2014-03-30 13:01:04 +08:00
|
|
|
; RUN: llc < %s -O3 -mtriple=arm64-unknown-unknown -mcpu=cyclone -pre-RA-sched=list-hybrid | FileCheck %s
|
2014-03-29 18:18:08 +08:00
|
|
|
; <rdar://problem/11635990> [arm64] [lsr] Inefficient EA/loop-exit calc in bzero_phys
|
|
|
|
|
;
|
|
|
|
|
; LSR on loop %while.cond should reassociate non-address mode
|
|
|
|
|
; expressions at use %cmp16 to avoid sinking computation into %while.body18.
|
|
|
|
|
;
|
|
|
|
|
; Remove the -pre-RA-sched=list-hybrid option after fixing:
|
|
|
|
|
; <rdar://problem/12702735> [ARM64][coalescer] need better register
|
|
|
|
|
; coalescing for simple unit tests.
|
|
|
|
|
|
|
|
|
|
; CHECK: @memset
|
|
|
|
|
; CHECK: %while.body18{{$}}
|
|
|
|
|
; CHECK: str x{{[0-9]+}}, [x{{[0-9]+}}], #8
|
|
|
|
|
; First set the IVREG variable, then use it
|
|
|
|
|
; CHECK-NEXT: sub [[IVREG:x[0-9]+]],
|
|
|
|
|
; CHECK: [[IVREG]], #8
|
|
|
|
|
; CHECK-NEXT: cmp [[IVREG]], #7
|
|
|
|
|
; CHECK-NEXT: b.hi
|
|
|
|
|
define i8* @memset(i8* %dest, i32 %val, i64 %len) nounwind ssp noimplicitfloat {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp = icmp eq i64 %len, 0
|
|
|
|
|
br i1 %cmp, label %done, label %while.cond.preheader
|
|
|
|
|
|
|
|
|
|
while.cond.preheader: ; preds = %entry
|
|
|
|
|
%conv = trunc i32 %val to i8
|
|
|
|
|
br label %while.cond
|
|
|
|
|
|
|
|
|
|
while.cond: ; preds = %while.body, %while.cond.preheader
|
|
|
|
|
%ptr.0 = phi i8* [ %incdec.ptr, %while.body ], [ %dest, %while.cond.preheader ]
|
|
|
|
|
%len.addr.0 = phi i64 [ %dec, %while.body ], [ %len, %while.cond.preheader ]
|
|
|
|
|
%cond = icmp eq i64 %len.addr.0, 0
|
|
|
|
|
br i1 %cond, label %done, label %land.rhs
|
|
|
|
|
|
|
|
|
|
land.rhs: ; preds = %while.cond
|
|
|
|
|
%0 = ptrtoint i8* %ptr.0 to i64
|
|
|
|
|
%and = and i64 %0, 7
|
|
|
|
|
%cmp5 = icmp eq i64 %and, 0
|
|
|
|
|
br i1 %cmp5, label %if.end9, label %while.body
|
|
|
|
|
|
|
|
|
|
while.body: ; preds = %land.rhs
|
[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
|
|
|
%incdec.ptr = getelementptr inbounds i8, i8* %ptr.0, i64 1
|
2014-03-29 18:18:08 +08:00
|
|
|
store i8 %conv, i8* %ptr.0, align 1, !tbaa !0
|
|
|
|
|
%dec = add i64 %len.addr.0, -1
|
|
|
|
|
br label %while.cond
|
|
|
|
|
|
|
|
|
|
if.end9: ; preds = %land.rhs
|
|
|
|
|
%conv.mask = and i32 %val, 255
|
|
|
|
|
%1 = zext i32 %conv.mask to i64
|
|
|
|
|
%2 = shl nuw nsw i64 %1, 8
|
|
|
|
|
%ins18 = or i64 %2, %1
|
|
|
|
|
%3 = shl nuw nsw i64 %1, 16
|
|
|
|
|
%ins15 = or i64 %ins18, %3
|
|
|
|
|
%4 = shl nuw nsw i64 %1, 24
