x i8], [8193 x i8]* @main.flags, i64 0, i64 %i.02 ; <i8*> [#uses=1]
|
2010-04-13 05:13:43 +08:00
|
|
|
store i8 1, i8* %arrayidx10
|
|
|
|
|
%inc = add nsw i64 %i.02, 1 ; <i64> [#uses=2]
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.cond12.loopexit: ; preds = %for.cond.for.cond12.loopexit_crit_edge, %for.cond.preheader
|
|
|
|
|
br i1 true, label %bb.nph16, label %while.cond.loopexit
|
|
|
|
|
|
|
|
|
|
for.cond12: ; preds = %for.inc35
|
|
|
|
|
%cmp14 = icmp slt i64 %inc37, 8193 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp14, label %for.body15, label %for.cond12.while.cond.loopexit_crit_edge
|
|
|
|
|
|
|
|
|
|
for.cond12.while.cond.loopexit_crit_edge: ; preds = %for.cond12
|
|
|
|
|
%count.1.lcssa = phi i32 [ %count.1, %for.cond12 ] ; <i32> [#uses=1]
|
|
|
|
|
br label %while.cond.loopexit
|
|
|
|
|
|
|
|
|
|
bb.nph16: ; preds = %for.cond12.loopexit
|
|
|
|
|
br label %for.body15
|
|
|
|
|
|
|
|
|
|
for.body15: ; preds = %bb.nph16, %for.cond12
|
|
|
|
|
%count.212 = phi i32 [ 0, %bb.nph16 ], [ %count.1, %for.cond12 ] ; <i32> [#uses=2]
|
|
|
|
|
%i.17 = phi i64 [ 2, %bb.nph16 ], [ %inc37, %for.cond12 ] ; <i64> [#uses=4]
|
[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
|
|
|
%arrayidx17 = getelementptr inbounds [8193 x i8], [8193 x i8]* @main.flags, i64 0, i64 %i.17 ; <i8*> [#uses=1]
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp18 = load i8, i8* %arrayidx17 ; <i8> [#uses=1]
|
2010-04-13 05:13:43 +08:00
|
|
|
%tobool19 = icmp eq i8 %tmp18, 0 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %tobool19, label %for.inc35, label %if.then
|
|
|
|
|
|
|
|
|
|
if.then: ; preds = %for.body15
|
|
|
|
|
%add = shl i64 %i.17, 1 ; <i64> [#uses=2]
|
|
|
|
|
%cmp243 = icmp slt i64 %add, 8193 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp243, label %bb.nph5, label %for.end32
|
|
|
|
|
|
|
|
|
|
for.cond22: ; preds = %for.body25
|
|
|
|
|
%cmp24 = icmp slt i64 %add31, 8193 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp24, label %for.body25, label %for.cond22.for.end32_crit_edge
|
|
|
|
|
|
|
|
|
|
for.cond22.for.end32_crit_edge: ; preds = %for.cond22
|
|
|
|
|
br label %for.end32
|
|
|
|
|
|
|
|
|
|
bb.nph5: ; preds = %if.then
|
|
|
|
|
br label %for.body25
|
|
|
|
|
|
|
|
|
|
for.body25: ; preds = %bb.nph5, %for.cond22
|
|
|
|
|
%k.04 = phi i64 [ %add, %bb.nph5 ], [ %add31, %for.cond22 ] ; <i64> [#uses=2]
|
[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
|
|
|
%arrayidx27 = getelementptr inbounds [8193 x i8], [8193 x i8]* @main.flags, i64 0, i64 %k.04 ; <i8*> [#uses=1]
|
2010-04-13 05:13:43 +08:00
|
|
|
store i8 0, i8* %arrayidx27
|
|
|
|
|
%add31 = add nsw i64 %k.04, %i.17 ; <i64> [#uses=2]
|
|
|
|
|
br label %for.cond22
|
|
|
|
|
|
|
|
|
|
for.end32: ; preds = %for.cond22.for.end32_crit_edge, %if.then
|
|
|
|
|
%inc34 = add nsw i32 %count.212, 1 ; <i32> [#uses=1]
|
|
|
|
|
br label %for.inc35
|
|
|
|
|
|
|
|
|
|
for.inc35: ; preds = %for.body15, %for.end32
|
|
|
|
|
%count.1 = phi i32 [ %inc34, %for.end32 ], [ %count.212, %for.body15 ] ; <i32> [#uses=2]
|
|
|
|
|
%inc37 = add nsw i64 %i.17, 1 ; <i64> [#uses=2]
|
|
|
|
|
br label %for.cond12
|
|
|
|
|
|
|
|
|
|
while.end: ; preds = %while.cond.while.end_crit_edge, %while.cond.preheader
|
|
|
|
|
%count.0.lcssa = phi i32 [ %count.2.lcssa.lcssa, %while.cond.while.end_crit_edge ], [ 0, %while.cond.preheader ] ; <i32> [#uses=1]
|
[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction
See r230786 and r230794 for similar changes to gep and load
respectively.