|
|
|
|
|
%5 = shl nuw nsw i64 %1, 32
|
|
|
|
|
%mask8 = or i64 %ins15, %4
|
|
|
|
|
%6 = shl nuw nsw i64 %1, 40
|
|
|
|
|
%mask5 = or i64 %mask8, %5
|
|
|
|
|
%7 = shl nuw nsw i64 %1, 48
|
|
|
|
|
%8 = shl nuw i64 %1, 56
|
|
|
|
|
%mask2.masked = or i64 %mask5, %6
|
|
|
|
|
%mask = or i64 %mask2.masked, %7
|
|
|
|
|
%ins = or i64 %mask, %8
|
|
|
|
|
%9 = bitcast i8* %ptr.0 to i64*
|
|
|
|
|
%cmp1636 = icmp ugt i64 %len.addr.0, 7
|
|
|
|
|
br i1 %cmp1636, label %while.body18, label %while.body29.lr.ph
|
|
|
|
|
|
|
|
|
|
while.body18: ; preds = %if.end9, %while.body18
|
|
|
|
|
%wideptr.038 = phi i64* [ %incdec.ptr19, %while.body18 ], [ %9, %if.end9 ]
|
|
|
|
|
%len.addr.137 = phi i64 [ %sub, %while.body18 ], [ %len.addr.0, %if.end9 ]
|
[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
|
|
|
%incdec.ptr19 = getelementptr inbounds i64, i64* %wideptr.038, i64 1
|
2014-03-29 18:18:08 +08:00
|
|
|
store i64 %ins, i64* %wideptr.038, align 8, !tbaa !2
|
|
|
|
|
%sub = add i64 %len.addr.137, -8
|
|
|
|
|
%cmp16 = icmp ugt i64 %sub, 7
|
|
|
|
|
br i1 %cmp16, label %while.body18, label %while.end20
|
|
|
|
|
|
|
|
|
|
while.end20: ; preds = %while.body18
|
|
|
|
|
%cmp21 = icmp eq i64 %sub, 0
|
|
|
|
|
br i1 %cmp21, label %done, label %while.body29.lr.ph
|
|
|
|
|
|
|
|
|
|
while.body29.lr.ph: ; preds = %while.end20, %if.end9
|
|
|
|
|
%len.addr.1.lcssa49 = phi i64 [ %sub, %while.end20 ], [ %len.addr.0, %if.end9 ]
|
|
|
|
|
%wideptr.0.lcssa48 = phi i64* [ %incdec.ptr19, %while.end20 ], [ %9, %if.end9 ]
|
|
|
|
|
%10 = bitcast i64* %wideptr.0.lcssa48 to i8*
|
|
|
|
|
br label %while.body29
|
|
|
|
|
|
|
|
|
|
while.body29: ; preds = %while.body29, %while.body29.lr.ph
|
|
|
|
|
%len.addr.235 = phi i64 [ %len.addr.1.lcssa49, %while.body29.lr.ph ], [ %dec26, %while.body29 ]
|
|
|
|
|
%ptr.134 = phi i8* [ %10, %while.body29.lr.ph ], [ %incdec.ptr31, %while.body29 ]
|
|
|
|
|
%dec26 = add i64 %len.addr.235, -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
|
|
|
%incdec.ptr31 = getelementptr inbounds i8, i8* %ptr.134, i64 1
|
2014-03-29 18:18:08 +08:00
|
|
|
store i8 %conv, i8* %ptr.134, align 1, !tbaa !0
|
|
|
|
|
%cmp27 = icmp eq i64 %dec26, 0
|
|
|
|
|
br i1 %cmp27, label %done, label %while.body29
|
|
|
|
|
|
|
|
|
|
done: ; preds = %while.cond, %while.body29, %while.end20, %entry
|
|
|
|
|
ret i8* %dest
|
|
|
|
|
}
|
|
|
|
|
|
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
|
|
|
!0 = !{!"omnipotent char", !1}
|
|
|
|
|
!1 = !{!"Simple C/C++ TBAA"}
|
|
|
|
|
!2 = !{!"long long", !0}
|