Call is a bit different because it often doesn't have a single explicit
type - usually the type is deduced from the arguments, and just the
return type is explicit. In those cases there's no need to change the
IR.
When that's not the case, the IR usually contains the pointer type of
the first operand - but since typed pointers are going away, that
representation is insufficient so I'm just stripping the "pointerness"
of the explicit type away.
This does make the IR a bit weird - it /sort of/ reads like the type of
the first operand: "call void () %x(" but %x is actually of type "void
()*" and will eventually be just of type "ptr". But this seems not too
bad and I don't think it would benefit from repeating the type
("void (), void () * %x(" and then eventually "void (), ptr %x(") as has
been done with gep and load.
This also has a side benefit: since the explicit type is no longer a
pointer, there's no ambiguity between an explicit type and a function
that returns a function pointer. Previously this case needed an explicit
type (eg: a function returning a void() function was written as
"call void () () * @x(" rather than "call void () * @x(" because of the
ambiguity between a function returning a pointer to a void() function
and a function returning void).
No ambiguity means even function pointer return types can just be
written alone, without writing the whole function's type.
This leaves /only/ the varargs case where the explicit type is required.
Given the special type syntax in call instructions, the regex-fu used
for migration was a bit more involved in its own unique way (as every
one of these is) so here it is. Use it in conjunction with the apply.sh
script and associated find/xargs commands I've provided in rr230786 to
migrate your out of tree tests. Do let me know if any of this doesn't
cover your cases & we can iterate on a more general script/regexes to
help others with out of tree tests.
About 9 test cases couldn't be automatically migrated - half of those
were functions returning function pointers, where I just had to manually
delete the function argument types now that we didn't need an explicit
function type there. The other half were typedefs of function types used
in calls - just had to manually drop the * from those.
import fileinput
import sys
import re
pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)')
addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$")
func_end = re.compile("(?:void.*|\)\s*)\*$")
def conv(match, line):
if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)):
return line
return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():]
for line in sys.stdin:
sys.stdout.write(conv(re.search(pat, line), line))
llvm-svn: 235145
2015-04-17 07:24:18 +08:00
|
|
|
%call40 = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i64 0, i64 0), i32 %count.0.lcssa) nounwind ; <i32> [#uses=0]
|
2010-04-13 05:13:43 +08:00
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i32 @atoi(i8* nocapture) nounwind readonly
|
|
|
|
|
|
|
|
|
|
declare i32 @printf(i8* nocapture, ...) nounwind
|
|
|
|
|
|
[SCEV] Try to reuse existing value during SCEV expansion
Current SCEV expansion will expand SCEV as a sequence of operations
and doesn't utilize the value already existed. This will introduce
redundent computation which may not be cleaned up throughly by
following optimizations.
This patch introduces an ExprValueMap which is a map from SCEV to the
set of equal values with the same SCEV. When a SCEV is expanded, the
set of values is checked and reused whenever possible before generating
a sequence of operations.
The original commit triggered regressions in Polly tests. The regressions
exposed two problems which have been fixed in current version.
1. Polly will generate a new function based on the old one. To generate an
instruction for the new function, it builds SCEV for the old instruction,
applies some tranformation on the SCEV generated, then expands the transformed
SCEV and insert the expanded value into new function. Because SCEV expansion
may reuse value cached in ExprValueMap, the value in old function may be
inserted into new function, which is wrong.
In SCEVExpander::expand, there is a logic to check the cached value to
be used should dominate the insertion point. However, for the above
case, the check always passes. That is because the insertion point is
in a new function, which is unreachable from the old function. However
for unreachable node, DominatorTreeBase::dominates thinks it will be
dominated by any other node.
The fix is to simply add a check that the cached value to be used in
expansion should be in the same function as the insertion point instruction.
2. When the SCEV is of scConstant type, expanding it directly is cheaper than
reusing a normal value cached. Although in the cached value set in ExprValueMap,
there is a Constant type value, but it is not easy to find it out -- the cached
Value set is not sorted according to the potential cost. Existing reuse logic
in SCEVExpander::expand simply chooses the first legal element from the cached
value set.
The fix is that when the SCEV is of scConstant type, don't try the reuse
logic. simply expand it.
Differential Revision: http://reviews.llvm.org/D12090
llvm-svn: 259736
2016-02-04 09:27:38 +08:00
|
|
|
; IndVars doesn't emit a udiv in for.body.preheader since SCEVExpander::expand will
|
|
|
|
|
; find out there's already a udiv in the original code.
|
2010-04-13 05:13:43 +08:00
|
|
|
|
2017-10-27 12:17:44 +08:00
|
|
|
; CHECK-LABEL: @foo(
|
2010-04-13 05:13:43 +08:00
|
|
|
; CHECK: for.body.preheader:
|
[SCEV] Try to reuse existing value during SCEV expansion
Current SCEV expansion will expand SCEV as a sequence of operations
and doesn't utilize the value already existed. This will introduce
redundent computation which may not be cleaned up throughly by
following optimizations.
This patch introduces an ExprValueMap which is a map from SCEV to the
set of equal values with the same SCEV. When a SCEV is expanded, the
set of values is checked and reused whenever possible before generating
a sequence of operations.
The original commit triggered regressions in Polly tests. The regressions
exposed two problems which have been fixed in current version.
1. Polly will generate a new function based on the old one. To generate an
instruction for the new function, it builds SCEV for the old instruction,
applies some tranformation on the SCEV generated, then expands the transformed
SCEV and insert the expanded value into new function. Because SCEV expansion
may reuse value cached in ExprValueMap, the value in old function may be
inserted into new function, which is wrong.
In SCEVExpander::expand, there is a logic to check the cached value to
be used should dominate the insertion point. However, for the above
case, the check always passes. That is because the insertion point is
in a new function, which is unreachable from the old function. However
for unreachable node, DominatorTreeBase::dominates thinks it will be
dominated by any other node.
The fix is to simply add a check that the cached value to be used in
expansion should be in the same function as the insertion point instruction.
2. When the SCEV is of scConstant type, expanding it directly is cheaper than
reusing a normal value cached. Although in the cached value set in ExprValueMap,
there is a Constant type value, but it is not easy to find it out -- the cached
Value set is not sorted according to the potential cost. Existing reuse logic
in SCEVExpander::expand simply chooses the first legal element from the cached
value set.
The fix is that when the SCEV is of scConstant type, don't try the reuse
logic. simply expand it.
Differential Revision: http://reviews.llvm.org/D12090
llvm-svn: 259736
2016-02-04 09:27:38 +08:00
|
|
|
; CHECK-NOT: udiv
|
2010-04-13 05:13:43 +08:00
|
|
|
|
2017-10-27 12:17:44 +08:00
|
|
|
define void @foo(double* %p, i64 %n) nounwind {
|
2010-04-13 05:13:43 +08:00
|
|
|
entry:
|
|
|
|
|
%div0 = udiv i64 %n, 7 ; <i64> [#uses=1]
|
|
|
|
|
%div1 = add i64 %div0, 1
|
|
|
|
|
%cmp2 = icmp ult i64 0, %div1 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp2, label %for.body.preheader, label %for.end
|
|
|
|
|
|
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.body
|
|
|
|
|
%i.03 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ] ; <i64> [#uses=2]
|
[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
|
|
|
%arrayidx = getelementptr inbounds double, double* %p, i64 %i.03 ; <double*> [#uses=1]
|
2010-04-13 05:13:43 +08:00
|
|
|
store double 0.000000e+00, double* %arrayidx
|
|
|
|
|
%inc = add i64 %i.03, 1 ; <i64> [#uses=2]
|
|
|
|
|
%divx = udiv i64 %n, 7 ; <i64> [#uses=1]
|
|
|
|
|
%div = add i64 %divx, 1
|
|
|
|
|
%cmp = icmp ult i64 %inc, %div ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp, label %for.body, label %for.end.loopexit
|
|
|
|
|
|
|
|
|
|
for.end.loopexit: ; preds = %for.body
|
|
|
|
|
br label %for.end
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.end.loopexit, %entry
|
|
|
|
|
ret void
|
|
|
|
|
}
|